Chat Completions | JoyToken

Creates a model response for a chat conversation. This endpoint accepts OpenAI-compatible chat payloads and adds JoyToken routing, policy, wallet, and usage metadata around the provider call.

Authentication

AuthorizationBearer

Use Authorization: Bearer $JOY_TOKEN_API_KEY.

Request

This endpoint expects an object.

messageslist of objectsRequired

OpenAI-compatible chat messages.

modelstringOptional

Model ID. Use auto or omit to let JoyToken route automatically.

tierenumOptional

JoyToken model tier.

streambooleanOptionalDefaults to false

Return an OpenAI-compatible SSE stream when true.

temperaturedoubleOptional0-2

Sampling temperature forwarded to the selected provider when supported.

top_pdoubleOptional0-1

Nucleus sampling value forwarded to the selected provider when supported.

max_tokensintegerOptional>=1

Maximum output tokens. Also participates in JoyToken billing estimation.

userstringOptional

Optional end-user identifier used as route session context.

toolslist of objectsOptional

OpenAI-compatible tool definitions.

Response headers

X-DAOE-Used-Modelstring

The final model selected by JoyToken routing.

X-DAOE-Used-Providerstring

The provider that served the request.

X-DAOE-Failoverstring

Present on streaming responses when provider failover occurred.

Response

Successful chat completion response.

idstring

objectstring

choiceslist of objects

createdlong

modelstring

usageobject

metadataobject

JoyToken routing and billing metadata appended by the gateway when available.

Errors

400

Bad Request Error

401

Unauthorized Error

402

Payment Required Error

403

Forbidden Error

429

Too Many Requests Error

500

Internal Server Error

$	curl -X POST https://api-dev.joytokens.ai/openai/v1/chat/completions \
>	-H "Authorization: Bearer <token>" \
>	-H "Content-Type: application/json" \
>	-d '{
>	"messages": [
>	{
>	"role": "system",
>	"content": "You are concise."
>	},
>	{
>	"role": "user",
>	"content": "Explain JoyToken in one sentence."
>	}
>	],
>	"model": "auto",
>	"tier": "standard",
>	"stream": false,
>	"temperature": 0.2
>	}'

1	{
2	"id": "chatcmpl_xxx",
3	"object": "chat.completion",
4	"choices": [
5	{
6	"index": 0,
7	"message": {
8	"role": "assistant",
9	"content": "JoyToken is a governed model gateway for OpenAI-compatible apps."
10	},
11	"finish_reason": "stop"
12	}
13	],
14	"created": 1793395200,
15	"model": "GLM-5",
16	"usage": {
17	"prompt_tokens": 24,
18	"completion_tokens": 14,
19	"total_tokens": 38
20	},
21	"metadata": {
22	"model": "GLM-5",
23	"tier": "standard",
24	"score": 7.57,
25	"billing": {
26	"credits_used": "0.2288",
27	"input_tokens": 24,
28	"output_tokens": 14
29	}
30	}
31	}

Authentication

Headers

Request

Response headers

Response

Errors