Chat completion (any provider) | Gateway AI

Send an OpenAI-compatible request and Gateway AI routes it to the right provider. Use provider/model format (e.g. openai/gpt-4o, anthropic/claude-sonnet-4-6, google/gemini-2.5-flash) or a plain model name for well-known models. Set stream: true for server-sent event streaming.

Authentication

AuthorizationBearer

Your proxy key (starts with sk-proxy-…). Create one in the dashboard at app.trygateway.ai.

Request

This endpoint expects an object.

modelstringRequired

Provider and model (e.g. openai/gpt-4o, anthropic/claude-sonnet-4-6, google/gemini-2.5-flash)

messageslist of objectsRequired

streambooleanOptionalDefaults to false

temperaturedoubleOptional

max_tokensintegerOptional

Response

Chat completion response (OpenAI-compatible format)

idstring

objectstring

createdinteger

modelstring

choiceslist of objects

usageobject

$	curl -X POST https://api.trygateway.ai/v1/chat/completions \
>	-H "Authorization: Bearer <token>" \
>	-H "Content-Type: application/json" \
>	-d '{
>	"model": "openai/gpt-4o",
>	"messages": [
>	{
>	"role": "system",
>	"content": "string"
>	}
>	]
>	}'

1	{
2	"id": "string",
3	"object": "string",
4	"created": 1,
5	"model": "string",
6	"choices": [
7	{
8	"index": 1,
9	"message": {
10	"role": "string",
11	"content": "string"
12	},
13	"finish_reason": "string"
14	}
15	],
16	"usage": {
17	"prompt_tokens": 1,
18	"completion_tokens": 1,
19	"total_tokens": 1
20	}
21	}

$	curl -X POST https://api.trygateway.ai/v1/chat/completions \
>	-H "Authorization: Bearer <token>" \
>	-H "Content-Type: application/json" \
>	-d '{
>	"model": "openai/gpt-4o",
>	"messages": [
>	{
>	"role": "system",
>	"content": "string"
>	}
>	]
>	}'

1	{
2	"id": "string",
3	"object": "string",
4	"created": 1,
5	"model": "string",
6	"choices": [
7	{
8	"index": 1,
9	"message": {
10	"role": "string",
11	"content": "string"
12	},
13	"finish_reason": "string"
14	}
15	],
16	"usage": {
17	"prompt_tokens": 1,
18	"completion_tokens": 1,
19	"total_tokens": 1
20	}
21	}