Create a chat completion

Generate a model response for a conversation. POST a list of messages; the model returns the next assistant message. Supports streaming, tool calling, and structured outputs.

Authorization

bearerAuth

AuthorizationBearer <token>

Send your Merius API key as a bearer token: Authorization: Bearer riv_.... Create keys in the dashboard; the full key is shown once. Keep it server-side.

In: header

Request Body

application/json

TypeScript Definitions

Use the request body type in TypeScript.

model*string

The model slug to call. See the Models endpoint for the full list.

messages*array<>

The conversation so far.

temperature?number

Sampling temperature. Higher is more random, lower more focused.

Range0 <= value <= 2

Default1

top_p?number

Nucleus sampling. Adjust this or temperature, not both.

Range0 <= value <= 1

Default1

max_tokens?integer

Upper bound on tokens generated. Defaults to the model's remaining context.

stream?boolean

Stream the response as server-sent events.

Defaultfalse

stop?|array<string>

Up to four sequences where generation stops.

presence_penalty?number

Positive values push the model toward new topics.

Range-2 <= value <= 2

Default0

frequency_penalty?number

Positive values discourage repeating the same tokens.

Range-2 <= value <= 2

Default0

seed?integer

Best-effort determinism for the same seed and parameters.

tools?array<>

Function definitions the model may call.

response_format?

Request JSON or a JSON schema for structured outputs.

Response Body

`application/json`

curl -X POST "https://example.com/chat/completions" \  -H "Content-Type: application/json" \  -d '{    "model": "z-ai/glm-5.1",    "messages": [      {        "role": "system",        "content": "You are concise."      },      {        "role": "user",        "content": "Name three primary colors."      }    ],    "temperature": 0.7  }'

{  "id": "chatcmpl-9f3a",  "object": "chat.completion",  "created": 1768000000,  "model": "z-ai/glm-5.1",  "choices": [    {      "index": 0,      "message": {        "role": "system",        "content": "string"      },      "finish_reason": "stop"    }  ],  "usage": {    "prompt_tokens": 0,    "completion_tokens": 0,    "total_tokens": 0  }}

{  "error": {    "message": "Unknown model: gpt-foo",    "type": "invalid_request_error",    "param": "model",    "code": "model_not_found"  }}

{  "error": {    "message": "Unknown model: gpt-foo",    "type": "invalid_request_error",    "param": "model",    "code": "model_not_found"  }}

{  "error": {    "message": "Unknown model: gpt-foo",    "type": "invalid_request_error",    "param": "model",    "code": "model_not_found"  }}

{  "error": {    "message": "Unknown model: gpt-foo",    "type": "invalid_request_error",    "param": "model",    "code": "model_not_found"  }}

{  "error": {    "message": "Unknown model: gpt-foo",    "type": "invalid_request_error",    "param": "model",    "code": "model_not_found"  }}

{  "error": {    "message": "Unknown model: gpt-foo",    "type": "invalid_request_error",    "param": "model",    "code": "model_not_found"  }}

Create a chat completion

Authorization

Request Body

Response Body

200application/json

400application/json

401application/json

402application/json

404application/json

429application/json

500application/json

`application/json`

`application/json`

`application/json`

`application/json`

`application/json`

`application/json`

`application/json`