Chat Completions

Create chat completions using various LLM models. Compatible with the OpenAI chat completions API format.

Create chat completion

post

Creates a chat completion for the provided messages using the specified model. This endpoint is compatible with the OpenAI chat completions API format.

The request is validated and then routed to the appropriate LLM provider. Your account balance is checked before processing.

Authorizations

bearerAuth

AuthorizationstringRequired

Bearer token authentication using your API key.

Include your API key in the Authorization header:

Authorization: Bearer YOUR_API_KEY

Generate API keys from your Grid Dashboard.

Body

application/json

modelstringOptionalExample: chat-prime

max_tokensinteger · min: 1 · nullableOptionalDeprecated

max_completion_tokensinteger · min: 1 · nullableOptional

temperaturenumber · max: 2 · nullableOptionalDefault: 1

top_pnumber · max: 1 · nullableOptionalDefault: 1

ninteger · min: 1 · max: 128 · nullableOptionalDefault: 1

streamboolean · nullableOptionalDefault: false

stopone of · nullableOptional

stringOptional

or

string[] · max: 4Optional

logprobsboolean · nullableOptionalDefault: false

top_logprobsinteger · max: 20 · nullableOptional

response_formatone of · nullableOptional

or

or

tool_choiceone of · nullableOptional

string · enumOptionalPossible values:

or

parallel_tool_callsbooleanOptionalDefault: true

frequency_penaltynumber · min: -2 · max: 2 · nullableOptionalDefault: 0

presence_penaltynumber · min: -2 · max: 2 · nullableOptionalDefault: 0

seedinteger · nullableOptional

service_tierstring · enum · nullableOptionalPossible values:

reasoning_effortstring · enum · nullableOptionalPossible values:

storeboolean · nullableOptional

verbositystring · enum · nullableOptionalPossible values:

prompt_cache_keystring · nullableOptional

prompt_cache_retentionstring · enum · nullableOptionalPossible values:

safety_identifierstring · nullableOptional

routestring · enumOptionalPossible values:

providerobjectOptional

userstringOptionalDeprecated

Responses

200

Chat completion response

application/json

idstringRequiredExample: chatcmpl-abc123

objectstring · enumRequiredPossible values:

createdintegerRequiredExample: 1677858242

modelstringRequiredExample: chat-prime

system_fingerprintstring · nullableOptional

service_tierstring · enum · nullableOptionalPossible values:

400

Bad Request - Invalid parameters

application/json

401

Unauthorized - Invalid or missing API key

application/json

404

Not Found - Model not found

application/json

422

Validation Error

application/json

429

Rate Limit Exceeded

application/json

500

Internal Server Error

application/json

503

Service Unavailable - Balance replenishment in progress. Retry the request after a short delay.

application/json

post

/chat/completions

cURLPythonJavaScriptOpenAI SDK

curl -X POST 'https://api.cortex.thegrid.ai/api/v1/chat/completions' \
  -H 'Authorization: Bearer YOUR_API_KEY' \
  -H 'Content-Type: application/json' \
  -d '{
    "model": "chat-prime",
    "messages": [
      {"role": "system", "content": "Be concise and to the point."},
      {"role": "user", "content": "Write one paragraph on why inference needs a market."}
    ],
    "max_tokens": 500
  }'

{
  "id": "chatcmpl-abc123",
  "object": "chat.completion",
  "created": 1677858242,
  "model": "chat-prime",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Inference - the real‑time application of trained AI models to generate predictions, classifications, or recommendations - requires a market because its value is realized only when it can be delivered as a scalable, reliable service to end users. A market provides the economic incentives for developers to invest in optimizing hardware, software, and infrastructure that reduce latency, improve accuracy, and lower cost per query; it creates competition that drives innovation in model compression, edge deployment, and pricing models (pay‑per‑call, subscription, or platform‑as‑a‑service). Moreover, a market facilitates the aggregation of demand across diverse industries—healthcare, finance, retail, autonomous systems—allowing providers to achieve economies of scale, standardize APIs, and ensure compliance and security standards. Without such a marketplace, inference would remain a fragmented, research‑only capability, lacking the financial and operational mechanisms needed for widespread, sustainable adoption."
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 25,
    "completion_tokens": 18,
    "total_tokens": 43
  }
}