GET
/v1/schemas/groq/chat/openai%2Fv1%2Fchat%2Fcompletions?kind=output
Accept:
Response body
11 properties · 5 required · 16 $defs| property | type | description | constraints |
|---|---|---|---|
| id* | string | A unique identifier for the chat completion. | |
| choices* | object[] | A list of chat completion choices. Can be more than one if `n` is greater than 1. | |
| created* | integer | The Unix timestamp (in seconds) of when the chat completion was created. | |
| model* | string | The model used for the chat completion. | |
| object* | enum | The object type, which is always `chat.completion`. | chat.completion |
| system_fingerprint | string | This fingerprint represents the backend configuration that the model runs with. | |
| usage | CompletionUsage | Usage statistics for the completion request. | |
| usage_breakdown | ChatCompletionUsageBreakdown | Usage statistics for compound AI completion requests. | |
| service_tier | enum | The service tier used for the request. Deployments running in strict OpenAI compatibility report Groq-specific tiers as `default`. | auto | on_demand | flex | performance | default | null |
| mcp_list_tools | object[] | List of discovered MCP tools from connected servers. | |
| x_groq | XGroqNonStreaming | Groq-specific metadata for non-streaming chat completion responses. |
Validate a payload
before you spend tokensshell
$ curl -X POST https://modelschemas.com/v1/validate \
-d '{"provider":"groq","endpointId":"openai/v1/chat/completions","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}