Chat Completions

Replace <BASE_URL> with https://api.x6.ai. See Endpoints.

Create a model response for a multi-turn conversation.

POST <BASE_URL>/v1/chat/completions

Protocol note: This endpoint uses the OpenAI Chat Completions request shape and works with models from GET /v1/models. For Claude images use /v1/messages.

Authentication

Required: Authorization: Bearer <API_KEY>

Request headers

Header	Required	Description
`Authorization`	Yes	Bearer API key
`Content-Type`	Yes	`application/json`
`Idempotency-Key`	No	Prevents duplicate calls within 24h
`Accept-Language` / `X-Locale`	No	Affects localized error messages where applicable

Request body

X6.AI accepts the OpenAI Chat Completions JSON shape and reads model and stream; other fields follow OpenAI-compatible behavior. For multimodal input (image_url, and video_url as public URLs only), see Parameters → Multimodal input.

{
  "model": "deepseek/deepseek-chat",
  "messages": [
    {"role": "system", "content": "You are a helpful assistant."},
    {"role": "user", "content": "Hello!"}
  ],
  "stream": false,
  "temperature": 0.7,
  "max_tokens": 1024
}

Field	Required	Description
`model`	Yes	Model id from `GET /v1/models` (e.g. `deepseek/deepseek-chat`)
`messages`	Yes	Chat message array (OpenAI format)
`stream`	No	`true` for SSE streaming — see Streaming

Non-streaming response

Returns OpenAI-compatible JSON. Example shape:

{
  "id": "chatcmpl-...",
  "object": "chat.completion",
  "choices": [
    {
      "index": 0,
      "message": {"role": "assistant", "content": "Hello! How can I help?"},
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 2000,
    "completion_tokens": 300,
    "total_tokens": 2300,
    "prompt_tokens_details": {
      "cached_tokens": 1500
    }
  }
}

prompt_tokens_details.cached_tokens (OpenAI) counts input tokens served from Prompt Cache. X6.AI uses this with cached input pricing when configured; otherwise all input tokens bill at the input rate.

Usage and Prompt Cache billing

X6.AI does not run Prompt Cache but reads cache fields from the response usage for billing:

Provider	Typical field
OpenAI	`usage.prompt_tokens_details.cached_tokens`; cache write via upstream fields such as `cache_creation_tokens` when present
Anthropic	`usage.cache_read_input_tokens`, `cache_creation_input_tokens` (plus short/long TTL buckets under `cache_creation`)

Billing uses four tiers — input / cache read / cache write (short·long TTL) / output (see Model pricing):

charge ≈ plain_input × input_rate
       + cache_read × cache_read_rate
       + cache_write_short × short_write_rate + cache_write_long × long_write_rate
       + output × output_rate
(long-context multipliers apply when the threshold is exceeded)

See the Models marketplace for rates. Server-side usage records may include cached_input_tokens and cache_write_short_tokens / cache_write_long_tokens.

Response headers (X6.AI)

Header	Description
`X-SNX-Trace-ID`	Unique request id for support
`X-SNX-Model`	Model id used for this request
`X-SNX-Provider`	Vendor identifier for the inference provider

Idempotency

Send Idempotency-Key: <unique-string> to deduplicate chat requests within 24 hours per API key. If the same key was already processed:

HTTP 409
error.code: duplicate_request

If Idempotency-Key is omitted, X6.AI may fall back to X-SNX-Trace-ID.

Routing

X6.AI selects an available service for your model id. If the request cannot be completed, you may receive 502 or 503.

Data and privacy

X6.AI does not store conversation history across requests — callers assemble messages[] on every call.

Handling	Description
Request body	X6.AI does not persist prompt/completion text by default
Usage records	Call time, model, token counts, and billing-related metadata
Support	Provide `X-SNX-Trace-ID` when contacting support

Chat history in the developer console Text chat playground lives only in the current browser session; X6.AI does not restore it from the server after refresh or close.

See Privacy Policy and Terms of Service.

Common errors

HTTP	Meaning
400	Missing `model`, invalid JSON, or illegal `video_url` (not public http(s))
401	Authentication failed
413	Request body exceeds the default 64 MB
402	Insufficient account balance (`error.code=402`)
404	Unknown or unavailable model
408	Request timeout (default 120s)
409	Idempotency conflict
429	Usage quota exceeded
502	Service temporarily unavailable
503	Service temporarily unavailable

See Errors for full reference.