curl --request POST \
  --url https://api.omnirelay.ai/v1/chat/completions \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "gpt-6-luna",
  "messages": [
    {
      "role": "system",
      "content": "Answer concisely."
    },
    {
      "role": "user",
      "content": "Hello OmniRelay"
    }
  ]
}
'

{
  "id": "chatcmpl-example",
  "object": "chat.completion",
  "created": 1790985600,
  "model": "gpt-6-luna",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Hello."
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 10,
    "completion_tokens": 5,
    "total_tokens": 15
  },
  "cost_microusd": 30
}

{
  "error": {
    "code": "unsupported_parameter"
  },
  "request_id": "2f6c1d0e9a"
}

{
  "error": {
    "code": "unauthorized"
  }
}

{
  "error": {
    "code": "insufficient_balance"
  },
  "request_id": "2f6c1d0e9a"
}

{
  "error": {
    "code": "model_not_allowed"
  },
  "request_id": "2f6c1d0e9a"
}

{
  "error": {
    "code": "model_unavailable"
  },
  "request_id": "2f6c1d0e9a"
}

{
  "error": {
    "code": "payload_too_large"
  },
  "request_id": "2f6c1d0e9a"
}

{
  "error": {
    "code": "rate_limited"
  },
  "request_id": "2f6c1d0e9a"
}

{
  "error": {
    "code": "model_unavailable",
    "message": "The model does not exist or is disabled.",
    "type": "not_found_error",
    "param": "<string>"
  },
  "request_id": "<string>"
}

{
  "error": {
    "code": "live_provider_not_configured"
  },
  "request_id": "2f6c1d0e9a"
}

Chat

Create chat completion

Calls an enabled model with its protocol-specific reviewed capabilities. Query GET /v1/models for tools, JSON formats, sampling, reasoning and combination restrictions. Capability review covers every callable route. New combinations are documentation-based, pending individual live validation. Reserves and settles validated usage; disable automatic SDK retries. Responses is stateless/store:false; hosted tools and stored IDs are unsupported. All callable routes use parameter passthrough (parameter_policy upstream-first). Capability lists are guidance, not local rejection lists; ordinary schemas and extension fields are forwarded. Native responses/reasoning output is retained. Model provider 400/422 rejections release holds; provider failures, timeouts and interrupted streams need reconciliation.

POST

chat

completions

curl --request POST \
  --url https://api.omnirelay.ai/v1/chat/completions \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "gpt-6-luna",
  "messages": [
    {
      "role": "system",
      "content": "Answer concisely."
    },
    {
      "role": "user",
      "content": "Hello OmniRelay"
    }
  ]
}
'

{
  "id": "chatcmpl-example",
  "object": "chat.completion",
  "created": 1790985600,
  "model": "gpt-6-luna",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Hello."
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 10,
    "completion_tokens": 5,
    "total_tokens": 15
  },
  "cost_microusd": 30
}

{
  "error": {
    "code": "unsupported_parameter"
  },
  "request_id": "2f6c1d0e9a"
}

{
  "error": {
    "code": "unauthorized"
  }
}

{
  "error": {
    "code": "insufficient_balance"
  },
  "request_id": "2f6c1d0e9a"
}

{
  "error": {
    "code": "model_not_allowed"
  },
  "request_id": "2f6c1d0e9a"
}

{
  "error": {
    "code": "model_unavailable"
  },
  "request_id": "2f6c1d0e9a"
}

{
  "error": {
    "code": "payload_too_large"
  },
  "request_id": "2f6c1d0e9a"
}

{
  "error": {
    "code": "rate_limited"
  },
  "request_id": "2f6c1d0e9a"
}

{
  "error": {
    "code": "model_unavailable",
    "message": "The model does not exist or is disabled.",
    "type": "not_found_error",
    "param": "<string>"
  },
  "request_id": "<string>"
}

{
  "error": {
    "code": "live_provider_not_configured"
  },
  "request_id": "2f6c1d0e9a"
}

Authorizations

Authorization

string

header

required

An API key created in the OmniRelay console. The owner can view it again in the console after confirming their identity.

Headers

X-Gateway-Tags

string

Tags for this call as comma-separated key=value pairs, for example client=acme,env=prod. Merged with the API key's default tags; the tags body field wins on the same key. X-OmniRelay-Tags is the same header under its former name and stays accepted.

X-Gateway-Metadata

enum<string>

Send enabled to receive a gateway_metadata block describing what the gateway decided. Any other value, or no header, leaves the response unchanged. X-OmniRelay-Metadata is the same header under its former name and stays accepted.

Available options:

enabled

Body

application/json

Parameter passthrough: ordinary extension fields are forwarded; authentication, text/function protocol and budget settlement boundaries remain enforced.

model

string

required

An active model ID from GET /v1/models.

Example:

"gpt-6-luna"

messages

object[]

required

1 to 2000 text messages within the model context contract. Request body limit: 4 MiB (4194304 bytes of UTF-8). Provider-context-ceiling reserves input/output separately; the provider validates actual context fit.

Required array length: 1 - 2000 elements

Show child attributes

stream

boolean

default:false

Deliver the answer as server-sent events instead of one JSON body.

stream_options

object

Only read when stream is true.

Show child attributes

tags

object

Tags for this call. At most 10 after merging with the header and the key's default tags. Keys are 1 to 64 characters and stored in lowercase; values are 1 to 128 characters. Both use only letters, digits and - _ . : /. Keys starting with gateway: or omnirelay: are reserved. A tags field that is not an object is ignored.

Show child attributes

Example:

{ "client": "acme", "project": "invoices" }

max_tokens

integer

Live only. Positive integer; send one output-limit field, never both. The gateway normalizes it for the model. Read limits.output_tokens and limits.default_output_tokens from your model list; GPT 5.4 Mini uses 64/256; most other integrated text routes default to 32,000 up to 128,000 (Gemini 3.1 Pro Preview and Gemini 3.6 Flash: 65,536); DeepSeek V4 Pro, GLM 5.3 and Kimi K3 use 4,096/4,096.

Required range: x >= 1

max_completion_tokens

integer

Required range: x >= 1

temperature

number

Forwarded; the model provider decides and may ignore unsupported values. Consult model-specific documented guidance.

Required range: 0 <= x <= 2

top_p

number

Forwarded; the model provider decides and may ignore unsupported values. Consult model-specific documented guidance.

Required range: 0 <= x <= 1

frequency_penalty

number

Live only and only when supported by the reviewed endpoint.

Required range: -2 <= x <= 2

presence_penalty

number

Live only and only when supported by the reviewed endpoint.

Required range: -2 <= x <= 2

seed

integer

Live only and only when supported by the reviewed endpoint.

stop

Live only and only when supported by the reviewed endpoint.

Maximum string length: 256

enum<integer>

Live only. Multiple completions per request are not supported.

Available options:

1

tools

object[]

Live only when tools are supported. Function tools only; strict tools and JSON Schema keywords require separate support. See the provider integration guide.

Required array length: 1 - 64 elements

Show child attributes

tool_choice

Use auto, none or required when tool_choice is advertised. Named function selection additionally requires capabilities.named_tool_choice.

Available options:

auto,

none,

required

parallel_tool_calls

boolean

Live only and only when supported by the reviewed endpoint.

response_format

object

Forwarded; the model provider decides and may ignore unsupported values. Consult model-specific documented guidance.

Show child attributes

reasoning_effort

string

Forwarded; the model provider decides and may ignore unsupported values. Consult model-specific documented guidance.

thinking

object

Only for models advertising thinking_modes; GLM 5.3 only accepts enabled.

Show child attributes

tool_stream

boolean

For models advertising tool_stream; true requires stream:true.

Response

Completion with settled usage and cost, or an SSE stream. A failed stream may emit an error after HTTP 200 and ends without [DONE].

string

required

Example:

"chatcmpl-2f6c1d0e9a"

object

enum<string>

required

Available options:

chat.completion

created

integer

required

Unix timestamp in seconds.

model

string

required

choices

object[]

required

Show child attributes

usage

object

required

Validated provider usage; missing or invalid usage prevents automatic settlement. Prompt usage includes cache partitions; completion includes reasoning. Omitted detail counters do not erase token usage.

Show child attributes

cost_microusd

integer

required

Settled customer charge in micro-USD, using frozen prices, token partitions, tiers and discount. Round the full sum, apply the discount and round up again. This is the final charge, not the maximum hold.

omnirelay_metadata

object

Present only when the request sent X-Gateway-Metadata: enabled. Returned under both gateway_metadata and its former name omnirelay_metadata, with the same content. On a stream it rides the first chunk.

Show child attributes

gateway_metadata

object

Show child attributes

Service

Models

Chat

Management

Responses

Embeddings

Images

Videos

Create chat completion

Authorizations

Headers

Body

Response