← Back to search

Search • Shortlists • Rankings • Digests • Backfill • Incident feed • MCP API

ai.com.mcp/openai-tools

OpenAI Tools MCP Server

Focused MCP server for OpenAI image/audio generation (v2.0.0). Wraps endpoints via HAPI CLI.

JSON report • History API • Manage this server • Global feed

Status

Healthy

Score

72.5

Transport

streamable-http

Tools

Production readiness

Verdict

Needs remediation

Current validation evidence shows operational or discovery gaps that should be fixed first.

Critical alerts

Production verdicts degrade quickly when critical alerts are active.

Evidence confidence

Confidence score

65.0

Based on 20 recent validations, 26 captured checks, and validation age of 606.0 hours.

Live checks captured

More direct checks increase trust in the current verdict.

Validation age

606.0h

Lower age means fresher evidence.

Recommended for

Claude Desktop

Claude Desktop is marked compatible with score 83.

Smithery

Smithery is marked compatible with score 80.

Generic Streamable HTTP

Generic Streamable HTTP is marked compatible with score 100.

Client readiness verdicts

Ready for ChatGPT custom connector

Partial

OpenAI connectors expect OAuth for remote server auth.; Dynamic client registration materially improves connector setup.; Transport compliance should be in good shape.

Confidence: medium (65.0)

Evidence provenance

Winner: live_validation

Supporting sources: live_validation, history, server_card

Disagreements: none

initialize • OK
tools_list • OK
transport_compliance_probe • Error
step_up_auth_probe • Missing
connector_replay_probe • OK — Frozen tool snapshots must survive refresh.
request_association_probe • Missing — Roots, sampling, and elicitation should stay request-scoped.

Ready for Claude remote MCP

Ready

Transport behavior should match Claude-compatible HTTP expectations.

Confidence: medium (65.0)

Evidence provenance

Winner: live_validation

Supporting sources: live_validation, history, server_card

Disagreements: none

initialize • OK
tools_list • OK
transport_compliance_probe • Error

Unsafe for write actions

Yes

High-risk write, exec, or destructive tools need stronger auth and confirmation semantics.

Confidence: medium (65.0)

Evidence provenance

Winner: live_validation

Supporting sources: live_validation, history

Disagreements: none

action_safety_probe • Error

Snapshot churn risk

Low

No material tool-surface churn detected in the latest comparison.

Confidence: medium (65.0)

Evidence provenance

Winner: history

Supporting sources: history, live_validation

Disagreements: none

tool_snapshot_probe • OK
connector_replay_probe • OK

Why not ready by client

ChatGPT custom connector

Partial

Remediation checklist

No explicit blockers recorded.

Claude remote MCP

Ready

Remediation checklist

No explicit blockers recorded.

Write-safe publishing

Blocked

Remediation checklist

No explicit blockers recorded.

Verdict traces

Production verdict

Needs remediation

Current validation evidence shows operational or discovery gaps that should be fixed first.

Confidence: medium (65.0)

Winning source: live_validation

Triggering alerts

validation_stale • medium • Validation evidence is stale

Client verdict trace table

Verdict	Status	Checks	Winning source	Conflicts
`openai_connectors`	Partial	initialize, tools_list, transport_compliance_probe, step_up_auth_probe, connector_replay_probe, request_association_probe	live_validation	none
`claude_desktop`	Ready	initialize, tools_list, transport_compliance_probe	live_validation	none
`unsafe_for_write_actions`	Yes	action_safety_probe	live_validation	none
`snapshot_churn_risk`	Low	tool_snapshot_probe, connector_replay_probe	history	none

Publishability policy profiles

ChatGPT custom connector publishability

Caution

OpenAI connectors expect OAuth for remote server auth.; Dynamic client registration materially improves connector setup.; Transport compliance should be in good shape.

Search Fetch Only: No
Write Actions Present: Yes
Oauth Configured: No
Admin Refresh Required: No
Safe For Company Knowledge: No
Safe For Messages Api Remote Mcp: No

Claude remote MCP publishability

Ready

Transport behavior should match Claude-compatible HTTP expectations.

Search Fetch Only: No
Write Actions Present: Yes
Oauth Configured: No
Admin Refresh Required: No
Safe For Company Knowledge: No
Safe For Messages Api Remote Mcp: No

Compatibility fixtures

ChatGPT custom connector fixture

Degraded

OpenAI connectors expect OAuth for remote server auth.; Dynamic client registration materially improves connector setup.; Transport compliance should be in good shape.

remote_http_endpoint: Passes
oauth_discovery: Degraded
frozen_tool_snapshot_refresh: Passes
request_association: Passes

Anthropic remote MCP fixture

Degraded

Transport behavior should match Claude-compatible HTTP expectations.

remote_transport: Passes
tool_discovery: Passes
auth_connect: Passes
safe_write_review: Degraded

Authenticated validation sessions

Latest profile

remote_mcp

Authenticated session used

Public score isolation

✓

Preview endpoint

/v1/verify

CI preview endpoint

/v1/ci/preview

Public server reputation

Validation success 7d

n/a

Validation success 30d

1.0

Mean time to recover

n/a

Breaking diffs 30d

Registry drift frequency 30d

Snapshot changes 30d

Incident & change feed

Timestamp	Event	Details
Apr 09, 2026 12:54:01 AM UTC	Latest validation: healthy	Score 72.5 with status healthy.

Capabilities

OAuth: ✕
DCR/CIMD: ✕
Prompts: ✓
Homepage: https://platform.openai.com/docs/api-reference
Docs: none
Support: none
Icon: none
Remote endpoint: https://openai-tools.run.mcp.com.ai/mcp
Server card: none

Use-case taxonomy

other

Security posture

Tools analyzed

High-risk tools

Destructive tools

Exec tools

Egress tools

Secret tools

Bulk-access tools

Risk distribution

low:1, medium:7, high:1

Tool capability & risk inventory

Tool	Capabilities	Risk	Findings	Notes
`createImage`	write	Medium	none	No explicit safeguard hints detected.
`createImageEdit`	write	Medium	none	No explicit safeguard hints detected.
`createImageVariation`	write	Medium	none	No explicit safeguard hints detected.
`createTranscription`	write	Medium	none	No explicit safeguard hints detected.
`createTranslation`	write	Medium	none	No explicit safeguard hints detected.
`listModels`	read	Low	none	No explicit safeguard hints detected.
`retrieveModel`	admin	Medium	none	No explicit safeguard hints detected.
`deleteModel`	write delete admin	High	destructive operation admin mutation	No explicit safeguard hints detected.
`createModeration`	write admin	Medium	admin mutation	No explicit safeguard hints detected.

Write-action governance

Governance status

Error

Safe to publish

Auth boundary

public_or_unclear

Blast radius

Medium

High-risk tools

Confirmation signals

none

Safeguard count

Status detail: 1 high-risk tool(s), 1 destructive tool(s) are exposed without a clear auth boundary; no safeguards or confirmation signals detected.

Tool	Risk	Flags	Safeguards
`deleteModel`	High	destructive operation admin mutation	no

Action-controls diff

Snapshot changed

Disabled-by-default candidates

none

Manual review candidates

none

New actions

Action	Risk	Flags
No newly added actions.

Changed actions

Action	Change types	Risk
No materially changed actions.

Why this score?

Access & Protocol

29.5/44

Connectivity, auth, and transport expectations for common clients.

Interface Quality

35/56

How well the tool/resource interface communicates and behaves under automation.

Security Posture

27/36

How safely the exposed tool surface handles destructive actions, egress, execution, secrets, and risky inputs.

Reliability & Trust

23/24

Operational stability, consistency, and trustworthiness over time.

Discovery & Governance

21.5/28

How well the server is documented, listed, and governed in public registries.

Adoption & Market

6/8

Adoption clues and public evidence that the server is intended for external use.

Algorithmic score breakdown

Auth Operability

2/4

Measures whether auth discovery and protected access behave predictably for clients.

Error Contract Quality

0/4

Grades machine-readable error structure, status alignment, and remediation hints.

Rate-Limit Semantics

2/4

Checks whether quota/throttle responses are deterministic and automation-friendly.

Schema Completeness

2/4

Completeness of tool descriptions, parameter docs, examples, and schema shape.

Backward Compatibility

4/4

Stability score across tool schema/name drift relative to prior validations.

SLO Health

4/4

Availability, latency, and burst-failure profile across recent validation history.

Security Hygiene

4/4

HTTPS posture, endpoint hygiene, and response-surface hardening checks.

Task Success

3/4

Can an agent reliably initialize, enumerate tools, and execute core MCP flows?

Trust Confidence

4/4

Confidence-adjusted reliability score that penalizes low evidence volume.

Abuse/Noise Resilience

4/4

How well the server preserves core behavior in the presence of noisy traffic patterns.

Prompt Contract

3/4

Quality of prompt metadata, argument shape, and prompt discoverability for clients.

Resource Contract

4/4

How completely resources and resource templates describe URIs, types, and usage shape.

Discovery Metadata

4/4

Homepage, docs, icon, repository, support, and license coverage for directory consumers.

Registry Consistency

2/4

Agreement between stored registry metadata, live server-card data, and current validation output.

Installability

3/4

How cleanly a real client can connect, initialize, enumerate tools, and proceed through auth.

Session Semantics

3.5/4

Determinism and state behavior across repeated MCP calls, including sticky-session surprises.

Tool Surface Design

2/4

Naming clarity, schema ergonomics, and parameter complexity across the tool surface.

Result Shape Stability

3/4

Stability of declared output schemas across validations, with penalties for drift or missing shapes.

OAuth Interop

3/4

Depth and client compatibility of OAuth/OIDC metadata beyond the minimal protected-resource check.

Recovery Semantics

0/4

Whether failures include actionable machine-readable next steps such as retry or upgrade guidance.

Maintenance Signal

3/4

Versioning, update recency, and historical validation cadence that indicate active stewardship.

Adoption Signal

3/4

Directory presence and distribution clues that suggest the server is intended for external use.

Freshness Confidence

4/4

Confidence that recent validations are current enough and dense enough to trust operationally.

Transport Fidelity

4/4

Whether declared transport metadata matches the observed endpoint behavior and response formats.

Spec Recency

3/4

How close the server’s claimed MCP protocol version is to the latest known public revision.

Session Resume

3/4

Whether Streamable HTTP session identifiers and resumed requests behave cleanly for real clients.

Step-Up Auth

3/4

Whether OAuth metadata and WWW-Authenticate challenges support granular, incremental consent instead of broad upfront scopes.

Transport Compliance

0/4

Checks session headers, protocol-version enforcement, session teardown, and expired-session behavior.

Utility Coverage

2/4

Signals support for completions, pagination, and task-oriented utility surfaces that larger clients increasingly expect.

Advanced Capability Coverage

3/4

Coverage of newer MCP surfaces like roots, sampling, elicitation, structured output, and related metadata.

Connector Publishability

3/4

How ready the server looks for client catalogs and managed connector programs.

Tool Snapshot Churn

4/4

Stability of the tool surface across recent validations, including add/remove and output-shape drift.

Connector Replay

4/4

Whether a previously published frozen connector snapshot would remain backward compatible after the latest tool refresh.

Request Association

3/4

Whether roots, sampling, and elicitation appear tied to active client requests instead of arriving unsolicited on idle sessions.

Interactive Flow Safety

3/4

Whether prompts and docs steer users toward safe auth flows instead of pasting secrets directly.

Action Safety

2/4

Risk-weighted view of destructive, exec, egress, and confirmation semantics across the tool surface.

Official Registry Presence

4/4

Whether the server appears directly or indirectly in the official MCP registry.

Provenance Divergence

4/4

How closely official registry metadata, the live server card, and public repo/package signals agree with each other.

Safety Transparency

2/4

Clarity of docs, auth disclosure, support links, and other trust signals visible to integrators.

Tool Capability Clarity

3/4

How clearly the tool surface communicates whether each action reads, writes, deletes, executes, or exports data.

Destructive Operation Safety

2/4

Penalizes delete/revoke/destroy style tools unless auth and safeguards reduce blast radius.

Egress / SSRF Resilience

3/4

Assesses arbitrary URL fetch, crawl, webhook, and remote-request exposure on the tool surface.

Execution / Sandbox Safety

4/4

Evaluates shell, code, script, and command-execution exposure and whether that surface appears contained.

Data Exfiltration Resilience

3/4

Assesses export, dump, backup, and bulk-read behavior against the surrounding auth and safeguard signals.

Least Privilege Scope

2/4

Rewards scoped auth metadata and penalizes broad or missing scopes around privileged tools.

Secret Handling Hygiene

3/4

Assesses secret-bearing tools, token leakage risk, and whether the public surface avoids obvious secret exposure.

Supply Chain Signal

2.5/4

Public metadata signal for repository, changelog, license, versioning, and recency that supports supply-chain trust.

Input Sanitization Safety

3/4

Penalizes risky freeform string inputs when schemas do not constrain URLs, code, paths, queries, or templates.

Tool Namespace Clarity

3/4

Measures naming uniqueness and ambiguity across the tool namespace to reduce collision and confusion risk.

Compatibility profiles

OpenAI Connectors

66.7

partial

OpenAI connectors expect OAuth for remote server auth.; Dynamic client registration materially improves connector setup.; Transport compliance should be in good shape.

Connector URL: https://openai-tools.run.mcp.com.ai/mcp
# No OAuth metadata detected.
# Server: ai.com.mcp/openai-tools

Claude Desktop

83.3

compatible

Transport behavior should match Claude-compatible HTTP expectations.

{
  "mcpServers": {
    "openai-tools": {
      "command": "npx",
      "args": ["mcp-remote", "https://openai-tools.run.mcp.com.ai/mcp"]
    }
  }
}

Smithery

80.0

compatible

Machine-readable failure semantics should be present.

smithery mcp add "https://openai-tools.run.mcp.com.ai/mcp"

Generic Streamable HTTP

100.0

compatible

No major blockers detected.

curl -sS https://openai-tools.run.mcp.com.ai/mcp -H 'content-type: application/json' -d '{"jsonrpc":"2.0","id":1,"method":"initialize","params":{"protocolVersion":"2025-03-26","capabilities":{},"clientInfo":{"name":"mcp-verify","version":"0.1.0"}}}'

Actionable remediation

Severity	Remediation	Why it matters	Recommended action
High	Add confirmation and dry-run semantics for risky actions	High-risk write, delete, exec, or egress tools should communicate safeguards clearly.	Inspect the latest validation evidence and resolve the client-visible regression. Playbook Inspect the latest validation evidence. Resolve the highest-severity client-facing gap first. Revalidate and confirm the score and verdict improve.
High	Align session and protocol behavior with Streamable HTTP expectations	Clients increasingly rely on MCP-Protocol-Version, session teardown, and expired-session semantics.	Align MCP-Protocol-Version, MCP-Session-Id, DELETE teardown, and expired-session handling with the transport spec. Playbook Return `Mcp-Session-Id` and `Mcp-Protocol-Version` headers consistently on streamable HTTP responses. Honor `DELETE` session teardown and return `404` when a deleted session is reused. Reject invalid protocol-version headers with `400 Bad Request`.
High	Associate roots, sampling, and elicitation with active client requests	Modern MCP guidance expects roots, sampling, and elicitation traffic to be tied to an active client request instead of arriving unsolicited on idle sessions.	Inspect the latest validation evidence and resolve the client-visible regression. Playbook Inspect the latest validation evidence. Resolve the highest-severity client-facing gap first. Revalidate and confirm the score and verdict improve.
High	Expose /.well-known/oauth-protected-resource	Without a protected-resource document, OAuth clients cannot discover auth requirements reliably.	Serve /.well-known/oauth-protected-resource and point it at your authorization server metadata. Playbook Serve `/.well-known/oauth-protected-resource` from the same host as the MCP endpoint. Point it at the authorization server metadata URL. Confirm clients receive consistent auth hints before tool execution.
High	Publish OAuth authorization-server metadata	Clients need authorization-server metadata to discover issuer, endpoints, and DCR support.	Publish /.well-known/oauth-authorization-server from your issuer and include registration_endpoint when supported. Playbook Publish `/.well-known/oauth-authorization-server` from the issuer. Add `registration_endpoint` if DCR is supported. Verify issuer, authorization, token, and jwks metadata are all reachable.
High	Publish a complete server card	Missing or incomplete server-card metadata weakens discovery, documentation, and trust signals.	Serve /.well-known/mcp/server-card.json and include tools, prompts/resources, homepage, and support links. Playbook Publish `/.well-known/mcp/server-card.json`. Include homepage, repository, support, tools, prompts/resources, and auth metadata. Revalidate the server after publishing the card.
High	Stabilize repeated tools/list responses	Tool enumeration drift causes client caching and planning issues.	Return the same tool surface on repeated tools/list calls unless a real version change occurred. Playbook Inspect the latest validation evidence. Resolve the highest-severity client-facing gap first. Revalidate and confirm the score and verdict improve.
High	Stop asking users to paste secrets directly	Public MCP servers should prefer OAuth or browser-based auth guidance over in-band secret collection.	Inspect the latest validation evidence and resolve the client-visible regression. Playbook Inspect the latest validation evidence. Resolve the highest-severity client-facing gap first. Revalidate and confirm the score and verdict improve.
Medium	Adopt a current MCP protocol revision	Older protocol revisions reduce compatibility with newer clients and registry programs.	Inspect the latest validation evidence and resolve the client-visible regression. Playbook Inspect the latest validation evidence. Resolve the highest-severity client-facing gap first. Revalidate and confirm the score and verdict improve.
Medium	Close connector-publishing gaps	Connector catalogs care about protocol recency, session behavior, auth clarity, and tool-surface stability.	Inspect the latest validation evidence and resolve the client-visible regression. Playbook Inspect the latest validation evidence. Resolve the highest-severity client-facing gap first. Revalidate and confirm the score and verdict improve.
Medium	Document minimal scopes and return cleaner auth challenges	Modern clients expect granular scopes and step-up auth signals such as WWW-Authenticate scope hints.	Return granular scopes and WWW-Authenticate challenge hints instead of forcing overly broad auth upfront. Playbook Advertise the narrowest viable scopes in OAuth metadata. Return `WWW-Authenticate` challenges with scope or insufficient-scope hints when additional consent is needed. Revalidate with both public discovery and auth-required flows.
Medium	Publish OpenID configuration	OIDC metadata improves token validation and client compatibility.	Expose /.well-known/openid-configuration with issuer, jwks_uri, and supported grants. Playbook Inspect the latest validation evidence. Resolve the highest-severity client-facing gap first. Revalidate and confirm the score and verdict improve.
Medium	Respond to validation evidence is stale	Latest validation is 606.0 hours old.	Trigger a fresh validation run or increase scheduler priority for this server. Playbook Queue a new validation run now. Inspect whether the scheduler priority should be raised for this server. Do not rely on stale evidence for production decisions.
Medium	Support resumable HTTP sessions cleanly	Modern MCP clients increasingly expect resumable session behavior on streamable HTTP transports.	Inspect the latest validation evidence and resolve the client-visible regression. Playbook Inspect the latest validation evidence. Resolve the highest-severity client-facing gap first. Revalidate and confirm the score and verdict improve.
Low	Expose modern utility surfaces like completions, pagination, or tasks	Utility coverage improves interoperability with larger clients and long-lived agent workflows.	Expose completions, pagination, and task metadata where supported so larger clients can plan and resume work safely. Playbook Advertise `completions`, pagination cursors, and `tasks` only when they are actually supported. Return `nextCursor` on large list operations when pagination is available. Document task support and whether it requires step-up auth.
Low	Publish newer MCP capability signals	Roots, sampling, elicitation, structured outputs, and related metadata improve client understanding and ranking.	Inspect the latest validation evidence and resolve the client-visible regression. Playbook Inspect the latest validation evidence. Resolve the highest-severity client-facing gap first. Revalidate and confirm the score and verdict improve.

Point loss breakdown

Component	Current	Points missing
Transport Compliance	0/4	-4.0
Recovery Semantics	0/4	-4.0
Error Contract	0/4	-4.0
Utility Coverage	2/4	-2.0
Tool Surface Design	2/4	-2.0
Schema Completeness	2/4	-2.0
Safety Transparency	2/4	-2.0
Registry Consistency	2/4	-2.0
Rate Limit Semantics	2/4	-2.0
Least Privilege Scope	2/4	-2.0
Destructive Operation Safety	2/4	-2.0
Auth Operability	2/4	-2.0

Validation diff

Score delta

Summary changed

Tool delta

Prompt delta

Auth mode changed

Write surface expanded

Protocol regressed

Registry drift changed

Regressed checks: none

Improved checks: none

Component	Previous	Latest	Delta
No component deltas between the latest two runs.

Tool snapshot diff & changelog

Snapshot changed

Added tools

none

Removed tools

none

Required-argument changes

Tool	Added required args	Removed required args
No required-argument changes detected.

Output-schema drift

Tool	Previous properties	Latest properties
No output-schema drift detected.

Connector replay

Status

Backward compatible

✓

Would break after refresh

Added tools

none

Removed tools

none

Additive output changes

none

Required-argument replay breaks

Tool	Added required args	Removed required args
No required-argument replay breaks detected.

Output-schema replay breaks

Tool	Removed properties	Added properties
No output-schema replay breaks detected.

Transport compliance drilldown

Probe status

Error

Transport

streamable-http

Session header

Protocol header

Bad protocol response

200

DELETE teardown

n/a

Expired session retry

n/a

Last-Event-ID visible

Issues: missing_session_id, missing_protocol_header, bad_protocol_not_rejected

Request association

Status

Missing

Advertised capabilities

none

Observed idle methods

none

Violating methods

none

Probe HTTP status

n/a

Issues

none

Utility coverage

Probe status

Missing

Completions

not detected

Completion probe target: { "type": "resource", "uri": "http://localhost:3000/openai.json" }

Pagination

not detected

No nextCursor evidence.

Tasks

Missing

Advertised: no

Benchmark tasks

Benchmark task	Status	Evidence
Discover tools	Passes	`initialize` • OK `tools_list` • OK
Read-only fetch flow	Passes	`resource_read` • OK `read_only_tool_surface` • OK
OAuth-required connect	Degraded	`oauth_protected_resource` • Error `step_up_auth_probe` • Missing
Safe write flow with confirmation	Likely to fail	`action_safety_probe` • Error

Registry & provenance divergence

Probe status

Direct official match

yes

Drift fields

none

Field	Registry	Live server card
Title	n/a	n/a
Version	n/a	n/a
Homepage	n/a	n/a

Active alerts

Validation evidence is stale (medium)
Latest validation is 606.0 hours old.

Aliases & registry graph

Identifier	Source	Canonical	Score
`ai.com.mcp/openai-tools`	official_registry	yes	72.45

Alias consolidation

Canonical identifier

ai.com.mcp/openai-tools

Duplicate aliases

Registry sources

official_registry

Remote URLs

https://openai-tools.run.mcp.com.ai/mcp

Homepages

https://platform.openai.com/docs/api-reference

Source disagreements

Field	What differs	Observed values
No source disagreements detected.

Install snippets

Openai Connectors

Connector URL: https://openai-tools.run.mcp.com.ai/mcp
# No OAuth metadata detected.
# Server: ai.com.mcp/openai-tools

Claude Desktop

{
  "mcpServers": {
    "openai-tools": {
      "command": "npx",
      "args": ["mcp-remote", "https://openai-tools.run.mcp.com.ai/mcp"]
    }
  }
}

Smithery

smithery mcp add "https://openai-tools.run.mcp.com.ai/mcp"

Generic Http

curl -sS https://openai-tools.run.mcp.com.ai/mcp -H 'content-type: application/json' -d '{"jsonrpc":"2.0","id":1,"method":"initialize","params":{"protocolVersion":"2025-03-26","capabilities":{},"clientInfo":{"name":"mcp-verify","version":"0.1.0"}}}'

Agent access & tool surface

Live server tools

createImage createImageEdit createImageVariation createTranscription createTranslation listModels retrieveModel deleteModel

Observed from the latest live validation against https://openai-tools.run.mcp.com.ai/mcp. This is the target server surface, not Verify's own inspection tools.

Live capability counts

9 tools • 1 prompts • 1 resources

Counts come from the latest tools/list, prompts/list, and resources/list checks.

Inspect with Verify

search_servers recommend_servers get_server_report compare_servers

Use Verify itself to search, recommend, compare, and fetch the full report for ai.com.mcp/openai-tools.

Direct machine links

JSON report • Compare this server • Verify MCP API

Claims & monitoring

Server ownership

No verified maintainer claim recorded.

Watch subscriptions

Teams: none

Alert routing

Active watches

Generic webhooks

Slack routes

Teams routes

Email routes

Watch	Team	Channels	Minimum severity
No active watch destinations.

Maintainer analytics

Validation Run Count

Average Latency Ms

521.52

Healthy Run Ratio Recent

1.0

Registry Presence Count

Active Alert Count

Watcher Count

Verified Claim

False

Taxonomy Tags

other

Score Trend

72.45, 72.45, 72.45, 72.45, 72.45, 72.45, 72.45, 72.45, 72.45, 72.45

Remediation Count

High Risk Tool Count

Destructive Tool Count

Exec Tool Count

Maintainer response quality

Score

16.67

Verified claim

Support contact

Changelog present

Incident notes present

Tool changes documented

✓

Annotation history

Annotation count

Maintainer annotations

No maintainer annotations have been recorded yet.

Maintainer rebuttals & expected behavior

No maintainer rebuttals or expected-behavior overrides are recorded yet.

Latest validation evidence

Latest summary

Healthy

Validation profile

remote_mcp

Started

Apr 09, 2026 12:54:00 AM UTC

Latency

913.4 ms

Failures

determinism_probe Check completed
oauth_authorization_server no authorization server
oauth_protected_resource Client error '404 Not Found' for url 'https://openai-tools.run.mcp.com.ai/.well-known/oauth-protected-resource' For more information check: https://developer.mozilla.org/en-US/docs/Web/HTTP/Status/404
openid_configuration no authorization server
server_card Client error '404 Not Found' for url 'https://openai-tools.run.mcp.com.ai/.well-known/mcp/server-card.json' For more information check: https://developer.mozilla.org/en-US/docs/Web/HTTP/Status/404
transport_compliance_probe Issues: missing session id, missing protocol header, bad protocol not rejected (bad protocol=200).

Checks

Check	Status	Latency	Evidence
`action_safety_probe`	Error	n/a	1 high-risk, 1 destructive tool(s); no clear auth boundary; safeguards=0; confirmation=none.
`advanced_capabilities_probe`	Warning	n/a	Only 3 capability signal(s): prompts, resource links, resources.
`connector_publishability_probe`	Warning	n/a	Publishability blockers: transport compliance, action safety, server card.
`connector_replay_probe`	OK	n/a	Backward compatible with no breaking tool-surface changes.
`determinism_probe`	Error	14.0 ms	Check completed
`initialize`	OK	43.1 ms	Protocol 2025-06-18
`interactive_flow_probe`	Missing	n/a	Check completed
`oauth_authorization_server`	Missing	n/a	no authorization server
`oauth_protected_resource`	Error	396.1 ms	Client error '404 Not Found' for url 'https://openai-tools.run.mcp.com.ai/.well-known/oauth-protected-resource' For more information check: https://developer.mozilla.org/en-US/docs/Web/HTTP/Status/404
`official_registry_probe`	OK	n/a	Check completed
`openid_configuration`	Missing	n/a	no authorization server
`probe_noise_resilience`	OK	11.2 ms	Fetched https://openai-tools.run.mcp.com.ai/robots.txt
`prompt_get`	OK	14.0 ms	1 prompt message(s) returned
`prompts_list`	OK	15.1 ms	1 prompt(s) exposed
`protocol_version_probe`	Warning	n/a	Claims 2025-06-18; 1 release(s) behind 2025-11-25.
`provenance_divergence_probe`	OK	n/a	Check completed
`request_association_probe`	Missing	n/a	No request-association capabilities were advertised.
`resource_read`	OK	20.7 ms	1 resource content item(s) returned
`resources_list`	OK	13.3 ms	1 resource item(s) exposed
`server_card`	Error	225.9 ms	Client error '404 Not Found' for url 'https://openai-tools.run.mcp.com.ai/.well-known/mcp/server-card.json' For more information check: https://developer.mozilla.org/en-US/docs/Web/HTTP/Status/404
`session_resume_probe`	Warning	n/a	no session id
`step_up_auth_probe`	Missing	n/a	No OAuth or incremental-scope signals detected.
`tool_snapshot_probe`	OK	n/a	Check completed
`tools_list`	OK	15.7 ms	9 tool(s) exposed
`transport_compliance_probe`	Error	15.0 ms	Issues: missing session id, missing protocol header, bad protocol not rejected (bad protocol=200).
`utility_coverage_probe`	Missing	13.4 ms	No completions evidence; no pagination evidence; tasks missing.

Raw evidence view

Show raw JSON evidence

{
  "checks": {
    "action_safety_probe": {
      "details": {
        "auth_present": false,
        "confirmation_signals": [],
        "safeguard_count": 0,
        "summary": {
          "bulk_access_tools": 0,
          "capability_distribution": {
            "admin": 3,
            "delete": 1,
            "read": 1,
            "write": 7
          },
          "destructive_tools": 1,
          "egress_tools": 0,
          "exec_tools": 0,
          "high_risk_tools": 1,
          "risk_distribution": {
            "critical": 0,
            "high": 1,
            "low": 1,
            "medium": 7
          },
          "secret_tools": 0,
          "tool_count": 9
        }
      },
      "latency_ms": null,
      "status": "error"
    },
    "advanced_capabilities_probe": {
      "details": {
        "capabilities": {
          "completions": false,
          "elicitation": false,
          "prompts": true,
          "resource_links": true,
          "resources": true,
          "roots": false,
          "sampling": false,
          "structured_outputs": false
        },
        "enabled": [
          "prompts",
          "resource_links",
          "resources"
        ],
        "enabled_count": 3,
        "initialize_capability_keys": [
          "logging",
          "prompts",
          "resources",
          "resourcesTemplates",
          "tools"
        ]
      },
      "latency_ms": null,
      "status": "warning"
    },
    "connector_publishability_probe": {
      "details": {
        "blockers": [
          "transport_compliance",
          "action_safety",
          "server_card"
        ],
        "criteria": {
          "action_safety": false,
          "auth_flow": true,
          "connector_replay": true,
          "initialize": true,
          "protocol_version": true,
          "remote_transport": true,
          "request_association": true,
          "server_card": false,
          "session_resume": true,
          "step_up_auth": true,
          "tool_surface": true,
          "tools_list": true,
          "transport_compliance": false
        },
        "high_risk_tools": 1,
        "tool_count": 9,
        "transport": "streamable-http"
      },
      "latency_ms": null,
      "status": "warning"
    },
    "connector_replay_probe": {
      "details": {
        "added_tools": [],
        "additive_output_changes": [],
        "backward_compatible": true,
        "output_breaks": [],
        "removed_tools": [],
        "required_arg_breaks": [],
        "would_break_after_refresh": false
      },
      "latency_ms": null,
      "status": "ok"
    },
    "determinism_probe": {
      "details": {
        "attempts": 2,
        "baseline_signature": "aba67f1929703989f5a8ad04ae29f13aae9eea1c5a9bd8eab73c68bf514fd05b",
        "errors": [
          "request_failed",
          "request_failed"
        ],
        "matches": 0,
        "stable_ratio": 0.0,
        "successful": 0
      },
      "latency_ms": 13.98,
      "status": "error"
    },
    "initialize": {
      "details": {
        "headers": {
          "content-type": "application/json"
        },
        "http_status": 200,
        "payload": {
          "id": 0,
          "jsonrpc": "2.0",
          "result": {
            "capabilities": {
              "logging": {},
              "prompts": {
                "listChanged": true
              },
              "resources": {
                "listChanged": true,
                "subscribe": true
              },
              "resourcesTemplates": {
                "listChanged": true,
                "subscribe": true
              },
              "tools": {
                "listChanged": true
              }
            },
            "protocolVersion": "2025-06-18",
            "serverInfo": {
              "name": "openai",
              "version": "0.6.0"
            }
          }
        },
        "url": "https://openai-tools.run.mcp.com.ai/mcp"
      },
      "latency_ms": 43.12,
      "status": "ok"
    },
    "interactive_flow_probe": {
      "details": {
        "oauth_supported": false,
        "prompt_available": true,
        "risk_hits": [],
        "safe_hits": []
      },
      "latency_ms": null,
      "status": "missing"
    },
    "oauth_authorization_server": {
      "details": {
        "reason": "no_authorization_server"
      },
      "latency_ms": null,
      "status": "missing"
    },
    "oauth_protected_resource": {
      "details": {
        "error": "Client error '404 Not Found' for url 'https://openai-tools.run.mcp.com.ai/.well-known/oauth-protected-resource'\nFor more information check: https://developer.mozilla.org/en-US/docs/Web/HTTP/Status/404",
        "url": "https://openai-tools.run.mcp.com.ai/.well-known/oauth-protected-resource"
      },
      "latency_ms": 396.05,
      "status": "error"
    },
    "official_registry_probe": {
      "details": {
        "direct_match": true,
        "official_peer_count": 1,
        "registry_identifier": "ai.com.mcp/openai-tools",
        "registry_source": "official_registry"
      },
      "latency_ms": null,
      "status": "ok"
    },
    "openid_configuration": {
      "details": {
        "reason": "no_authorization_server"
      },
      "latency_ms": null,
      "status": "missing"
    },
    "probe_noise_resilience": {
      "details": {
        "headers": {
          "content-type": "text/plain; charset=utf-8"
        },
        "http_status": 200,
        "url": "https://openai-tools.run.mcp.com.ai/robots.txt"
      },
      "latency_ms": 11.15,
      "status": "ok"
    },
    "prompt_get": {
      "details": {
        "headers": {
          "content-type": "application/json"
        },
        "http_status": 200,
        "payload": {
          "id": 4,
          "jsonrpc": "2.0",
          "result": {
            "description": "System prompt for API interaction",
            "messages": [
              {
                "content": {
                  "text": "You are an API assistant that helps users interact with the API endpoints.",
                  "type": "text"
                },
                "role": "system"
              }
            ]
          }
        },
        "prompt_name": "system",
        "url": "https://openai-tools.run.mcp.com.ai/mcp"
      },
      "latency_ms": 13.99,
      "status": "ok"
    },
    "prompts_list": {
      "details": {
        "headers": {
          "content-type": "application/json"
        },
        "http_status": 200,
        "payload": {
          "id": 3,
          "jsonrpc": "2.0",
          "result": {
            "prompts": [
              {
                "arguments": [],
                "description": "System prompt for API interaction",
                "name": "system"
              }
            ]
          }
        },
        "url": "https://openai-tools.run.mcp.com.ai/mcp"
      },
      "latency_ms": 15.14,
      "status": "ok"
    },
    "protocol_version_probe": {
      "details": {
        "claimed_version": "2025-06-18",
        "lag_days": 160,
        "latest_known_version": "2025-11-25",
        "releases_behind": 1,
        "validator_protocol_version": "2025-03-26"
      },
      "latency_ms": null,
      "status": "warning"
    },
    "provenance_divergence_probe": {
      "details": {
        "direct_official_match": true,
        "drift_fields": [],
        "metadata_document_count": 2,
        "registry_homepage": null,
        "registry_repository": null,
        "registry_title": null,
        "registry_version": null,
        "server_card_homepage": null,
        "server_card_repository": null,
        "server_card_title": null,
        "server_card_version": null
      },
      "latency_ms": null,
      "status": "ok"
    },
    "request_association_probe": {
      "details": {
        "reason": "no_request_association_capabilities_advertised"
      },
      "latency_ms": null,
      "status": "missing"
    },
    "resource_read": {
      "details": {
        "headers": {
          "content-type": "application/json"
        },
        "http_status": 200,
        "payload": {
          "id": 6,
          "jsonrpc": "2.0",
          "result": {
            "contents": [
              {
                "mimeType": "application/json",
                "text": "{\n  \"openapi\": \"3.0.0\",\n  \"info\": {\n    \"title\": \"OpenAI API\",\n    \"description\": \"APIs for sampling from and fine-tuning language models\",\n    \"version\": \"2.0.0\"\n  },\n  \"servers\": [\n    {\n      \"url\": \"https://api.openai.com/v1\"\n    }\n  ],\n  \"tags\": [\n    {\n      \"name\": \"OpenAI\",\n      \"description\": \"The OpenAI REST API\"\n    }\n  ],\n  \"paths\": {\n    \"/images/generations\": {\n      \"post\": {\n        \"operationId\": \"createImage\",\n        \"tags\": [\n          \"OpenAI\"\n        ],\n        \"summary\": \"Creates an image given a prompt.\",\n        \"requestBody\": {\n          \"required\": true,\n          \"content\": {\n            \"application/json\": {\n              \"schema\": {\n                \"$ref\": \"#/components/schemas/CreateImageRequest\"\n              }\n            }\n          }\n        },\n        \"responses\": {\n          \"200\": {\n            \"description\": \"OK\",\n            \"content\": {\n              \"application/json\": {\n                \"schema\": {\n                  \"$ref\": \"#/components/schemas/ImagesResponse\"\n                }\n              }\n            }\n          }\n        },\n        \"x-oaiMeta\": {\n          \"name\": \"Create image\",\n          \"group\": \"images\",\n          \"path\": \"create\",\n          \"beta\": true,\n          \"examples\": {\n            \"curl\": \"curl https://api.openai.com/v1/images/generations \\\\\\n  -H \\\"Content-Type: application/json\\\" \\\\\\n  -H \\\"Authorization: Bearer $OPENAI_API_KEY\\\" \\\\\\n  -d '{\\n    \\\"prompt\\\": \\\"A cute baby sea otter\\\",\\n    \\\"n\\\": 2,\\n    \\\"size\\\": \\\"1024x1024\\\"\\n  }'\\n\",\n            \"python\": \"import os\\nimport openai\\nopenai.api_key = os.getenv(\\\"OPENAI_API_KEY\\\")\\nopenai.Image.create(\\n  prompt=\\\"A cute baby sea otter\\\",\\n  n=2,\\n  size=\\\"1024x1024\\\"\\n)\\n\",\n            \"node.js\": \"const { Configuration, OpenAIApi } = require(\\\"openai\\\");\\nconst configuration = new Configuration({\\n  apiKey: process.env.OPENAI_API_KEY,\\n});\\nconst openai = new OpenAIApi(configuration);\\nconst response = await openai.createImage({\\n  prompt: \\\"A cute baby sea otter\\\",\\n  n: 2,\\n  size: \\\"1024x1024\\\",\\n});\\n\"\n          },\n          \"parameters\": \"{\\n  \\\"prompt\\\": \\\"A cute baby sea otter\\\",\\n  \\\"n\\\": 2,\\n  \\\"size\\\": \\\"1024x1024\\\"\\n}\\n\",\n          \"response\": \"{\\n  \\\"created\\\": 1589478378,\\n  \\\"data\\\": [\\n    {\\n      \\\"url\\\": \\\"https://...\\\"\\n    },\\n    {\\n      \\\"url\\\": \\\"https://...\\\"\\n    }\\n  ]\\n}\\n\"\n        },\n        \"parameters\": []\n      }\n    },\n    \"/images/edits\": {\n      \"post\": {\n        \"operationId\": \"createImageEdit\",\n        \"tags\": [\n          \"OpenAI\"\n        ],\n        \"summary\": \"Creates an edited or extended image given an original image and a prompt.\",\n        \"requestBody\": {\n          \"required\": true,\n          \"content\": {\n            \"multipart/form-data\": {\n              \"schema\": {\n                \"$ref\": \"#/components/schemas/CreateImageEditRequest\"\n              }\n            }\n          }\n        },\n        \"responses\": {\n          \"200\": {\n            \"description\": \"OK\",\n            \"content\": {\n              \"application/json\": {\n                \"schema\": {\n                  \"$ref\": \"#/components/schemas/ImagesResponse\"\n                }\n              }\n            }\n          }\n        },\n        \"x-oaiMeta\": {\n          \"name\": \"Create image edit\",\n          \"group\": \"images\",\n          \"path\": \"create-edit\",\n          \"beta\": true,\n          \"examples\": {\n            \"curl\": \"curl https://api.openai.com/v1/images/edits \\\\\\n  -H \\\"Authorization: Bearer $OPENAI_API_KEY\\\" \\\\\\n  -F image=\\\"@otter.png\\\" \\\\\\n  -F mask=\\\"@mask.png\\\" \\\\\\n  -F prompt=\\\"A cute baby sea otter wearing a beret\\\" \\\\\\n  -F n=2 \\\\\\n  -F size=\\\"1024x1024\\\"\\n\",\n            \"python\": \"import os\\nimport openai\\nopenai.api_key = os.getenv(\\\"OPENAI_API_KEY\\\")\\nopenai.Image.create_edit(\\n  image=open(\\\"otter.png\\\", \\\"rb\\\"),\\n  mask=open(\\\"mask.png\\\", \\\"rb\\\"),\\n  prompt=\\\"A cute baby sea otter wearing a beret\\\",\\n  n=2,\\n  size=\\\"1024x1024\\\"\\n)\\n\",\n            \"node.js\": \"const { Configuration, OpenAIApi } = require(\\\"openai\\\");\\nconst configuration = new Configuration({\\n  apiKey: process.env.OPENAI_API_KEY,\\n});\\nconst openai = new OpenAIApi(configuration);\\nconst response = await openai.createImageEdit(\\n  fs.createReadStream(\\\"otter.png\\\"),\\n  fs.createReadStream(\\\"mask.png\\\"),\\n  \\\"A cute baby sea otter wearing a beret\\\",\\n  2,\\n  \\\"1024x1024\\\"\\n);\\n\"\n          },\n          \"response\": \"{\\n  \\\"created\\\": 1589478378,\\n  \\\"data\\\": [\\n    {\\n      \\\"url\\\": \\\"https://...\\\"\\n    },\\n    {\\n      \\\"url\\\": \\\"https://...\\\"\\n    }\\n  ]\\n}\\n\"\n        },\n        \"parameters\": []\n      }\n    },\n    \"/images/variations\": {\n      \"post\": {\n        \"operationId\": \"createImageVariation\",\n        \"tags\": [\n          \"OpenAI\"\n        ],\n        \"summary\": \"Creates a variation of a given image.\",\n        \"requestBody\": {\n          \"required\": true,\n          \"content\": {\n            \"multipart/form-data\": {\n              \"schema\": {\n                \"$ref\": \"#/components/schemas/CreateImageVariationRequest\"\n              }\n            }\n          }\n        },\n        \"responses\": {\n          \"200\": {\n            \"description\": \"OK\",\n            \"content\": {\n              \"application/json\": {\n                \"schema\": {\n                  \"$ref\": \"#/components/schemas/ImagesResponse\"\n                }\n              }\n            }\n          }\n        },\n        \"x-oaiMeta\": {\n          \"name\": \"Create image variation\",\n          \"group\": \"images\",\n          \"path\": \"create-variation\",\n          \"beta\": true,\n          \"examples\": {\n            \"curl\": \"curl https://api.openai.com/v1/images/variations \\\\\\n  -H \\\"Authorization: Bearer $OPENAI_API_KEY\\\" \\\\\\n  -F image=\\\"@otter.png\\\" \\\\\\n  -F n=2 \\\\\\n  -F size=\\\"1024x1024\\\"\\n\",\n            \"python\": \"import os\\nimport openai\\nopenai.api_key = os.getenv(\\\"OPENAI_API_KEY\\\")\\nopenai.Image.create_variation(\\n  image=open(\\\"otter.png\\\", \\\"rb\\\"),\\n  n=2,\\n  size=\\\"1024x1024\\\"\\n)\\n\",\n            \"node.js\": \"const { Configuration, OpenAIApi } = require(\\\"openai\\\");\\nconst configuration = new Configuration({\\n  apiKey: process.env.OPENAI_API_KEY,\\n});\\nconst openai = new OpenAIApi(configuration);\\nconst response = await openai.createImageVariation(\\n  fs.createReadStream(\\\"otter.png\\\"),\\n  2,\\n  \\\"1024x1024\\\"\\n);\\n\"\n          },\n          \"response\": \"{\\n  \\\"created\\\": 1589478378,\\n  \\\"data\\\": [\\n    {\\n      \\\"url\\\": \\\"https://...\\\"\\n    },\\n    {\\n      \\\"url\\\": \\\"https://...\\\"\\n    }\\n  ]\\n}\\n\"\n        },\n        \"parameters\": []\n      }\n    },\n    \"/audio/transcriptions\": {\n      \"post\": {\n        \"operationId\": \"createTranscription\",\n        \"tags\": [\n          \"OpenAI\"\n        ],\n        \"summary\": \"Transcribes audio into the input language.\",\n        \"requestBody\": {\n          \"required\": true,\n          \"content\": {\n            \"multipart/form-data\": {\n              \"schema\": {\n                \"$ref\": \"#/components/schemas/CreateTranscriptionRequest\"\n              }\n            }\n          }\n        },\n        \"responses\": {\n          \"200\": {\n            \"description\": \"OK\",\n            \"content\": {\n              \"application/json\": {\n                \"schema\": {\n                  \"$ref\": \"#/components/schemas/CreateTranscriptionResponse\"\n                }\n              }\n            }\n          }\n        },\n        \"x-oaiMeta\": {\n          \"name\": \"Create transcription\",\n          \"group\": \"audio\",\n          \"path\": \"create\",\n          \"beta\": true,\n          \"examples\": {\n            \"curl\": \"curl https://api.openai.com/v1/audio/transcriptions \\\\\\n  -H \\\"Authorization: Bearer $OPENAI_API_KEY\\\" \\\\\\n  -H \\\"Content-Type: multipart/form-data\\\" \\\\\\n  -F file=\\\"@/path/to/file/audio.mp3\\\" \\\\\\n  -F model=\\\"whisper-1\\\"\\n\",\n            \"python\": \"import os\\nimport openai\\nopenai.api_key = os.getenv(\\\"OPENAI_API_KEY\\\")\\naudio_file = open(\\\"audio.mp3\\\", \\\"rb\\\")\\ntranscript = openai.Audio.transcribe(\\\"whisper-1\\\", audio_file)\\n\",\n            \"node\": \"const { Configuration, OpenAIApi } = require(\\\"openai\\\");\\nconst configuration = new Configuration({\\n  apiKey: process.env.OPENAI_API_KEY,\\n});\\nconst openai = new OpenAIApi(configuration);\\nconst resp = await openai.createTranscription(\\n  fs.createReadStream(\\\"audio.mp3\\\"),\\n  \\\"whisper-1\\\"\\n);\\n\"\n          },\n          \"parameters\": \"{\\n  \\\"file\\\": \\\"audio.mp3\\\",\\n  \\\"model\\\": \\\"whisper-1\\\"\\n}\\n\",\n          \"response\": \"{\\n  \\\"text\\\": \\\"Imagine the wildest idea that you've ever had, and you're curious about how it might scale to something that's a 100, a 1,000 times bigger. This is a place where you can get to do that.\\\"\\n}\\n\"\n        },\n        \"parameters\": []\n      }\n    },\n    \"/audio/translations\": {\n      \"post\": {\n        \"operationId\": \"createTranslation\",\n        \"tags\": [\n          \"OpenAI\"\n        ],\n        \"summary\": \"Translates audio into English.\",\n        \"requestBody\": {\n          \"required\": true,\n          \"content\": {\n            \"multipart/form-data\": {\n              \"schema\": {\n                \"$ref\": \"#/components/schemas/CreateTranslationRequest\"\n              }\n            }\n          }\n        },\n        \"responses\": {\n          \"200\": {\n            \"description\": \"OK\",\n            \"content\": {\n              \"application/json\": {\n                \"schema\": {\n                  \"$ref\": \"#/components/schemas/CreateTranslationResponse\"\n                }\n              }\n            }\n          }\n        },\n        \"x-oaiMeta\": {\n          \"name\": \"Create translation\",\n          \"group\": \"audio\",\n          \"path\": \"create\",\n          \"beta\": true,\n          \"examples\": {\n            \"curl\": \"curl https://api.openai.com/v1/audio/translations \\\\\\n  -H \\\"Authorization: Bearer $OPENAI_API_KEY\\\" \\\\\\n  -H \\\"Content-Type: multipart/form-data\\\" \\\\\\n  -F file=\\\"@/path/to/file/german.m4a\\\" \\\\\\n  -F model=\\\"whisper-1\\\"\\n\",\n            \"python\": \"import os\\nimport openai\\nopenai.api_key = os.getenv(\\\"OPENAI_API_KEY\\\")\\naudio_file = open(\\\"german.m4a\\\", \\\"rb\\\")\\ntranscript = openai.Audio.translate(\\\"whisper-1\\\", audio_file)\\n\",\n            \"node\": \"const { Configuration, OpenAIApi } = require(\\\"openai\\\");\\nconst configuration = new Configuration({\\n  apiKey: process.env.OPENAI_API_KEY,\\n});\\nconst openai = new OpenAIApi(configuration);\\nconst resp = await openai.createTranslation(\\n  fs.createReadStream(\\\"audio.mp3\\\"),\\n  \\\"whisper-1\\\"\\n);\\n\"\n          },\n          \"parameters\": \"{\\n  \\\"file\\\": \\\"german.m4a\\\",\\n  \\\"model\\\": \\\"whisper-1\\\"\\n}\\n\",\n          \"response\": \"{\\n  \\\"text\\\": \\\"Hello, my name is Wolfgang and I come from Germany. Where are you heading today?\\\"\\n}\\n\"\n        },\n        \"parameters\": []\n      }\n    },\n    \"/models\": {\n      \"get\": {\n        \"operationId\": \"listModels\",\n        \"tags\": [\n          \"OpenAI\"\n        ],\n        \"summary\": \"Lists the currently available models, and provides basic information about each one such as the owner and availability.\",\n        \"responses\": {\n          \"200\": {\n            \"description\": \"OK\",\n            \"content\": {\n              \"application/json\": {\n                \"schema\": {\n                  \"$ref\": \"#/components/schemas/ListModelsResponse\"\n                }\n              }\n            }\n          }\n        },\n        \"x-oaiMeta\": {\n          \"name\": \"List models\",\n          \"group\": \"models\",\n          \"path\": \"list\",\n          \"examples\": {\n            \"curl\": \"curl https://api.openai.com/v1/models \\\\\\n  -H \\\"Authorization: Bearer $OPENAI_API_KEY\\\"\\n\",\n            \"python\": \"import os\\nimport openai\\nopenai.api_key = os.getenv(\\\"OPENAI_API_KEY\\\")\\nopenai.Model.list()\\n\",\n            \"node.js\": \"const { Configuration, OpenAIApi } = require(\\\"openai\\\");\\nconst configuration = new Configuration({\\n  apiKey: process.env.OPENAI_API_KEY,\\n});\\nconst openai = new OpenAIApi(configuration);\\nconst response = await openai.listModels();\\n\"\n          },\n          \"response\": \"{\\n  \\\"data\\\": [\\n    {\\n      \\\"id\\\": \\\"model-id-0\\\",\\n      \\\"object\\\": \\\"model\\\",\\n      \\\"owned_by\\\": \\\"organization-owner\\\",\\n      \\\"permission\\\": [...]\\n    },\\n    {\\n      \\\"id\\\": \\\"model-id-1\\\",\\n      \\\"object\\\": \\\"model\\\",\\n      \\\"owned_by\\\": \\\"organization-owner\\\",\\n      \\\"permission\\\": [...]\\n    },\\n    {\\n      \\\"id\\\": \\\"model-id-2\\\",\\n      \\\"object\\\": \\\"model\\\",\\n      \\\"owned_by\\\": \\\"openai\\\",\\n      \\\"permission\\\": [...]\\n    },\\n  ],\\n  \\\"object\\\": \\\"list\\\"\\n}\\n\"\n        },\n        \"parameters\": []\n      }\n    },\n    \"/models/{model}\": {\n      \"get\": {\n        \"operationId\": \"retrieveModel\",\n        \"tags\": [\n          \"OpenAI\"\n        ],\n        \"summary\": \"Retrieves a model instance, providing basic information about the model such as the owner and permissioning.\",\n        \"parameters\": [\n          {\n            \"in\": \"path\",\n            \"name\": \"model\",\n            \"required\": true,\n            \"schema\": {\n              \"type\": \"string\",\n              \"example\": \"text-davinci-001\"\n            },\n            \"description\": \"The ID of the model to use for this request\"\n          }\n        ],\n        \"responses\": {\n          \"200\": {\n            \"description\": \"OK\",\n            \"content\": {\n              \"application/json\": {\n                \"schema\": {\n                  \"$ref\": \"#/components/schemas/Model\"\n                }\n              }\n            }\n          }\n        },\n        \"x-oaiMeta\": {\n          \"name\": \"Retrieve model\",\n          \"group\": \"models\",\n          \"path\": \"retrieve\",\n          \"examples\": {\n            \"curl\": \"curl https://api.openai.com/v1/models/VAR_model_id \\\\\\n  -H \\\"Authorization: Bearer $OPENAI_API_KEY\\\"\\n\",\n            \"python\": \"import os\\nimport openai\\nopenai.api_key = os.getenv(\\\"OPENAI_API_KEY\\\")\\nopenai.Model.retrieve(\\\"VAR_model_id\\\")\\n\",\n            \"node.js\": \"const { Configuration, OpenAIApi } = require(\\\"openai\\\");\\nconst configuration = new Configuration({\\n  apiKey: process.env.OPENAI_API_KEY,\\n});\\nconst openai = new OpenAIApi(configuration);\\nconst response = await openai.retrieveModel(\\\"VAR_model_id\\\");\\n\"\n          },\n          \"response\": \"{\\n  \\\"id\\\": \\\"VAR_model_id\\\",\\n  \\\"object\\\": \\\"model\\\",\\n  \\\"owned_by\\\": \\\"openai\\\",\\n  \\\"permission\\\": [...]\\n}\\n\"\n        }\n      },\n      \"delete\": {\n        \"operationId\": \"deleteModel\",\n        \"tags\": [\n          \"OpenAI\"\n        ],\n        \"summary\": \"Delete a fine-tuned model. You must have the Owner role in your organization.\",\n        \"parameters\": [\n          {\n            \"in\": \"path\",\n            \"name\": \"model\",\n            \"required\": true,\n            \"schema\": {\n              \"type\": \"string\",\n              \"example\": \"curie:ft-acmeco-2021-03-03-21-44-20\"\n            },\n            \"description\": \"The model to delete\"\n          }\n        ],\n        \"responses\": {\n          \"200\": {\n            \"description\": \"OK\",\n            \"content\": {\n              \"application/json\": {\n                \"schema\": {\n                  \"$ref\": \"#/components/schemas/DeleteModelResponse\"\n                }\n              }\n            }\n          }\n        },\n        \"x-oaiMeta\": {\n          \"name\": \"Delete fine-tune model\",\n          \"group\": \"fine-tunes\",\n          \"path\": \"delete-model\",\n          \"examples\": {\n            \"curl\": \"curl https://api.openai.com/v1/models/curie:ft-acmeco-2021-03-03-21-44-20 \\\\\\n  -X DELETE \\\\\\n  -H \\\"Authorization: Bearer $OPENAI_API_KEY\\\"\\n\",\n            \"python\": \"import os\\nimport openai\\nopenai.api_key = os.getenv(\\\"OPENAI_API_KEY\\\")\\nopenai.Model.delete(\\\"curie:ft-acmeco-2021-03-03-21-44-20\\\")\\n\",\n            \"node.js\": \"const { Configuration, OpenAIApi } = require(\\\"openai\\\");\\nconst configuration = new Configuration({\\n  apiKey: process.env.OPENAI_API_KEY,\\n});\\nconst openai = new OpenAIApi(configuration);\\nconst response = await openai.deleteModel('curie:ft-acmeco-2021-03-03-21-44-20');\\n\"\n          },\n          \"response\": \"{\\n  \\\"id\\\": \\\"curie:ft-acmeco-2021-03-03-21-44-20\\\",\\n  \\\"object\\\": \\\"model\\\",\\n  \\\"deleted\\\": true\\n}\\n\"\n        }\n      }\n    },\n    \"/moderations\": {\n      \"post\": {\n        \"operationId\": \"createModeration\",\n        \"tags\": [\n          \"OpenAI\"\n        ],\n        \"summary\": \"Classifies if text violates OpenAI's Content Policy\",\n        \"requestBody\": {\n          \"required\": true,\n          \"content\": {\n            \"application/json\": {\n              \"schema\": {\n                \"$ref\": \"#/components/schemas/CreateModerationRequest\"\n              }\n            }\n          }\n        },\n        \"responses\": {\n          \"200\": {\n            \"description\": \"OK\",\n            \"content\": {\n              \"application/json\": {\n                \"schema\": {\n                  \"$ref\": \"#/components/schemas/CreateModerationResponse\"\n                }\n              }\n            }\n          }\n        },\n        \"x-oaiMeta\": {\n          \"name\": \"Create moderation\",\n          \"group\": \"moderations\",\n          \"path\": \"create\",\n          \"examples\": {\n            \"curl\": \"curl https://api.openai.com/v1/moderations \\\\\\n  -H \\\"Content-Type: application/json\\\" \\\\\\n  -H \\\"Authorization: Bearer $OPENAI_API_KEY\\\" \\\\\\n  -d '{\\n    \\\"input\\\": \\\"I want to kill them.\\\"\\n  }'\\n\",\n            \"python\": \"import os\\nimport openai\\nopenai.api_key = os.getenv(\\\"OPENAI_API_KEY\\\")\\nopenai.Moderation.create(\\n  input=\\\"I want to kill them.\\\",\\n)\\n\",\n            \"node.js\": \"const { Configuration, OpenAIApi } = require(\\\"openai\\\");\\nconst configuration = new Configuration({\\n  apiKey: process.env.OPENAI_API_KEY,\\n});\\nconst openai = new OpenAIApi(configuration);\\nconst response = await openai.createModeration({\\n  input: \\\"I want to kill them.\\\",\\n});\\n\"\n          },\n          \"parameters\": \"{\\n  \\\"input\\\": \\\"I want to kill them.\\\"\\n}\\n\",\n          \"response\": \"{\\n  \\\"id\\\": \\\"modr-5MWoLO\\\",\\n  \\\"model\\\": \\\"text-moderation-001\\\",\\n  \\\"results\\\": [\\n    {\\n      \\\"categories\\\": {\\n        \\\"hate\\\": false,\\n        \\\"hate/threatening\\\": true,\\n        \\\"self-harm\\\": false,\\n        \\\"sexual\\\": false,\\n        \\\"sexual/minors\\\": false,\\n        \\\"violence\\\": true,\\n        \\\"violence/graphic\\\": false\\n      },\\n      \\\"category_scores\\\": {\\n        \\\"hate\\\": 0.22714105248451233,\\n        \\\"hate/threatening\\\": 0.4132447838783264,\\n        \\\"self-harm\\\": 0.005232391878962517,\\n        \\\"sexual\\\": 0.01407341007143259,\\n        \\\"sexual/minors\\\": 0.0038522258400917053,\\n        \\\"violence\\\": 0.9223177433013916,\\n        \\\"violence/graphic\\\": 0.036865197122097015\\n      },\\n      \\\"flagged\\\": true\\n    }\\n  ]\\n}\\n\"\n        },\n        \"parameters\": []\n      }\n    }\n  },\n  \"components\": {\n    \"schemas\": {\n      \"Error\": {\n        \"type\": \"object\",\n        \"properties\": {\n          \"type\": {\n            \"type\": \"string\",\n            \"nullable\": false\n          },\n          \"message\": {\n            \"type\": \"string\",\n            \"nullable\": false\n          },\n          \"param\": {\n            \"type\": \"string\",\n            \"nullable\": true\n          },\n          \"code\": {\n            \"type\": \"string\",\n            \"nullable\": true\n          }\n        },\n        \"required\": [\n          \"type\",\n          \"message\",\n          \"param\",\n          \"code\"\n        ]\n      },\n      \"ErrorResponse\": {\n        \"type\": \"object\",\n        \"properties\": {\n          \"error\": {\n            \"$ref\": \"#/components/schemas/Error\"\n          }\n        },\n        \"required\": [\n          \"error\"\n        ]\n      },\n      \"ListModelsResponse\": {\n        \"type\": \"object\",\n        \"properties\": {\n          \"object\": {\n            \"type\": \"string\"\n          },\n          \"data\": {\n            \"type\": \"array\",\n            \"items\": {\n              \"$ref\": \"#/components/schemas/Model\"\n            }\n          }\n        },\n        \"required\": [\n          \"object\",\n          \"data\"\n        ]\n      },\n      \"DeleteModelResponse\": {\n        \"type\": \"object\",\n        \"properties\": {\n          \"id\": {\n            \"type\": \"string\"\n          },\n          \"object\": {\n            \"type\": \"string\"\n          },\n          \"deleted\": {\n            \"type\": \"boolean\"\n          }\n        },\n        \"required\": [\n          \"id\",\n          \"object\",\n          \"deleted\"\n        ]\n      },\n      \"CreateCompletionRequest\": {\n        \"type\": \"object\",\n        \"properties\": {\n          \"model\": {\n            \"description\": \"ID of the model to use. You can use the [List models](/docs/api-reference/models/list) API to see all of your available models, or see our [Model overview](/docs/models/overview) for descriptions of them.\\n\",\n            \"oneOf\": [\n              {\n                \"type\": \"string\"\n              },\n              {\n                \"type\": \"string\",\n                \"enum\": [\n                  \"text-davinci-003\",\n                  \"text-davinci-002\",\n                  \"text-davinci-001\",\n                  \"code-davinci-002\",\n                  \"text-curie-001\",\n                  \"text-babbage-001\",\n                  \"text-ada-001\"\n                ]\n              }\n            ]\n          },\n          \"prompt\": {\n            \"description\": \"The prompt(s) to generate completions for, encoded as a string, array of strings, array of tokens, or array of token arrays.\\n\\nNote that <|endoftext|> is the document separator that the model sees during training, so if a prompt is not specified the model will generate as if from the beginning of a new document.\\n\",\n            \"default\": \"<|endoftext|>\",\n            \"nullable\": true,\n            \"oneOf\": [\n              {\n                \"type\": \"string\",\n                \"default\": \"\",\n                \"example\": \"This is a test.\"\n              },\n              {\n                \"type\": \"array\",\n                \"items\": {\n                  \"type\": \"string\",\n                  \"default\": \"\",\n                  \"example\": \"This is a test.\"\n                }\n              },\n              {\n                \"type\": \"array\",\n                \"minItems\": 1,\n                \"items\": {\n                  \"type\": \"integer\"\n                },\n                \"example\": \"[1212, 318, 257, 1332, 13]\"\n              },\n              {\n                \"type\": \"array\",\n                \"minItems\": 1,\n                \"items\": {\n                  \"type\": \"array\",\n                  \"minItems\": 1,\n                  \"items\": {\n                    \"type\": \"integer\"\n                  }\n                },\n                \"example\": \"[[1212, 318, 257, 1332, 13]]\"\n              }\n            ]\n          },\n          \"suffix\": {\n            \"description\": \"The suffix that comes after a completion of inserted text.\",\n            \"default\": null,\n            \"nullable\": true,\n            \"type\": \"string\",\n            \"example\": \"test.\"\n          },\n          \"max_tokens\": {\n            \"type\": \"integer\",\n            \"minimum\": 0,\n            \"default\": 16,\n            \"example\": 16,\n            \"nullable\": true,\n            \"description\": \"The maximum number of [tokens](/tokenizer) to generate in the completion.\\n\\nThe token count of your prompt plus `max_tokens` cannot exceed the model's context length. [Example Python code](https://github.com/openai/openai-cookbook/blob/main/examples/How_to_count_tokens_with_tiktoken.ipynb) for counting tokens.\\n\"\n          },\n          \"temperature\": {\n            \"type\": \"number\",\n            \"minimum\": 0,\n            \"maximum\": 2,\n            \"default\": 1,\n            \"example\": 1,\n            \"nullable\": true,\n            \"description\": \"What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic.\\n\\nWe generally recommend altering this or `top_p` but not both.\\n\"\n          },\n          \"top_p\": {\n            \"type\": \"number\",\n            \"minimum\": 0,\n            \"maximum\": 1,\n            \"default\": 1,\n            \"example\": 1,\n            \"nullable\": true,\n            \"description\": \"An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered.\\n\\nWe generally recommend altering this or `temperature` but not both.\\n\"\n          },\n          \"n\": {\n            \"type\": \"integer\",\n            \"minimum\": 1,\n            \"maximum\": 128,\n            \"default\": 1,\n            \"example\": 1,\n            \"nullable\": true,\n            \"description\": \"How many completions to generate for each prompt.\\n\\n**Note:** Because this parameter generates many completions, it can quickly consume your token quota. Use carefully and ensure that you have reasonable settings for `max_tokens` and `stop`.\\n\"\n          },\n          \"stream\": {\n            \"description\": \"Whether to stream back partial progress. If set, tokens will be sent as data-only [server-sent events](https://developer.mozilla.org/en-US/docs/Web/API/Server-sent_events/Using_server-sent_events#Event_stream_format) as they become available, with the stream terminated by a `data: [DONE]` message. [Example Python code](https://github.com/openai/openai-cookbook/blob/main/examples/How_to_stream_completions.ipynb).\\n\",\n            \"type\": \"boolean\",\n            \"nullable\": true,\n            \"default\": false\n          },\n          \"logprobs\": {\n            \"type\": \"integer\",\n            \"minimum\": 0,\n            \"maximum\": 5,\n            \"default\": null,\n            \"nullable\": true,\n            \"description\": \"Include the log probabilities on the `logprobs` most likely tokens, as well the chosen tokens. For example, if `logprobs` is 5, the API will return a list of the 5 most likely tokens. The API will always return the `logprob` of the sampled token, so there may be up to `logprobs+1` elements in the response.\\n\\nThe maximum value for `logprobs` is 5.\\n\"\n          },\n          \"echo\": {\n            \"type\": \"boolean\",\n            \"default\": false,\n            \"nullable\": true,\n            \"description\": \"Echo back the prompt in addition to the completion\\n\"\n          },\n          \"stop\": {\n            \"description\": \"Up to 4 sequences where the API will stop generating further tokens. The returned text will not contain the stop sequence.\\n\",\n            \"default\": null,\n            \"nullable\": true,\n            \"oneOf\": [\n              {\n                \"type\": \"string\",\n                \"default\": \"<|endoftext|>\",\n                \"example\": \"\\n\",\n                \"nullable\": true\n              },\n              {\n                \"type\": \"array\",\n                \"minItems\": 1,\n                \"maxItems\": 4,\n                \"items\": {\n                  \"type\": \"string\",\n                  \"example\": \"[\\\"\\\\n\\\"]\"\n                }\n              }\n            ]\n          },\n          \"presence_penalty\": {\n            \"type\": \"number\",\n            \"default\": 0,\n            \"minimum\": -2,\n            \"maximum\": 2,\n            \"nullable\": true,\n            \"description\": \"Number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far, increasing the model's likelihood to talk about new topics.\\n\\n[See more information about frequency and presence penalties.](/docs/api-reference/parameter-details)\\n\"\n          },\n          \"frequency_penalty\": {\n            \"type\": \"number\",\n            \"default\": 0,\n            \"minimum\": -2,\n            \"maximum\": 2,\n            \"nullable\": true,\n            \"description\": \"Number between -2.0 and 2.0. Positive values penalize new tokens based on their existing frequency in the text so far, decreasing the model's likelihood to repeat the same line verbatim.\\n\\n[See more information about frequency and presence penalties.](/docs/api-reference/parameter-details)\\n\"\n          },\n          \"best_of\": {\n            \"type\": \"integer\",\n            \"default\": 1,\n            \"minimum\": 0,\n            \"maximum\": 20,\n            \"nullable\": true,\n            \"description\": \"Generates `best_of` completions server-side and returns the \\\"best\\\" (the one with the highest log probability per token). Results cannot be streamed.\\n\\nWhen used with `n`, `best_of` controls the number of candidate completions and `n` specifies how many to return \u2013 `best_of` must be greater than `n`.\\n\\n**Note:** Because this parameter generates many completions, it can quickly consume your token quota. Use carefully and ensure that you have reasonable settings for `max_tokens` and `stop`.\\n\"\n          },\n          \"logit_bias\": {\n            \"type\": \"object\",\n            \"x-oaiTypeLabel\": \"map\",\n            \"default\": null,\n            \"nullable\": true,\n            \"description\": \"Modify the likelihood of specified tokens appearing in the completion.\\n\\nAccepts a json object that maps tokens (specified by their token ID in the GPT tokenizer) to an associated bias value from -100 to 100. You can use this [tokenizer tool](/tokenizer?view=bpe) (which works for both GPT-2 and GPT-3) to convert text to token IDs. Mathematically, the bias is added to the logits generated by the model prior to sampling. The exact effect will vary per model, but values between -1 and 1 should decrease or increase likelihood of selection; values like -100 or 100 should result in a ban or exclusive selection of the relevant token.\\n\\nAs an example, you can pass `{\\\"50256\\\": -100}` to prevent the <|endoftext|> token from being generated.\\n\"\n          },\n          \"user\": {\n            \"type\": \"string\",\n            \"example\": \"user-1234\",\n            \"description\": \"A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse. [Learn more](/docs/guides/safety-best-practices/end-user-ids).\\n\"\n          }\n        },\n        \"required\": [\n          \"model\",\n          \"prompt\"\n        ]\n      },\n      \"CreateCompletionResponse\": {\n        \"type\": \"object\",\n        \"properties\": {\n          \"id\": {\n            \"type\": \"string\"\n          },\n          \"object\": {\n            \"type\": \"string\"\n          },\n          \"created\": {\n            \"type\": \"integer\"\n          },\n          \"model\": {\n            \"type\": \"string\"\n          },\n          \"choices\": {\n            \"type\": \"array\",\n            \"items\": {\n              \"type\": \"object\",\n              \"required\": [\n                \"text\",\n                \"index\",\n                \"logprobs\",\n                \"finish_reason\"\n              ],\n              \"properties\": {\n                \"text\": {\n                  \"type\": \"string\"\n                },\n                \"index\": {\n                  \"type\": \"integer\"\n                },\n                \"logprobs\": {\n                  \"type\": \"object\",\n                  \"nullable\": true,\n                  \"properties\": {\n                    \"tokens\": {\n                      \"type\": \"array\",\n                      \"items\": {\n                        \"type\": \"string\"\n                      }\n                    },\n                    \"token_logprobs\": {\n                      \"type\": \"array\",\n                      \"items\": {\n                        \"type\": \"number\"\n                      }\n                    },\n                    \"top_logprobs\": {\n                      \"type\": \"array\",\n                      \"items\": {\n                        \"type\": \"object\"\n                      }\n                    },\n                    \"text_offset\": {\n                      \"type\": \"array\",\n                      \"items\": {\n                        \"type\": \"integer\"\n                      }\n                    }\n                  }\n                },\n                \"finish_reason\": {\n                  \"type\": \"string\",\n                  \"enum\": [\n                    \"stop\",\n                    \"length\"\n                  ]\n                }\n              }\n            }\n          },\n          \"usage\": {\n            \"type\": \"object\",\n            \"properties\": {\n              \"prompt_tokens\": {\n                \"type\": \"integer\"\n              },\n              \"completion_tokens\": {\n                \"type\": \"integer\"\n              },\n              \"total_tokens\": {\n                \"type\": \"integer\"\n              }\n            },\n            \"required\": [\n              \"prompt_tokens\",\n              \"completion_tokens\",\n              \"total_tokens\"\n            ]\n          }\n        },\n        \"required\": [\n          \"id\",\n          \"object\",\n          \"created\",\n          \"model\",\n          \"choices\"\n        ]\n      },\n      \"ChatCompletionRequestMessage\": {\n        \"type\": \"object\",\n        \"properties\": {\n          \"role\": {\n            \"type\": \"string\",\n            \"enum\": [\n              \"system\",\n              \"user\",\n              \"assistant\",\n              \"function\"\n            ],\n            \"description\": \"The role of the messages author. One of `system`, `user`, `assistant`, or `function`.\"\n          },\n          \"content\": {\n            \"type\": \"string\",\n            \"description\": \"The contents of the message. `content` is required for all messages except assistant messages with function calls.\"\n          },\n          \"name\": {\n            \"type\": \"string\",\n            \"description\": \"The name of the author of this message. `name` is required if role is `function`, and it should be the name of the function whose response is in the `content`. May contain a-z, A-Z, 0-9, and underscores, with a maximum length of 64 characters.\"\n          },\n          \"function_call\": {\n            \"type\": \"object\",\n            \"description\": \"The name and arguments of a function that should be called, as generated by the model.\",\n            \"properties\": {\n              \"name\": {\n                \"type\": \"string\",\n                \"description\": \"The name of the function to call.\"\n              },\n              \"arguments\": {\n                \"type\": \"string\",\n                \"description\": \"The arguments to call the function with, as generated by the model in JSON format. Note that the model does not always generate valid JSON, and may hallucinate parameters not defined by your function schema. Validate the arguments in your code before calling your function.\"\n              }\n            }\n          }\n        },\n        \"required\": [\n          \"role\"\n        ]\n      },\n      \"ChatCompletionFunctionParameters\": {\n        \"type\": \"object\",\n        \"description\": \"The parameters the functions accepts, described as a JSON Schema object. See the [guide](/docs/guides/gpt/function-calling) for examples, and the [JSON Schema reference](https://json-schema.org/understanding-json-schema/) for documentation about the format.\",\n        \"additionalProperties\": true\n      },\n      \"ChatCompletionFunctions\": {\n        \"type\": \"object\",\n        \"properties\": {\n          \"name\": {\n            \"type\": \"string\",\n            \"description\": \"The name of the function to be called. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.\"\n          },\n          \"description\": {\n            \"type\": \"string\",\n            \"description\": \"The description of what the function does.\"\n          },\n          \"parameters\": {\n            \"$ref\": \"#/components/schemas/ChatCompletionFunctionParameters\"\n          }\n        },\n        \"required\": [\n          \"name\"\n        ]\n      },\n      \"ChatCompletionResponseMessage\": {\n        \"type\": \"object\",\n        \"properties\": {\n          \"role\": {\n            \"type\": \"string\",\n            \"enum\": [\n              \"system\",\n              \"user\",\n              \"assistant\",\n              \"function\"\n            ],\n            \"description\": \"The role of the author of this message.\"\n          },\n          \"content\": {\n            \"type\": \"string\",\n            \"description\": \"The contents of the message.\",\n            \"nullable\": true\n          },\n          \"function_call\": {\n            \"type\": \"object\",\n            \"description\": \"The name and arguments of a function that should be called, as generated by the model.\",\n            \"properties\": {\n              \"name\": {\n                \"type\": \"string\",\n                \"description\": \"The name of the function to call.\"\n              },\n              \"arguments\": {\n                \"type\": \"string\",\n                \"description\": \"The arguments to call the function with, as generated by the model in JSON format. Note that the model does not always generate valid JSON, and may hallucinate parameters not defined by your function schema. Validate the arguments in your code before calling your function.\"\n              }\n            }\n          }\n        },\n        \"required\": [\n          \"role\"\n        ]\n      },\n      \"ChatCompletionStreamResponseDelta\": {\n        \"type\": \"object\",\n        \"properties\": {\n          \"role\": {\n            \"type\": \"string\",\n            \"enum\": [\n              \"system\",\n              \"user\",\n              \"assistant\",\n              \"function\"\n            ],\n            \"description\": \"The role of the author of this message.\"\n          },\n          \"content\": {\n            \"type\": \"string\",\n            \"description\": \"The contents of the chunk message.\",\n            \"nullable\": true\n          },\n          \"function_call\": {\n            \"type\": \"object\",\n            \"description\": \"The name and arguments of a function that should be called, as generated by the model.\",\n            \"properties\": {\n              \"name\": {\n                \"type\": \"string\",\n                \"description\": \"The name of the function to call.\"\n              },\n              \"arguments\": {\n                \"type\": \"string\",\n                \"description\": \"The arguments to call the function with, as generated by the model in JSON format. Note that the model does not always generate valid JSON, and may hallucinate parameters not defined by your function schema. Validate the arguments in your code before calling your function.\"\n              }\n            }\n          }\n        }\n      },\n      \"CreateChatCompletionRequest\": {\n        \"type\": \"object\",\n        \"properties\": {\n          \"model\": {\n            \"description\": \"ID of the model to use. See the [model endpoint compatibility](/docs/models/model-endpoint-compatibility) table for details on which models work with the Chat API.\",\n            \"example\": \"gpt-3.5-turbo\",\n            \"oneOf\": [\n              {\n                \"type\": \"string\"\n              },\n              {\n                \"type\": \"string\",\n                \"enum\": [\n                  \"gpt-4\",\n                  \"gpt-4-0613\",\n                  \"gpt-4-32k\",\n                  \"gpt-4-32k-0613\",\n                  \"gpt-3.5-turbo\",\n                  \"gpt-3.5-turbo-16k\",\n                  \"gpt-3.5-turbo-0613\",\n                  \"gpt-3.5-turbo-16k-0613\"\n                ]\n              }\n            ]\n          },\n          \"messages\": {\n            \"description\": \"A list of messages comprising the conversation so far. [Example Python code](https://github.com/openai/openai-cookbook/blob/main/examples/How_to_format_inputs_to_ChatGPT_models.ipynb).\",\n            \"type\": \"array\",\n            \"minItems\": 1,\n            \"items\": {\n              \"$ref\": \"#/components/schemas/ChatCompletionRequestMessage\"\n            }\n          },\n          \"functions\": {\n            \"description\": \"A list of functions the model may generate JSON inputs for.\",\n            \"type\": \"array\",\n            \"minItems\": 1,\n            \"items\": {\n              \"$ref\": \"#/components/schemas/ChatCompletionFunctions\"\n            }\n          },\n          \"function_call\": {\n            \"description\": \"Controls how the model responds to function calls. \\\"none\\\" means the model does not call a function, and responds to the end-user. \\\"auto\\\" means the model can pick between an end-user or calling a function.  Specifying a particular function via `{\\\"name\\\":\\\\ \\\"my_function\\\"}` forces the model to call that function. \\\"none\\\" is the default when no functions are present. \\\"auto\\\" is the default if functions are present.\",\n            \"oneOf\": [\n              {\n                \"type\": \"string\",\n                \"enum\": [\n                  \"none\",\n                  \"auto\"\n                ]\n              },\n              {\n                \"type\": \"object\",\n                \"properties\": {\n                  \"name\": {\n                    \"type\": \"string\",\n                    \"description\": \"The name of the function to call.\"\n                  }\n                },\n                \"required\": [\n                  \"name\"\n                ]\n              }\n            ]\n          },\n          \"temperature\": {\n            \"type\": \"number\",\n            \"minimum\": 0,\n            \"maximum\": 2,\n            \"default\": 1,\n            \"example\": 1,\n            \"nullable\": true,\n            \"description\": \"What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic.\\n\\nWe generally recommend altering this or `top_p` but not both.\\n\"\n          },\n          \"top_p\": {\n            \"type\": \"number\",\n            \"minimum\": 0,\n            \"maximum\": 1,\n            \"default\": 1,\n            \"example\": 1,\n            \"nullable\": true,\n            \"description\": \"An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered.\\n\\nWe generally recommend altering this or `temperature` but not both.\\n\"\n          },\n          \"n\": {\n            \"type\": \"integer\",\n            \"minimum\": 1,\n            \"maximum\": 128,\n            \"default\": 1,\n            \"example\": 1,\n            \"nullable\": true,\n            \"description\": \"How many chat completion choices to generate for each input message.\"\n          },\n          \"stream\": {\n            \"description\": \"If set, partial message deltas will be sent, like in ChatGPT. Tokens will be sent as data-only [server-sent events](https://developer.mozilla.org/en-US/docs/Web/API/Server-sent_events/Using_server-sent_events#Event_stream_format) as they become available, with the stream terminated by a `data: [DONE]` message. [Example Python code](https://github.com/openai/openai-cookbook/blob/main/examples/How_to_stream_completions.ipynb).\\n\",\n            \"type\": \"boolean\",\n            \"nullable\": true,\n            \"default\": false\n          },\n          \"stop\": {\n            \"description\": \"Up to 4 sequences where the API will stop generating further tokens.\\n\",\n            \"default\": null,\n            \"oneOf\": [\n              {\n                \"type\": \"string\",\n                \"nullable\": true\n              },\n              {\n                \"type\": \"array\",\n                \"minItems\": 1,\n                \"maxItems\": 4,\n                \"items\": {\n                  \"type\": \"string\"\n                }\n              }\n            ]\n          },\n          \"max_tokens\": {\n            \"description\": \"The maximum number of [tokens](/tokenizer) to generate in the chat completion.\\n\\nThe total length of input tokens and generated tokens is limited by the model's context length. [Example Python code](https://github.com/openai/openai-cookbook/blob/main/examples/How_to_count_tokens_with_tiktoken.ipynb) for counting tokens.\\n\",\n            \"default\": \"inf\",\n            \"type\": \"integer\"\n          },\n          \"presence_penalty\": {\n            \"type\": \"number\",\n            \"default\": 0,\n            \"minimum\": -2,\n            \"maximum\": 2,\n            \"nullable\": true,\n            \"description\": \"Number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far, increasing the model's likelihood to talk about new topics.\\n\\n[See more information about frequency and presence penalties.](/docs/api-reference/parameter-details)\\n\"\n          },\n          \"frequency_penalty\": {\n            \"type\": \"number\",\n            \"default\": 0,\n            \"minimum\": -2,\n            \"maximum\": 2,\n            \"nullable\": true,\n            \"description\": \"Number between -2.0 and 2.0. Positive values penalize new tokens based on their existing frequency in the text so far, decreasing the model's likelihood to repeat the same line verbatim.\\n\\n[See more information about frequency and presence penalties.](/docs/api-reference/parameter-details)\\n\"\n          },\n          \"logit_bias\": {\n            \"type\": \"object\",\n            \"x-oaiTypeLabel\": \"map\",\n            \"default\": null,\n            \"nullable\": true,\n            \"description\": \"Modify the likelihood of specified tokens appearing in the completion.\\n\\nAccepts a json object that maps tokens (specified by their token ID in the tokenizer) to an associated bias value from -100 to 100. Mathematically, the bias is added to the logits generated by the model prior to sampling. The exact effect will vary per model, but values between -1 and 1 should decrease or increase likelihood of selection; values like -100 or 100 should result in a ban or exclusive selection of the relevant token.\\n\"\n          },\n          \"user\": {\n            \"type\": \"string\",\n            \"example\": \"user-1234\",\n            \"description\": \"A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse. [Learn more](/docs/guides/safety-best-practices/end-user-ids).\\n\"\n          }\n        },\n        \"required\": [\n          \"model\",\n          \"messages\"\n        ]\n      },\n      \"CreateChatCompletionResponse\": {\n        \"type\": \"object\",\n        \"properties\": {\n          \"id\": {\n            \"type\": \"string\"\n          },\n          \"object\": {\n            \"type\": \"string\"\n          },\n          \"created\": {\n            \"type\": \"integer\"\n          },\n          \"model\": {\n            \"type\": \"string\"\n          },\n          \"choices\": {\n            \"type\": \"array\",\n            \"items\": {\n              \"type\": \"object\",\n              \"properties\": {\n                \"index\": {\n                  \"type\": \"integer\"\n                },\n                \"message\": {\n                  \"$ref\": \"#/components/schemas/ChatCompletionResponseMessage\"\n                },\n                \"finish_reason\": {\n                  \"type\": \"string\",\n                  \"enum\": [\n                    \"stop\",\n                    \"length\",\n                    \"function_call\"\n                  ]\n                }\n              }\n            }\n          },\n          \"usage\": {\n            \"type\": \"object\",\n            \"properties\": {\n              \"prompt_tokens\": {\n                \"type\": \"integer\"\n              },\n              \"completion_tokens\": {\n                \"type\": \"integer\"\n              },\n              \"total_tokens\": {\n                \"type\": \"integer\"\n              }\n            },\n            \"required\": [\n              \"prompt_tokens\",\n              \"completion_tokens\",\n              \"total_tokens\"\n            ]\n          }\n        },\n        \"required\": [\n          \"id\",\n          \"object\",\n          \"created\",\n          \"model\",\n          \"choices\"\n        ]\n      },\n      \"CreateChatCompletionStreamResponse\": {\n        \"type\": \"object\",\n        \"properties\": {\n          \"id\": {\n            \"type\": \"string\"\n          },\n          \"object\": {\n            \"type\": \"string\"\n          },\n          \"created\": {\n            \"type\": \"integer\"\n          },\n          \"model\": {\n            \"type\": \"string\"\n          },\n          \"choices\": {\n            \"type\": \"array\",\n            \"items\": {\n              \"type\": \"object\",\n              \"properties\": {\n                \"index\": {\n                  \"type\": \"integer\"\n                },\n                \"delta\": {\n                  \"$ref\": \"#/components/schemas/ChatCompletionStreamResponseDelta\"\n                },\n                \"finish_reason\": {\n                  \"type\": \"string\",\n                  \"enum\": [\n                    \"stop\",\n                    \"length\",\n                    \"function_call\"\n                  ]\n                }\n              }\n            }\n          }\n        },\n        \"required\": [\n          \"id\",\n          \"object\",\n          \"created\",\n          \"model\",\n          \"choices\"\n        ]\n      },\n      \"CreateEditRequest\": {\n        \"type\": \"object\",\n        \"properties\": {\n          \"model\": {\n            \"description\": \"ID of the model to use. You can use the `text-davinci-edit-001` or `code-davinci-edit-001` model with this endpoint.\",\n            \"type\": \"string\",\n            \"example\": \"text-davinci-edit-001\",\n            \"oneOf\": [\n              {\n                \"type\": \"string\"\n              },\n              {\n                \"type\": \"string\",\n                \"enum\": [\n                  \"text-davinci-edit-001\",\n                  \"code-davinci-edit-001\"\n                ]\n              }\n            ]\n          },\n          \"input\": {\n            \"description\": \"The input text to use as a starting point for the edit.\",\n            \"type\": \"string\",\n            \"default\": \"\",\n            \"nullable\": true,\n            \"example\": \"What day of the wek is it?\"\n          },\n          \"instruction\": {\n            \"description\": \"The instruction that tells the model how to edit the prompt.\",\n            \"type\": \"string\",\n            \"example\": \"Fix the spelling mistakes.\"\n          },\n          \"n\": {\n            \"type\": \"integer\",\n            \"minimum\": 1,\n            \"maximum\": 20,\n            \"default\": 1,\n            \"example\": 1,\n            \"nullable\": true,\n            \"description\": \"How many edits to generate for the input and instruction.\"\n          },\n          \"temperature\": {\n            \"type\": \"number\",\n            \"minimum\": 0,\n            \"maximum\": 2,\n            \"default\": 1,\n            \"example\": 1,\n            \"nullable\": true,\n            \"description\": \"What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic.\\n\\nWe generally recommend altering this or `top_p` but not both.\\n\"\n          },\n          \"top_p\": {\n            \"type\": \"number\",\n            \"minimum\": 0,\n            \"maximum\": 1,\n            \"default\": 1,\n            \"example\": 1,\n            \"nullable\": true,\n            \"description\": \"An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered.\\n\\nWe generally recommend altering this or `temperature` but not both.\\n\"\n          }\n        },\n        \"required\": [\n          \"model\",\n          \"instruction\"\n        ]\n      },\n      \"CreateEditResponse\": {\n        \"type\": \"object\",\n        \"properties\": {\n          \"object\": {\n            \"type\": \"string\"\n          },\n          \"created\": {\n            \"type\": \"integer\"\n          },\n          \"choices\": {\n            \"type\": \"array\",\n            \"items\": {\n              \"type\": \"object\",\n              \"properties\": {\n                \"text\": {\n                  \"type\": \"string\"\n                },\n                \"index\": {\n                  \"type\": \"integer\"\n                },\n                \"logprobs\": {\n                  \"type\": \"object\",\n                  \"nullable\": true,\n                  \"properties\": {\n                    \"tokens\": {\n                      \"type\": \"array\",\n                      \"items\": {\n                        \"type\": \"string\"\n                      }\n                    },\n                    \"token_logprobs\": {\n                      \"type\": \"array\",\n                      \"items\": {\n                        \"type\": \"number\"\n                      }\n                    },\n                    \"top_logprobs\": {\n                      \"type\": \"array\",\n                      \"items\": {\n                        \"type\": \"object\"\n                      }\n                    },\n                    \"text_offset\": {\n                      \"type\": \"array\",\n                      \"items\": {\n                        \"type\": \"integer\"\n                      }\n                    }\n                  }\n                },\n                \"finish_reason\": {\n                  \"type\": \"string\",\n                  \"enum\": [\n                    \"stop\",\n                    \"length\"\n                  ]\n                }\n              }\n            }\n          },\n          \"usage\": {\n            \"type\": \"object\",\n            \"properties\": {\n              \"prompt_tokens\": {\n                \"type\": \"integer\"\n              },\n              \"completion_tokens\": {\n                \"type\": \"integer\"\n              },\n              \"total_tokens\": {\n                \"type\": \"integer\"\n              }\n            },\n            \"required\": [\n              \"prompt_tokens\",\n              \"completion_tokens\",\n              \"total_tokens\"\n            ]\n          }\n        },\n        \"required\": [\n          \"object\",\n          \"created\",\n          \"choices\",\n          \"usage\"\n        ]\n      },\n      \"CreateImageRequest\": {\n        \"type\": \"object\",\n        \"properties\": {\n          \"prompt\": {\n            \"description\": \"A text description of the desired image(s). The maximum length is 1000 characters.\",\n            \"type\": \"string\",\n            \"example\": \"A cute baby sea otter\"\n          },\n          \"n\": {\n            \"type\": \"integer\",\n            \"minimum\": 1,\n            \"maximum\": 10,\n            \"default\": 1,\n            \"example\": 1,\n            \"nullable\": true,\n            \"description\": \"The number of images to generate. Must be between 1 and 10.\"\n          },\n          \"size\": {\n            \"type\": \"string\",\n            \"enum\": [\n              \"256x256\",\n              \"512x512\",\n              \"1024x1024\"\n            ],\n            \"default\": \"1024x1024\",\n            \"example\": \"1024x1024\",\n            \"nullable\": true,\n            \"description\": \"The size of the generated images. Must be one of `256x256`, `512x512`, or `1024x1024`.\"\n          },\n          \"response_format\": {\n            \"type\": \"string\",\n            \"enum\": [\n              \"url\",\n              \"b64_json\"\n            ],\n            \"default\": \"url\",\n            \"example\": \"url\",\n            \"nullable\": true,\n            \"description\": \"The format in which the generated images are returned. Must be one of `url` or `b64_json`.\"\n          },\n          \"user\": {\n            \"type\": \"string\",\n            \"example\": \"user-1234\",\n            \"description\": \"A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse. [Learn more](/docs/guides/safety-best-practices/end-user-ids).\\n\"\n          }\n        },\n        \"required\": [\n          \"prompt\"\n        ]\n      },\n      \"ImagesResponse\": {\n        \"properties\": {\n          \"created\": {\n            \"type\": \"integer\"\n          },\n          \"data\": {\n            \"type\": \"array\",\n            \"items\": {\n              \"type\": \"object\",\n              \"properties\": {\n                \"url\": {\n                  \"type\": \"string\"\n                },\n                \"b64_json\": {\n                  \"type\": \"string\"\n                }\n              }\n            }\n          }\n        },\n        \"required\": [\n          \"created\",\n          \"data\"\n        ]\n      },\n      \"CreateImageEditRequest\": {\n        \"type\": \"object\",\n        \"properties\": {\n          \"image\": {\n            \"description\": \"The image to edit. Must be a valid PNG file, less than 4MB, and square. If mask is not provided, image must have transparency, which will be used as the mask.\",\n            \"type\": \"string\",\n            \"format\": \"binary\"\n          },\n          \"mask\": {\n            \"description\": \"An additional image whose fully transparent areas (e.g. where alpha is zero) indicate where `image` should be edited. Must be a valid PNG file, less than 4MB, and have the same dimensions as `image`.\",\n            \"type\": \"string\",\n            \"format\": \"binary\"\n          },\n          \"prompt\": {\n            \"description\": \"A text description of the desired image(s). The maximum length is 1000 characters.\",\n            \"type\": \"string\",\n            \"example\": \"A cute baby sea otter wearing a beret\"\n          },\n          \"n\": {\n            \"type\": \"integer\",\n            \"minimum\": 1,\n            \"maximum\": 10,\n            \"default\": 1,\n            \"example\": 1,\n            \"nullable\": true,\n            \"description\": \"The number of images to generate. Must be between 1 and 10.\"\n          },\n          \"size\": {\n            \"type\": \"string\",\n            \"enum\": [\n              \"256x256\",\n              \"512x512\",\n              \"1024x1024\"\n            ],\n            \"default\": \"1024x1024\",\n            \"example\": \"1024x1024\",\n            \"nullable\": true,\n            \"description\": \"The size of the generated images. Must be one of `256x256`, `512x512`, or `1024x1024`.\"\n          },\n          \"response_format\": {\n            \"type\": \"string\",\n            \"enum\": [\n              \"url\",\n              \"b64_json\"\n            ],\n            \"default\": \"url\",\n            \"example\": \"url\",\n            \"nullable\": true,\n            \"description\": \"The format in which the generated images are returned. Must be one of `url` or `b64_json`.\"\n          },\n          \"user\": {\n            \"type\": \"string\",\n            \"example\": \"user-1234\",\n            \"description\": \"A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse. [Learn more](/docs/guides/safety-best-practices/end-user-ids).\\n\"\n          }\n        },\n        \"required\": [\n          \"prompt\",\n          \"image\"\n        ]\n      },\n      \"CreateImageVariationRequest\": {\n        \"type\": \"object\",\n        \"properties\": {\n          \"image\": {\n            \"description\": \"The image to use as the basis for the variation(s). Must be a valid PNG file, less than 4MB, and square.\",\n            \"type\": \"string\",\n            \"format\": \"binary\"\n          },\n          \"n\": {\n            \"type\": \"integer\",\n            \"minimum\": 1,\n            \"maximum\": 10,\n            \"default\": 1,\n            \"example\": 1,\n            \"nullable\": true,\n            \"description\": \"The number of images to generate. Must be between 1 and 10.\"\n          },\n          \"size\": {\n            \"type\": \"string\",\n            \"enum\": [\n              \"256x256\",\n              \"512x512\",\n              \"1024x1024\"\n            ],\n            \"default\": \"1024x1024\",\n            \"example\": \"1024x1024\",\n            \"nullable\": true,\n            \"description\": \"The size of the generated images. Must be one of `256x256`, `512x512`, or `1024x1024`.\"\n          },\n          \"response_format\": {\n            \"type\": \"string\",\n            \"enum\": [\n              \"url\",\n              \"b64_json\"\n            ],\n            \"default\": \"url\",\n            \"example\": \"url\",\n            \"nullable\": true,\n            \"description\": \"The format in which the generated images are returned. Must be one of `url` or `b64_json`.\"\n          },\n          \"user\": {\n            \"type\": \"string\",\n            \"example\": \"user-1234\",\n            \"description\": \"A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse. [Learn more](/docs/guides/safety-best-practices/end-user-ids).\\n\"\n          }\n        },\n        \"required\": [\n          \"image\"\n        ]\n      },\n      \"CreateModerationRequest\": {\n        \"type\": \"object\",\n        \"properties\": {\n          \"input\": {\n            \"description\": \"The input text to classify\",\n            \"oneOf\": [\n              {\n                \"type\": \"string\",\n                \"default\": \"\",\n                \"example\": \"I want to kill them.\"\n              },\n              {\n                \"type\": \"array\",\n                \"items\": {\n                  \"type\": \"string\",\n                  \"default\": \"\",\n                  \"example\": \"I want to kill them.\"\n                }\n              }\n            ]\n          },\n          \"model\": {\n            \"description\": \"Two content moderations models are available: `text-moderation-stable` and `text-moderation-latest`.\\n\\nThe default is `text-moderation-latest` which will be automatically upgraded over time. This ensures you are always using our most accurate model. If you use `text-moderation-stable`, we will provide advanced notice before updating the model. Accuracy of `text-moderation-stable` may be slightly lower than for `text-moderation-latest`.\\n\",\n            \"nullable\": false,\n            \"default\": \"text-moderation-latest\",\n            \"example\": \"text-moderation-stable\",\n            \"oneOf\": [\n              {\n                \"type\": \"string\"\n              },\n              {\n                \"type\": \"string\",\n                \"enum\": [\n                  \"text-moderation-latest\",\n                  \"text-moderation-stable\"\n                ]\n              }\n            ]\n          }\n        },\n        \"required\": [\n          \"input\"\n        ]\n      },\n      \"CreateModerationResponse\": {\n        \"type\": \"object\",\n        \"properties\": {\n          \"id\": {\n            \"type\": \"string\"\n          },\n          \"model\": {\n            \"type\": \"string\"\n          },\n          \"results\": {\n            \"type\": \"array\",\n            \"items\": {\n              \"type\": \"object\",\n              \"properties\": {\n                \"flagged\": {\n                  \"type\": \"boolean\"\n                },\n                \"categories\": {\n                  \"type\": \"object\",\n                  \"properties\": {\n                    \"hate\": {\n                      \"type\": \"boolean\"\n                    },\n                    \"hate/threatening\": {\n                      \"type\": \"boolean\"\n                    },\n                    \"self-harm\": {\n                      \"type\": \"boolean\"\n                    },\n                    \"sexual\": {\n                      \"type\": \"boolean\"\n                    },\n                    \"sexual/minors\": {\n                      \"type\": \"boolean\"\n                    },\n                    \"violence\": {\n                      \"type\": \"boolean\"\n                    },\n                    \"violence/graphic\": {\n                      \"type\": \"boolean\"\n                    }\n                  },\n                  \"required\": [\n                    \"hate\",\n                    \"hate/threatening\",\n                    \"self-harm\",\n                    \"sexual\",\n                    \"sexual/minors\",\n                    \"violence\",\n                    \"violence/graphic\"\n                  ]\n                },\n                \"category_scores\": {\n                  \"type\": \"object\",\n                  \"properties\": {\n                    \"hate\": {\n                      \"type\": \"number\"\n                    },\n                    \"hate/threatening\": {\n                      \"type\": \"number\"\n                    },\n                    \"self-harm\": {\n                      \"type\": \"number\"\n                    },\n                    \"sexual\": {\n                      \"type\": \"number\"\n                    },\n                    \"sexual/minors\": {\n                      \"type\": \"number\"\n                    },\n                    \"violence\": {\n                      \"type\": \"number\"\n                    },\n                    \"violence/graphic\": {\n                      \"type\": \"number\"\n                    }\n                  },\n                  \"required\": [\n                    \"hate\",\n                    \"hate/threatening\",\n                    \"self-harm\",\n                    \"sexual\",\n                    \"sexual/minors\",\n                    \"violence\",\n                    \"violence/graphic\"\n                  ]\n                }\n              },\n              \"required\": [\n                \"flagged\",\n                \"categories\",\n                \"category_scores\"\n              ]\n            }\n          }\n        },\n        \"required\": [\n          \"id\",\n          \"model\",\n          \"results\"\n        ]\n      },\n      \"ListFilesResponse\": {\n        \"type\": \"object\",\n        \"properties\": {\n          \"object\": {\n            \"type\": \"string\"\n          },\n          \"data\": {\n            \"type\": \"array\",\n            \"items\": {\n              \"$ref\": \"#/components/schemas/OpenAIFile\"\n            }\n          }\n        },\n        \"required\": [\n          \"object\",\n          \"data\"\n        ]\n      },\n      \"CreateFileRequest\": {\n        \"type\": \"object\",\n        \"additionalProperties\": false,\n        \"properties\": {\n          \"file\": {\n            \"description\": \"Name of the [JSON Lines](https://jsonlines.readthedocs.io/en/latest/) file to be uploaded.\\n\\nIf the `purpose` is set to \\\"fine-tune\\\", each line is a JSON record with \\\"prompt\\\" and \\\"completion\\\" fields representing your [training examples](/docs/guides/fine-tuning/prepare-training-data).\\n\",\n            \"type\": \"string\",\n            \"format\": \"binary\"\n          },\n          \"purpose\": {\n            \"description\": \"The intended purpose of the uploaded documents.\\n\\nUse \\\"fine-tune\\\" for [Fine-tuning](/docs/api-reference/fine-tunes). This allows us to validate the format of the uploaded file.\\n\",\n            \"type\": \"string\"\n          }\n        },\n        \"required\": [\n          \"file\",\n          \"purpose\"\n        ]\n      },\n      \"DeleteFileResponse\": {\n        \"type\": \"object\",\n        \"properties\": {\n          \"id\": {\n            \"type\": \"string\"\n          },\n          \"object\": {\n            \"type\": \"string\"\n          },\n          \"deleted\": {\n            \"type\": \"boolean\"\n          }\n        },\n        \"required\": [\n          \"id\",\n          \"object\",\n          \"deleted\"\n        ]\n      },\n      \"CreateFineTuneRequest\": {\n        \"type\": \"object\",\n        \"properties\": {\n          \"training_file\": {\n            \"description\": \"The ID of an uploaded file that contains training data.\\n\\nSee [upload file](/docs/api-reference/files/upload) for how to upload a file.\\n\\nYour dataset must be formatted as a JSONL file, where each training\\nexample is a JSON object with the keys \\\"prompt\\\" and \\\"completion\\\".\\nAdditionally, you must upload your file with the purpose `fine-tune`.\\n\\nSee the [fine-tuning guide](/docs/guides/fine-tuning/creating-training-data) for more details.\\n\",\n            \"type\": \"string\",\n            \"example\": \"file-ajSREls59WBbvgSzJSVWxMCB\"\n          },\n          \"validation_file\": {\n            \"description\": \"The ID of an uploaded file that contains validation data.\\n\\nIf you provide this file, the data is used to generate validation\\nmetrics periodically during fine-tuning. These metrics can be viewed in\\nthe [fine-tuning results file](/docs/guides/fine-tuning/analyzing-your-fine-tuned-model).\\nYour train and validation data should be mutually exclusive.\\n\\nYour dataset must be formatted as a JSONL file, where each validation\\nexample is a JSON object with the keys \\\"prompt\\\" and \\\"completion\\\".\\nAdditionally, you must upload your file with the purpose `fine-tune`.\\n\\nSee the [fine-tuning guide](/docs/guides/fine-tuning/creating-training-data) for more details.\\n\",\n            \"type\": \"string\",\n            \"nullable\": true,\n            \"example\": \"file-XjSREls59WBbvgSzJSVWxMCa\"\n          },\n          \"model\": {\n            \"description\": \"The name of the base model to fine-tune. You can select one of \\\"ada\\\",\\n\\\"babbage\\\", \\\"curie\\\", \\\"davinci\\\", or a fine-tuned model created after 2022-04-21.\\nTo learn more about these models, see the\\n[Models](https://platform.openai.com/docs/models) documentation.\\n\",\n            \"default\": \"curie\",\n            \"example\": \"curie\",\n            \"nullable\": true,\n            \"oneOf\": [\n              {\n                \"type\": \"string\"\n              },\n              {\n                \"type\": \"string\",\n                \"enum\": [\n                  \"ada\",\n                  \"babbage\",\n                  \"curie\",\n                  \"davinci\"\n                ]\n              }\n            ]\n          },\n          \"n_epochs\": {\n            \"description\": \"The number of epochs to train the model for. An epoch refers to one\\nfull cycle through the training dataset.\\n\",\n            \"default\": 4,\n            \"type\": \"integer\",\n            \"nullable\": true\n          },\n          \"batch_size\": {\n            \"description\": \"The batch size to use for training. The batch size is the number of\\ntraining examples used to train a single forward and backward pass.\\n\\nBy default, the batch size will be dynamically configured to be\\n~0.2% of the number of examples in the training set, capped at 256 -\\nin general, we've found that larger batch sizes tend to work better\\nfor larger datasets.\\n\",\n            \"default\": null,\n            \"type\": \"integer\",\n            \"nullable\": true\n          },\n          \"learning_rate_multiplier\": {\n            \"description\": \"The learning rate multiplier to use for training.\\nThe fine-tuning learning rate is the original learning rate used for\\npretraining multiplied by this value.\\n\\nBy default, the learning rate multiplier is the 0.05, 0.1, or 0.2\\ndepending on final `batch_size` (larger learning rates tend to\\nperform better with larger batch sizes). We recommend experimenting\\nwith values in the range 0.02 to 0.2 to see what produces the best\\nresults.\\n\",\n            \"default\": null,\n            \"type\": \"number\",\n            \"nullable\": true\n          },\n          \"prompt_loss_weight\": {\n            \"description\": \"The weight to use for loss on the prompt tokens. This controls how\\nmuch the model tries to learn to generate the prompt (as compared\\nto the completion which always has a weight of 1.0), and can add\\na stabilizing effect to training when completions are short.\\n\\nIf prompts are extremely long (relative to completions), it may make\\nsense to reduce this weight so as to avoid over-prioritizing\\nlearning the prompt.\\n\",\n            \"default\": 0.01,\n            \"type\": \"number\",\n            \"nullable\": true\n          },\n          \"compute_classification_metrics\": {\n            \"description\": \"If set, we calculate classification-specific metrics such as accuracy\\nand F-1 score using the validation set at the end of every epoch.\\nThese metrics can be viewed in the [results file](/docs/guides/fine-tuning/analyzing-your-fine-tuned-model).\\n\\nIn order to compute classification metrics, you must provide a\\n`validation_file`. Additionally, you must\\nspecify `classification_n_classes` for multiclass classification or\\n`classification_positive_class` for binary classification.\\n\",\n            \"type\": \"boolean\",\n            \"default\": false,\n            \"nullable\": true\n          },\n          \"classification_n_classes\": {\n            \"description\": \"The number of classes in a classification task.\\n\\nThis parameter is required for multiclass classification.\\n\",\n            \"type\": \"integer\",\n            \"default\": null,\n            \"nullable\": true\n          },\n          \"classification_positive_class\": {\n            \"description\": \"The positive class in binary classification.\\n\\nThis parameter is needed to generate precision, recall, and F1\\nmetrics when doing binary classification.\\n\",\n            \"type\": \"string\",\n            \"default\": null,\n            \"nullable\": true\n          },\n          \"classification_betas\": {\n            \"description\": \"If this is provided, we calculate F-beta scores at the specified\\nbeta values. The F-beta score is a generalization of F-1 score.\\nThis is only used for binary classification.\\n\\nWith a beta of 1 (i.e. the F-1 score), precision and recall are\\ngiven the same weight. A larger beta score puts more weight on\\nrecall and less on precision. A smaller beta score puts more weight\\non precision and less on recall.\\n\",\n            \"type\": \"array\",\n            \"items\": {\n              \"type\": \"number\"\n            },\n            \"example\": [\n              0.6,\n              1,\n              1.5,\n              2\n            ],\n            \"default\": null,\n            \"nullable\": true\n          },\n          \"suffix\": {\n            \"description\": \"A string of up to 40 characters that will be added to your fine-tuned model name.\\n\\nFor example, a `suffix` of \\\"custom-model-name\\\" would produce a model name like `ada:ft-your-org:custom-model-name-2022-02-15-04-21-04`.\\n\",\n            \"type\": \"string\",\n            \"minLength\": 1,\n            \"maxLength\": 40,\n            \"default\": null,\n            \"nullable\": true\n          }\n        },\n        \"required\": [\n          \"training_file\"\n        ]\n      },\n      \"ListFineTunesResponse\": {\n        \"type\": \"object\",\n        \"properties\": {\n          \"object\": {\n            \"type\": \"string\"\n          },\n          \"data\": {\n            \"type\": \"array\",\n            \"items\": {\n              \"$ref\": \"#/components/schemas/FineTune\"\n            }\n          }\n        },\n        \"required\": [\n          \"object\",\n          \"data\"\n        ]\n      },\n      \"ListFineTuneEventsResponse\": {\n        \"type\": \"object\",\n        \"properties\": {\n          \"object\": {\n            \"type\": \"string\"\n          },\n          \"data\": {\n            \"type\": \"array\",\n            \"items\": {\n              \"$ref\": \"#/components/schemas/FineTuneEvent\"\n            }\n          }\n        },\n        \"required\": [\n          \"object\",\n          \"data\"\n        ]\n      },\n      \"CreateEmbeddingRequest\": {\n        \"type\": \"object\",\n        \"additionalProperties\": false,\n        \"properties\": {\n          \"model\": {\n            \"description\": \"ID of the model to use. You can use the [List models](/docs/api-reference/models/list) API to see all of your available models, or see our [Model overview](/docs/models/overview) for descriptions of them.\\n\",\n            \"example\": \"text-embedding-ada-002\",\n            \"oneOf\": [\n              {\n                \"type\": \"string\"\n              },\n              {\n                \"type\": \"string\",\n                \"enum\": [\n                  \"text-embedding-ada-002\"\n                ]\n              }\n            ]\n          },\n          \"input\": {\n            \"description\": \"Input text to embed, encoded as a string or array of tokens. To embed multiple inputs in a single request, pass an array of strings or array of token arrays. Each input must not exceed the max input tokens for the model (8191 tokens for `text-embedding-ada-002`). [Example Python code](https://github.com/openai/openai-cookbook/blob/main/examples/How_to_count_tokens_with_tiktoken.ipynb) for counting tokens.\\n\",\n            \"example\": \"The quick brown fox jumped over the lazy dog\",\n            \"oneOf\": [\n              {\n                \"type\": \"string\",\n                \"default\": \"\",\n                \"example\": \"This is a test.\"\n              },\n              {\n                \"type\": \"array\",\n                \"items\": {\n                  \"type\": \"string\",\n                  \"default\": \"\",\n                  \"example\": \"This is a test.\"\n                }\n              },\n              {\n                \"type\": \"array\",\n                \"minItems\": 1,\n                \"items\": {\n                  \"type\": \"integer\"\n                },\n                \"example\": \"[1212, 318, 257, 1332, 13]\"\n              },\n              {\n                \"type\": \"array\",\n                \"minItems\": 1,\n                \"items\": {\n                  \"type\": \"array\",\n                  \"minItems\": 1,\n                  \"items\": {\n                    \"type\": \"integer\"\n                  }\n                },\n                \"example\": \"[[1212, 318, 257, 1332, 13]]\"\n              }\n            ]\n          },\n          \"user\": {\n            \"type\": \"string\",\n            \"example\": \"user-1234\",\n            \"description\": \"A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse. [Learn more](/docs/guides/safety-best-practices/end-user-ids).\\n\"\n          }\n        },\n        \"required\": [\n          \"model\",\n          \"input\"\n        ]\n      },\n      \"CreateEmbeddingResponse\": {\n        \"type\": \"object\",\n        \"properties\": {\n          \"object\": {\n            \"type\": \"string\"\n          },\n          \"model\": {\n            \"type\": \"string\"\n          },\n          \"data\": {\n            \"type\": \"array\",\n            \"items\": {\n              \"type\": \"object\",\n              \"properties\": {\n                \"index\": {\n                  \"type\": \"integer\"\n                },\n                \"object\": {\n                  \"type\": \"string\"\n                },\n                \"embedding\": {\n                  \"type\": \"array\",\n                  \"items\": {\n                    \"type\": \"number\"\n                  }\n                }\n              },\n              \"required\": [\n                \"index\",\n                \"object\",\n                \"embedding\"\n              ]\n            }\n          },\n          \"usage\": {\n            \"type\": \"object\",\n            \"properties\": {\n              \"prompt_tokens\": {\n                \"type\": \"integer\"\n              },\n              \"total_tokens\": {\n                \"type\": \"integer\"\n              }\n            },\n            \"required\": [\n              \"prompt_tokens\",\n              \"total_tokens\"\n            ]\n          }\n        },\n        \"required\": [\n          \"object\",\n          \"model\",\n          \"data\",\n          \"usage\"\n        ]\n      },\n      \"CreateTranscriptionRequest\": {\n        \"type\": \"object\",\n        \"additionalProperties\": false,\n        \"properties\": {\n          \"file\": {\n            \"description\": \"The audio file object (not file name) to transcribe, in one of these formats: mp3, mp4, mpeg, mpga, m4a, wav, or webm.\\n\",\n            \"type\": \"string\",\n            \"x-oaiTypeLabel\": \"file\",\n            \"format\": \"binary\"\n          },\n          \"model\": {\n            \"description\": \"ID of the model to use. Only `whisper-1` is currently available.\\n\",\n            \"example\": \"whisper-1\",\n            \"oneOf\": [\n              {\n                \"type\": \"string\"\n              },\n              {\n                \"type\": \"string\",\n                \"enum\": [\n                  \"whisper-1\"\n                ]\n              }\n            ]\n          },\n          \"prompt\": {\n            \"description\": \"An optional text to guide the model's style or continue a previous audio segment. The [prompt](/docs/guides/speech-to-text/prompting) should match the audio language.\\n\",\n            \"type\": \"string\"\n          },\n          \"response_format\": {\n            \"description\": \"The format of the transcript output, in one of these options: json, text, srt, verbose_json, or vtt.\\n\",\n            \"type\": \"string\",\n            \"default\": \"json\"\n          },\n          \"temperature\": {\n            \"description\": \"The sampling temperature, between 0 and 1. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. If set to 0, the model will use [log probability](https://en.wikipedia.org/wiki/Log_probability) to automatically increase the temperature until certain thresholds are hit.\\n\",\n            \"type\": \"number\",\n            \"default\": 0\n          },\n          \"language\": {\n            \"description\": \"The language of the input audio. Supplying the input language in [ISO-639-1](https://en.wikipedia.org/wiki/List_of_ISO_639-1_codes) format will improve accuracy and latency.\\n\",\n            \"type\": \"string\"\n          }\n        },\n        \"required\": [\n          \"file\",\n          \"model\"\n        ]\n      },\n      \"CreateTranscriptionResponse\": {\n        \"type\": \"object\",\n        \"properties\": {\n          \"text\": {\n            \"type\": \"string\"\n          }\n        },\n        \"required\": [\n          \"text\"\n        ]\n      },\n      \"CreateTranslationRequest\": {\n        \"type\": \"object\",\n        \"additionalProperties\": false,\n        \"properties\": {\n          \"file\": {\n            \"description\": \"The audio file object (not file name) translate, in one of these formats: mp3, mp4, mpeg, mpga, m4a, wav, or webm.\\n\",\n            \"type\": \"string\",\n            \"x-oaiTypeLabel\": \"file\",\n            \"format\": \"binary\"\n          },\n          \"model\": {\n            \"description\": \"ID of the model to use. Only `whisper-1` is currently available.\\n\",\n            \"example\": \"whisper-1\",\n            \"oneOf\": [\n              {\n                \"type\": \"string\"\n              },\n              {\n                \"type\": \"string\",\n                \"enum\": [\n                  \"whisper-1\"\n                ]\n              }\n            ]\n          },\n          \"prompt\": {\n            \"description\": \"An optional text to guide the model's style or continue a previous audio segment. The [prompt](/docs/guides/speech-to-text/prompting) should be in English.\\n\",\n            \"type\": \"string\"\n          },\n          \"response_format\": {\n            \"description\": \"The format of the transcript output, in one of these options: json, text, srt, verbose_json, or vtt.\\n\",\n            \"type\": \"string\",\n            \"default\": \"json\"\n          },\n          \"temperature\": {\n            \"description\": \"The sampling temperature, between 0 and 1. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. If set to 0, the model will use [log probability](https://en.wikipedia.org/wiki/Log_probability) to automatically increase the temperature until certain thresholds are hit.\\n\",\n            \"type\": \"number\",\n            \"default\": 0\n          }\n        },\n        \"required\": [\n          \"file\",\n          \"model\"\n        ]\n      },\n      \"CreateTranslationResponse\": {\n        \"type\": \"object\",\n        \"properties\": {\n          \"text\": {\n            \"type\": \"string\"\n          }\n        },\n        \"required\": [\n          \"text\"\n        ]\n      },\n      \"Model\": {\n        \"title\": \"Model\",\n        \"properties\": {\n          \"id\": {\n            \"type\": \"string\"\n          },\n          \"object\": {\n            \"type\": \"string\"\n          },\n          \"created\": {\n            \"type\": \"integer\"\n          },\n          \"owned_by\": {\n            \"type\": \"string\"\n          }\n        },\n        \"required\": [\n          \"id\",\n          \"object\",\n          \"created\",\n          \"owned_by\"\n        ]\n      },\n      \"OpenAIFile\": {\n        \"title\": \"OpenAIFile\",\n        \"properties\": {\n          \"id\": {\n            \"type\": \"string\"\n          },\n          \"object\": {\n            \"type\": \"string\"\n          },\n          \"bytes\": {\n            \"type\": \"integer\"\n          },\n          \"created_at\": {\n            \"type\": \"integer\"\n          },\n          \"filename\": {\n            \"type\": \"string\"\n          },\n          \"purpose\": {\n            \"type\": \"string\"\n          },\n          \"status\": {\n            \"type\": \"string\"\n          },\n          \"status_details\": {\n            \"type\": \"object\",\n            \"nullable\": true\n          }\n        },\n        \"required\": [\n          \"id\",\n          \"object\",\n          \"bytes\",\n          \"created_at\",\n          \"filename\",\n          \"purpose\"\n        ]\n      },\n      \"FineTune\": {\n        \"title\": \"FineTune\",\n        \"properties\": {\n          \"id\": {\n            \"type\": \"string\"\n          },\n          \"object\": {\n            \"type\": \"string\"\n          },\n          \"created_at\": {\n            \"type\": \"integer\"\n          },\n          \"updated_at\": {\n            \"type\": \"integer\"\n          },\n          \"model\": {\n            \"type\": \"string\"\n          },\n          \"fine_tuned_model\": {\n            \"type\": \"string\",\n            \"nullable\": true\n          },\n          \"organization_id\": {\n            \"type\": \"string\"\n          },\n          \"status\": {\n            \"type\": \"string\"\n          },\n          \"hyperparams\": {\n            \"type\": \"object\"\n          },\n          \"training_files\": {\n            \"type\": \"array\",\n            \"items\": {\n              \"$ref\": \"#/components/schemas/OpenAIFile\"\n            }\n          },\n          \"validation_files\": {\n            \"type\": \"array\",\n            \"items\": {\n              \"$ref\": \"#/components/schemas/OpenAIFile\"\n            }\n          },\n          \"result_files\": {\n            \"type\": \"array\",\n            \"items\": {\n              \"$ref\": \"#/components/schemas/OpenAIFile\"\n            }\n          },\n          \"events\": {\n            \"type\": \"array\",\n            \"items\": {\n              \"$ref\": \"#/components/schemas/FineTuneEvent\"\n            }\n          }\n        },\n        \"required\": [\n          \"id\",\n          \"object\",\n          \"created_at\",\n          \"updated_at\",\n          \"model\",\n          \"fine_tuned_model\",\n          \"organization_id\",\n          \"status\",\n          \"hyperparams\",\n          \"training_files\",\n          \"validation_files\",\n          \"result_files\"\n        ]\n      },\n      \"FineTuneEvent\": {\n        \"title\": \"FineTuneEvent\",\n        \"properties\": {\n          \"object\": {\n            \"type\": \"string\"\n          },\n          \"created_at\": {\n            \"type\": \"integer\"\n          },\n          \"level\": {\n            \"type\": \"string\"\n          },\n          \"message\": {\n            \"type\": \"string\"\n          }\n        },\n        \"required\": [\n          \"object\",\n          \"created_at\",\n          \"level\",\n          \"message\"\n        ]\n      }\n    }\n  },\n  \"x-oaiMeta\": {\n    \"groups\": [\n      {\n        \"id\": \"models\",\n        \"title\": \"Models\",\n        \"description\": \"List and describe the various models available in the API. You can refer to the [Models](/docs/models) documentation to understand what models are available and the differences between them.\\n\"\n      },\n      {\n        \"id\": \"chat\",\n        \"title\": \"Chat\",\n        \"description\": \"Given a list of messages comprising a conversation, the model will return a response.\\n\"\n      },\n      {\n        \"id\": \"completions\",\n        \"title\": \"Completions\",\n        \"description\": \"Given a prompt, the model will return one or more predicted completions, and can also return the probabilities of alternative tokens at each position.\\n\"\n      },\n      {\n        \"id\": \"edits\",\n        \"title\": \"Edits\",\n        \"description\": \"Given a prompt and an instruction, the model will return an edited version of the prompt.\\n\"\n      },\n      {\n        \"id\": \"images\",\n        \"title\": \"Images\",\n        \"description\": \"Given a prompt and/or an input image, the model will generate a new image.\\n\\nRelated guide: [Image generation](/docs/guides/images)\\n\"\n      },\n      {\n        \"id\": \"embeddings\",\n        \"title\": \"Embeddings\",\n        \"description\": \"Get a vector representation of a given input that can be easily consumed by machine learning models and algorithms.\\n\\nRelated guide: [Embeddings](/docs/guides/embeddings)\\n\"\n      },\n      {\n        \"id\": \"audio\",\n        \"title\": \"Audio\",\n        \"description\": \"Learn how to turn audio into text.\\n\\nRelated guide: [Speech to text](/docs/guides/speech-to-text)\\n\"\n      },\n      {\n        \"id\": \"files\",\n        \"title\": \"Files\",\n        \"description\": \"Files are used to upload documents that can be used with features like [Fine-tuning](/docs/api-reference/fine-tunes).\\n\"\n      },\n      {\n        \"id\": \"fine-tunes\",\n        \"title\": \"Fine-tunes\",\n        \"description\": \"Manage fine-tuning jobs to tailor a model to your specific training data.\\n\\nRelated guide: [Fine-tune models](/docs/guides/fine-tuning)\\n\"\n      },\n      {\n        \"id\": \"moderations\",\n        \"title\": \"Moderations\",\n        \"description\": \"Given a input text, outputs if the model classifies it as violating OpenAI's content policy.\\n\\nRelated guide: [Moderations](/docs/guides/moderation)\\n\"\n      }\n    ]\n  }\n}",
                "uri": "http://localhost:3000/openai.json"
              }
            ]
          }
        },
        "resource_uri": "http://localhost:3000/openai.json",
        "url": "https://openai-tools.run.mcp.com.ai/mcp"
      },
      "latency_ms": 20.73,
      "status": "ok"
    },
    "resources_list": {
      "details": {
        "headers": {
          "content-type": "application/json"
        },
        "http_status": 200,
        "payload": {
          "id": 5,
          "jsonrpc": "2.0",
          "result": {
            "resources": [
              {
                "description": "The OpenAPI specification for this API",
                "mimeType": "application/json",
                "name": "OpenAPI Specification",
                "uri": "http://localhost:3000/openai.json"
              }
            ]
          }
        },
        "url": "https://openai-tools.run.mcp.com.ai/mcp"
      },
      "latency_ms": 13.26,
      "status": "ok"
    },
    "server_card": {
      "details": {
        "error": "Client error '404 Not Found' for url 'https://openai-tools.run.mcp.com.ai/.well-known/mcp/server-card.json'\nFor more information check: https://developer.mozilla.org/en-US/docs/Web/HTTP/Status/404",
        "url": "https://openai-tools.run.mcp.com.ai/.well-known/mcp/server-card.json"
      },
      "latency_ms": 225.94,
      "status": "error"
    },
    "session_resume_probe": {
      "details": {
        "protocol_version": "2025-06-18",
        "reason": "no_session_id",
        "resume_expected": true,
        "transport": "streamable-http"
      },
      "latency_ms": null,
      "status": "warning"
    },
    "step_up_auth_probe": {
      "details": {
        "auth_required_checks": [],
        "broad_scopes": [],
        "challenge_headers": [],
        "minimal_scope_documented": false,
        "oauth_present": false,
        "scope_specificity_ratio": 0.0,
        "step_up_signals": [],
        "supported_scopes": []
      },
      "latency_ms": null,
      "status": "missing"
    },
    "tool_snapshot_probe": {
      "details": {
        "added": [],
        "changed_outputs": [],
        "current_tool_count": 9,
        "previous_tool_count": 9,
        "removed": [],
        "similarity": 1.0
      },
      "latency_ms": null,
      "status": "ok"
    },
    "tools_list": {
      "details": {
        "headers": {
          "content-type": "application/json"
        },
        "http_status": 200,
        "payload": {
          "id": 2,
          "jsonrpc": "2.0",
          "result": {
            "tools": [
              {
                "description": "Creates an image given a prompt.",
                "inputSchema": {
                  "properties": {
                    "createImageBody": {
                      "properties": {
                        "n": {
                          "description": "The number of images to generate. Must be between 1 and 10.",
                          "maximum": 10,
                          "minimum": 1,
                          "type": "integer"
                        },
                        "prompt": {
                          "description": "A text description of the desired image(s). The maximum length is 1000 characters.",
                          "type": "string"
                        },
                        "response_format": {
                          "description": "The format in which the generated images are returned. Must be one of `url` or `b64_json`.",
                          "enum": [
                            "url",
                            "b64_json"
                          ],
                          "type": "string"
                        },
                        "size": {
                          "description": "The size of the generated images. Must be one of `256x256`, `512x512`, or `1024x1024`.",
                          "enum": [
                            "256x256",
                            "512x512",
                            "1024x1024"
                          ],
                          "type": "string"
                        },
                        "user": {
                          "description": "A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse. [Learn more](/docs/guides/safety-best-practices/end-user-ids).\n",
                          "type": "string"
                        }
                      },
                      "required": [
                        "prompt"
                      ],
                      "type": "object"
                    },
                    "x-hapi-auth-state": {
                      "type": "string"
                    }
                  },
                  "required": [
                    "createImageBody"
                  ],
                  "type": "object"
                },
                "name": "createImage"
              },
              {
                "description": "Creates an edited or extended image given an original image and a prompt.",
                "inputSchema": {
                  "properties": {
                    "createImageEditBody": {
                      "properties": {
                        "image": {
                          "description": "The image to edit. Must be a valid PNG file, less than 4MB, and square. If mask is not provided, image must have transparency, which will be used as the mask.",
                          "format": "binary",
                          "type": "string"
                        },
                        "mask": {
                          "description": "An additional image whose fully transparent areas (e.g. where alpha is zero) indicate where `image` should be edited. Must be a valid PNG file, less than 4MB, and have the same dimensions as `image`.",
                          "format": "binary",
                          "type": "string"
                        },
                        "n": {
                          "description": "The number of images to generate. Must be between 1 and 10.",
                          "maximum": 10,
                          "minimum": 1,
                          "type": "integer"
                        },
                        "prompt": {
                          "description": "A text description of the desired image(s). The maximum length is 1000 characters.",
                          "type": "string"
                        },
                        "response_format": {
                          "description": "The format in which the generated images are returned. Must be one of `url` or `b64_json`.",
                          "enum": [
                            "url",
                            "b64_json"
                          ],
                          "type": "string"
                        },
                        "size": {
                          "description": "The size of the generated images. Must be one of `256x256`, `512x512`, or `1024x1024`.",
                          "enum": [
                            "256x256",
                            "512x512",
                            "1024x1024"
                          ],
                          "type": "string"
                        },
                        "user": {
                          "description": "A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse. [Learn more](/docs/guides/safety-best-practices/end-user-ids).\n",
                          "type": "string"
                        }
                      },
                      "required": [
                        "prompt",
                        "image"
                      ],
                      "type": "object"
                    },
                    "x-hapi-auth-state": {
                      "type": "string"
                    }
                  },
                  "required": [
                    "createImageEditBody"
                  ],
                  "type": "object"
                },
                "name": "createImageEdit"
              },
              {
                "description": "Creates a variation of a given image.",
                "inputSchema": {
                  "properties": {
                    "createImageVariationBody": {
                      "properties": {
                        "image": {
                          "description": "The image to use as the basis for the variation(s). Must be a valid PNG file, less than 4MB, and square.",
                          "format": "binary",
                          "type": "string"
                        },
                        "n": {
                          "description": "The number of images to generate. Must be between 1 and 10.",
                          "maximum": 10,
                          "minimum": 1,
                          "type": "integer"
                        },
                        "response_format": {
                          "description": "The format in which the generated images are returned. Must be one of `url` or `b64_json`.",
                          "enum": [
                            "url",
                            "b64_json"
                          ],
                          "type": "string"
                        },
                        "size": {
                          "description": "The size of the generated images. Must be one of `256x256`, `512x512`, or `1024x1024`.",
                          "enum": [
                            "256x256",
                            "512x512",
                            "1024x1024"
                          ],
                          "type": "string"
                        },
                        "user": {
                          "description": "A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse. [Learn more](/docs/guides/safety-best-practices/end-user-ids).\n",
                          "type": "string"
                        }
                      },
                      "required": [
                        "image"
                      ],
                      "type": "object"
                    },
                    "x-hapi-auth-state": {
                      "type": "string"
                    }
                  },
                  "required": [
                    "createImageVariationBody"
                  ],
                  "type": "object"
                },
                "name": "createImageVariation"
              },
              {
                "description": "Transcribes audio into the input language.",
                "inputSchema": {
                  "properties": {
                    "createTranscriptionBody": {
                      "additionalProperties": false,
                      "properties": {
                        "file": {
                          "description": "The audio file object (not file name) to transcribe, in one of these formats: mp3, mp4, mpeg, mpga, m4a, wav, or webm.\n",
                          "format": "binary",
                          "type": "string"
                        },
                        "language": {
                          "description": "The language of the input audio. Supplying the input language in [ISO-639-1](https://en.wikipedia.org/wiki/List_of_ISO_639-1_codes) format will improve accuracy and latency.\n",
                          "type": "string"
                        },
                        "model": {
                          "description": "ID of the model to use. Only `whisper-1` is currently available.\n",
                          "type": "string"
                        },
                        "prompt": {
                          "description": "An optional text to guide the model's style or continue a previous audio segment. The [prompt](/docs/guides/speech-to-text/prompting) should match the audio language.\n",
                          "type": "string"
                        },
                        "response_format": {
                          "description": "The format of the transcript output, in one of these options: json, text, srt, verbose_json, or vtt.\n",
                          "type": "string"
                        },
                        "temperature": {
                          "description": "The sampling temperature, between 0 and 1. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. If set to 0, the model will use [log probability](https://en.wikipedia.org/wiki/Log_probability) to automatically increase the temperature until certain thresholds are hit.\n",
                          "type": "number"
                        }
                      },
                      "required": [
                        "file",
                        "model"
                      ],
                      "type": "object"
                    },
                    "x-hapi-auth-state": {
                      "type": "string"
                    }
                  },
                  "required": [
                    "createTranscriptionBody"
                  ],
                  "type": "object"
                },
                "name": "createTranscription"
              },
              {
                "description": "Translates audio into English.",
                "inputSchema": {
                  "properties": {
                    "createTranslationBody": {
                      "additionalProperties": false,
                      "properties": {
                        "file": {
                          "description": "The audio file object (not file name) translate, in one of these formats: mp3, mp4, mpeg, mpga, m4a, wav, or webm.\n",
                          "format": "binary",
                          "type": "string"
                        },
                        "model": {
                          "description": "ID of the model to use. Only `whisper-1` is currently available.\n",
                          "type": "string"
                        },
                        "prompt": {
                          "description": "An optional text to guide the model's style or continue a previous audio segment. The [prompt](/docs/guides/speech-to-text/prompting) should be in English.\n",
                          "type": "string"
                        },
                        "response_format": {
                          "description": "The format of the transcript output, in one of these options: json, text, srt, verbose_json, or vtt.\n",
                          "type": "string"
                        },
                        "temperature": {
                          "description": "The sampling temperature, between 0 and 1. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. If set to 0, the model will use [log probability](https://en.wikipedia.org/wiki/Log_probability) to automatically increase the temperature until certain thresholds are hit.\n",
                          "type": "number"
                        }
                      },
                      "required": [
                        "file",
                        "model"
                      ],
                      "type": "object"
                    },
                    "x-hapi-auth-state": {
                      "type": "string"
                    }
                  },
                  "required": [
                    "createTranslationBody"
                  ],
                  "type": "object"
                },
                "name": "createTranslation"
              },
              {
                "description": "Lists the currently available models, and provides basic information about each one such as the owner and availability.",
                "inputSchema": {
                  "properties": {
                    "x-hapi-auth-state": {
                      "type": "string"
                    }
                  },
                  "type": "object"
                },
                "name": "listModels"
              },
              {
                "description": "Retrieves a model instance, providing basic information about the model such as the owner and permissioning.",
                "inputSchema": {
                  "properties": {
                    "model": {
                      "type": "string"
                    },
                    "x-hapi-auth-state": {
                      "type": "string"
                    }
                  },
                  "required": [
                    "model"
                  ],
                  "type": "object"
                },
                "name": "retrieveModel"
              },
              {
                "description": "Delete a fine-tuned model. You must have the Owner role in your organization.",
                "inputSchema": {
                  "properties": {
                    "model": {
                      "type": "string"
                    },
                    "x-hapi-auth-state": {
                      "type": "string"
                    }
                  },
                  "required": [
                    "model"
                  ],
                  "type": "object"
                },
                "name": "deleteModel"
              },
              {
                "description": "Classifies if text violates OpenAI's Content Policy",
                "inputSchema": {
                  "properties": {
                    "createModerationBody": {
                      "properties": {
                        "input": {
                          "description": "The input text to classify",
                          "type": "string"
                        },
                        "model": {
                          "description": "Two content moderations models are available: `text-moderation-stable` and `text-moderation-latest`.\n\nThe default is `text-moderation-latest` which will be automatically upgraded over time. This ensures you are always using our most accurate model. If you use `text-moderation-stable`, we will provide advanced notice before updating the model. Accuracy of `text-moderation-stable` may be slightly lower than for `text-moderation-latest`.\n",
                          "type": "string"
                        }
                      },
                      "required": [
                        "input"
                      ],
                      "type": "object"
                    },
                    "x-hapi-auth-state": {
                      "type": "string"
                    }
                  },
                  "required": [
                    "createModerationBody"
                  ],
                  "type": "object"
                },
                "name": "createModeration"
              }
            ]
          }
        },
        "url": "https://openai-tools.run.mcp.com.ai/mcp"
      },
      "latency_ms": 15.71,
      "status": "ok"
    },
    "transport_compliance_probe": {
      "details": {
        "bad_protocol_error": null,
        "bad_protocol_headers": {
          "content-type": "application/json"
        },
        "bad_protocol_payload": {
          "error": {
            "code": -32029,
            "data": {
              "limits": {
                "monthlyLimit": 1000,
                "perMinuteLimit": 5,
                "tier": "core.basic"
              },
              "reason": "minute",
              "remainingMinute": 0,
              "remainingMonth": 992,
              "tier": "core.basic"
            },
            "message": "Rate limit exceeded"
          },
          "id": 410,
          "jsonrpc": "2.0"
        },
        "bad_protocol_status_code": 200,
        "delete_error": null,
        "delete_status_code": null,
        "expired_session_error": null,
        "expired_session_status_code": null,
        "issues": [
          "missing_session_id",
          "missing_protocol_header",
          "bad_protocol_not_rejected"
        ],
        "last_event_id_visible": false,
        "protocol_header_present": false,
        "requested_protocol_version": "2025-06-18",
        "session_id_present": false,
        "transport": "streamable-http"
      },
      "latency_ms": 15.03,
      "status": "error"
    },
    "utility_coverage_probe": {
      "details": {
        "completions": {
          "advertised": false,
          "live_probe": "not_executed",
          "sample_target": {
            "type": "resource",
            "uri": "http://localhost:3000/openai.json"
          }
        },
        "initialize_capability_keys": [
          "logging",
          "prompts",
          "resources",
          "resourcesTemplates",
          "tools"
        ],
        "pagination": {
          "metadata_signal": false,
          "next_cursor_methods": [],
          "supported": false
        },
        "tasks": {
          "advertised": false,
          "http_status": 200,
          "probe_status": "missing"
        }
      },
      "latency_ms": 13.38,
      "status": "missing"
    }
  },
  "failures": {
    "determinism_probe": {
      "attempts": 2,
      "baseline_signature": "aba67f1929703989f5a8ad04ae29f13aae9eea1c5a9bd8eab73c68bf514fd05b",
      "errors": [
        "request_failed",
        "request_failed"
      ],
      "matches": 0,
      "stable_ratio": 0.0,
      "successful": 0
    },
    "oauth_authorization_server": {
      "reason": "no_authorization_server"
    },
    "oauth_protected_resource": {
      "error": "Client error '404 Not Found' for url 'https://openai-tools.run.mcp.com.ai/.well-known/oauth-protected-resource'\nFor more information check: https://developer.mozilla.org/en-US/docs/Web/HTTP/Status/404",
      "url": "https://openai-tools.run.mcp.com.ai/.well-known/oauth-protected-resource"
    },
    "openid_configuration": {
      "reason": "no_authorization_server"
    },
    "server_card": {
      "error": "Client error '404 Not Found' for url 'https://openai-tools.run.mcp.com.ai/.well-known/mcp/server-card.json'\nFor more information check: https://developer.mozilla.org/en-US/docs/Web/HTTP/Status/404",
      "url": "https://openai-tools.run.mcp.com.ai/.well-known/mcp/server-card.json"
    },
    "transport_compliance_probe": {
      "bad_protocol_error": null,
      "bad_protocol_headers": {
        "content-type": "application/json"
      },
      "bad_protocol_payload": {
        "error": {
          "code": -32029,
          "data": {
            "limits": {
              "monthlyLimit": 1000,
              "perMinuteLimit": 5,
              "tier": "core.basic"
            },
            "reason": "minute",
            "remainingMinute": 0,
            "remainingMonth": 992,
            "tier": "core.basic"
          },
          "message": "Rate limit exceeded"
        },
        "id": 410,
        "jsonrpc": "2.0"
      },
      "bad_protocol_status_code": 200,
      "delete_error": null,
      "delete_status_code": null,
      "expired_session_error": null,
      "expired_session_status_code": null,
      "issues": [
        "missing_session_id",
        "missing_protocol_header",
        "bad_protocol_not_rejected"
      ],
      "last_event_id_visible": false,
      "protocol_header_present": false,
      "requested_protocol_version": "2025-06-18",
      "session_id_present": false,
      "transport": "streamable-http"
    }
  },
  "remote_url": "https://openai-tools.run.mcp.com.ai/mcp",
  "server_card_payload": null,
  "server_identifier": "ai.com.mcp/openai-tools"
}

Known versions

0.6.0

Validation history

7 day score delta

+0.0

30 day score delta

+0.0

Recent healthy ratio

100%

Freshness

606.0h

Timestamp	Status	Score	Latency	Tools
Apr 09, 2026 12:54:01 AM UTC	Healthy	72.5	913.4 ms	9
Apr 08, 2026 12:49:53 AM UTC	Healthy	72.5	455.4 ms	9
Apr 07, 2026 12:45:56 AM UTC	Healthy	72.5	749.0 ms	9
Apr 06, 2026 12:42:49 AM UTC	Healthy	72.5	447.5 ms	9
Apr 05, 2026 12:39:55 AM UTC	Healthy	72.5	439.9 ms	9
Apr 04, 2026 12:39:26 AM UTC	Healthy	72.5	415.6 ms	9
Apr 03, 2026 12:32:33 AM UTC	Healthy	72.5	380.0 ms	9
Apr 02, 2026 12:20:44 AM UTC	Healthy	72.5	634.1 ms	9

Validation timeline

Validated	Summary	Score	Protocol	Auth mode	Tools	High-risk tools	Changes
Apr 09, 2026 12:54:01 AM UTC	Healthy	72.5	2025-06-18	public	9	1	none
Apr 08, 2026 12:49:53 AM UTC	Healthy	72.5	2025-06-18	public	9	1	none
Apr 07, 2026 12:45:56 AM UTC	Healthy	72.5	2025-06-18	public	9	1	none
Apr 06, 2026 12:42:49 AM UTC	Healthy	72.5	2025-06-18	public	9	1	none
Apr 05, 2026 12:39:55 AM UTC	Healthy	72.5	2025-06-18	public	9	1	none
Apr 04, 2026 12:39:26 AM UTC	Healthy	72.5	2025-06-18	public	9	1	none
Apr 03, 2026 12:32:33 AM UTC	Healthy	72.5	2025-06-18	public	9	1	none
Apr 02, 2026 12:20:44 AM UTC	Healthy	72.5	2025-06-18	public	9	1	none
Mar 31, 2026 11:43:41 PM UTC	Healthy	72.5	2025-06-18	public	9	1	none
Mar 30, 2026 11:35:02 PM UTC	Healthy	72.5	2025-06-18	public	9	1	none
Mar 29, 2026 11:23:58 PM UTC	Healthy	72.5	2025-06-18	public	9	1	none
Mar 28, 2026 10:03:43 PM UTC	Healthy	72.5	2025-06-18	public	9	1	none

Recent validation runs

Started	Status	Summary	Latency	Checks
Apr 09, 2026 12:54:00 AM UTC	Completed	Healthy	913.4 ms	action_safety_probe, advanced_capabilities_probe, connector_publishability_probe, connector_replay_probe, determinism_probe, initialize, interactive_flow_probe, oauth_authorization_server, oauth_protected_resource, official_registry_probe, openid_configuration, probe_noise_resilience, prompt_get, prompts_list, protocol_version_probe, provenance_divergence_probe, request_association_probe, resource_read, resources_list, server_card, session_resume_probe, step_up_auth_probe, tool_snapshot_probe, tools_list, transport_compliance_probe, utility_coverage_probe
Apr 08, 2026 12:49:53 AM UTC	Completed	Healthy	455.4 ms	action_safety_probe, advanced_capabilities_probe, connector_publishability_probe, connector_replay_probe, determinism_probe, initialize, interactive_flow_probe, oauth_authorization_server, oauth_protected_resource, official_registry_probe, openid_configuration, probe_noise_resilience, prompt_get, prompts_list, protocol_version_probe, provenance_divergence_probe, request_association_probe, resource_read, resources_list, server_card, session_resume_probe, step_up_auth_probe, tool_snapshot_probe, tools_list, transport_compliance_probe, utility_coverage_probe
Apr 07, 2026 12:45:56 AM UTC	Completed	Healthy	749.0 ms	action_safety_probe, advanced_capabilities_probe, connector_publishability_probe, connector_replay_probe, determinism_probe, initialize, interactive_flow_probe, oauth_authorization_server, oauth_protected_resource, official_registry_probe, openid_configuration, probe_noise_resilience, prompt_get, prompts_list, protocol_version_probe, provenance_divergence_probe, request_association_probe, resource_read, resources_list, server_card, session_resume_probe, step_up_auth_probe, tool_snapshot_probe, tools_list, transport_compliance_probe, utility_coverage_probe
Apr 06, 2026 12:42:48 AM UTC	Completed	Healthy	447.5 ms	action_safety_probe, advanced_capabilities_probe, connector_publishability_probe, connector_replay_probe, determinism_probe, initialize, interactive_flow_probe, oauth_authorization_server, oauth_protected_resource, official_registry_probe, openid_configuration, probe_noise_resilience, prompt_get, prompts_list, protocol_version_probe, provenance_divergence_probe, request_association_probe, resource_read, resources_list, server_card, session_resume_probe, step_up_auth_probe, tool_snapshot_probe, tools_list, transport_compliance_probe, utility_coverage_probe
Apr 05, 2026 12:39:54 AM UTC	Completed	Healthy	439.9 ms	action_safety_probe, advanced_capabilities_probe, connector_publishability_probe, connector_replay_probe, determinism_probe, initialize, interactive_flow_probe, oauth_authorization_server, oauth_protected_resource, official_registry_probe, openid_configuration, probe_noise_resilience, prompt_get, prompts_list, protocol_version_probe, provenance_divergence_probe, request_association_probe, resource_read, resources_list, server_card, session_resume_probe, step_up_auth_probe, tool_snapshot_probe, tools_list, transport_compliance_probe, utility_coverage_probe
Apr 04, 2026 12:39:25 AM UTC	Completed	Healthy	415.6 ms	action_safety_probe, advanced_capabilities_probe, connector_publishability_probe, connector_replay_probe, determinism_probe, initialize, interactive_flow_probe, oauth_authorization_server, oauth_protected_resource, official_registry_probe, openid_configuration, probe_noise_resilience, prompt_get, prompts_list, protocol_version_probe, provenance_divergence_probe, request_association_probe, resource_read, resources_list, server_card, session_resume_probe, step_up_auth_probe, tool_snapshot_probe, tools_list, transport_compliance_probe, utility_coverage_probe
Apr 03, 2026 12:32:33 AM UTC	Completed	Healthy	380.0 ms	action_safety_probe, advanced_capabilities_probe, connector_publishability_probe, connector_replay_probe, determinism_probe, initialize, interactive_flow_probe, oauth_authorization_server, oauth_protected_resource, official_registry_probe, openid_configuration, probe_noise_resilience, prompt_get, prompts_list, protocol_version_probe, provenance_divergence_probe, request_association_probe, resource_read, resources_list, server_card, session_resume_probe, step_up_auth_probe, tool_snapshot_probe, tools_list, transport_compliance_probe, utility_coverage_probe
Apr 02, 2026 12:20:44 AM UTC	Completed	Healthy	634.1 ms	action_safety_probe, advanced_capabilities_probe, connector_publishability_probe, connector_replay_probe, determinism_probe, initialize, interactive_flow_probe, oauth_authorization_server, oauth_protected_resource, official_registry_probe, openid_configuration, probe_noise_resilience, prompt_get, prompts_list, protocol_version_probe, provenance_divergence_probe, request_association_probe, resource_read, resources_list, server_card, session_resume_probe, step_up_auth_probe, tool_snapshot_probe, tools_list, transport_compliance_probe, utility_coverage_probe
Mar 31, 2026 11:43:41 PM UTC	Completed	Healthy	406.3 ms	action_safety_probe, advanced_capabilities_probe, connector_publishability_probe, connector_replay_probe, determinism_probe, initialize, interactive_flow_probe, oauth_authorization_server, oauth_protected_resource, official_registry_probe, openid_configuration, probe_noise_resilience, prompt_get, prompts_list, protocol_version_probe, provenance_divergence_probe, request_association_probe, resource_read, resources_list, server_card, session_resume_probe, step_up_auth_probe, tool_snapshot_probe, tools_list, transport_compliance_probe, utility_coverage_probe
Mar 30, 2026 11:35:02 PM UTC	Completed	Healthy	361.8 ms	action_safety_probe, advanced_capabilities_probe, connector_publishability_probe, connector_replay_probe, determinism_probe, initialize, interactive_flow_probe, oauth_authorization_server, oauth_protected_resource, official_registry_probe, openid_configuration, probe_noise_resilience, prompt_get, prompts_list, protocol_version_probe, provenance_divergence_probe, request_association_probe, resource_read, resources_list, server_card, session_resume_probe, step_up_auth_probe, tool_snapshot_probe, tools_list, transport_compliance_probe, utility_coverage_probe