Chat Completion with Ministral 7B

What it does

Ministral Chat Completion generates replies from a conversation using Ministral 7B Instruct, with the same request and response shape as the OpenAI Chat Completions API. Send a messages array of system, user, and assistant turns with model set to mistral-7b, and the generated reply comes back in a single synchronous call. There are no job IDs and no polling.

You can tune each call with max_tokens (default 512) and temperature (0 to 2, default 0.7). The reply is in choices[].message.content. The finish_reason field is stop or length, so you can tell when output was cut off. A usage object gives prompt, completion, and total token counts for tracking consumption.

Use it for chatbots and conversational agents, drafting and rewriting copy, summarising short text, Q&A over content you pass in, and other general language tasks where a fast reply matters more than frontier-model depth. If your code already builds OpenAI-style chat payloads, you can send them as they are.

Note: Runs Ministral-7B-Instruct-2410 (AWQ quantized) on a dedicated NVIDIA RTX 4070 Ti SUPER via vLLM. Typical response time is 1–3 seconds, depending on max_tokens.

POST

Chat completion (Ministral 7B)

https://api.eu.apyhub.com/mastera-ai/chat-completion-with-ministral-7b/v1/mistral/chat/completions

QUICKSTART

GUIDE

Quickstart

curl -X POST "https://api.eu.apyhub.com/mastera-ai/chat-completion-with-ministral-7b/v1/mistral/chat/completions" \
  -H "apy-token: $APY_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "mistral-7b",
    "messages": [
      {"role": "system", "content": "You are a helpful assistant."},
      {"role": "user", "content": "Write a short haiku about the ocean."}
    ],
    "max_tokens": 200,
    "temperature": 0.7
  }'

What you'll get back

{
  "id": "chatcmpl-ae8e9f07da25157e",
  "object": "chat.completion",
  "created": 1790318354,
  "model": "mistral-7b",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Deep blue whisper\nSalt-kissed waves embrace\nEternal tide.",
        "refusal": null,
        "annotations": null,
        "audio": null,
        "function_call": null,
        "tool_calls": [],
        "reasoning": null
      },
      "logprobs": null,
      "finish_reason": "stop",
      "stop_reason": null,
      "token_ids": null,
      "routed_experts": null
    }
  ],
  "service_tier": null,
  "system_fingerprint": "vllm-0.23.0-bfb893d8",
  "usage": {
    "prompt_tokens": 18,
    "total_tokens": 34,
    "completion_tokens": 16,
    "prompt_tokens_details": null
  },
  "prompt_logprobs": null,
  "prompt_token_ids": null,
  "prompt_text": null,
  "kv_transfer_params": null
}

TRY ITLIVE · 1 ATOM

API key

Loading your default key…

The full key is used to call the gateway and stays in this tab — never sent to orbit or saved.

About this endpoint

What it does

OpenAI-compatible chat completions using Ministral 7B. Send model ("mistral-7b"), a messages array (each item has role and content), and optionally max_tokens and temperature. Supports system, user, and assistant roles in any standard OpenAI conversation shape. Returns a single JSON response with the generated reply — no polling, no task ID.

Request Body

Parameter	Type	Mandatory	Description
model	String	Yes	Must be `mistral-7b`.
messages	Array	Yes	List of `{role, content}` objects, OpenAI chat format. At least one message.
messages[].role	String	Yes	`system`, `user` or `assistant`.
messages[].content	String	Yes	The message text.
max_tokens	Integer	No	Maximum tokens to generate. Default: `512`. Prompt plus `max_tokens` must fit the 6,144-token context window.
temperature	Number	No	Sampling temperature, `0`–`2`. Default: `0.7`.

Response

Returns a standard OpenAI chat completion object with the generated reply in choices[].message.content.

Field	Type	Description
id	String	Completion id, e.g. `chatcmpl-ae8e9f07da25157e`.
object	String	Always `chat.completion`.
created	Integer	Unix timestamp (seconds) of the completion.
model	String	Model used, `mistral-7b`.
choices	Array	Generated replies (one item).
choices[].index	Integer	Position of the choice, `0`.
choices[].message.role	String	Always `assistant`.
choices[].message.content	String	The generated reply.
choices[].message.tool_calls	Array	Always empty; tool calling is not enabled.
choices[].finish_reason	String	`stop` (natural end) or `length` (hit `max_tokens`).
system_fingerprint	String	Serving-stack build id, e.g. `vllm-0.23.0-bfb893d8`.
usage.prompt_tokens	Integer	Tokens in the prompt.
usage.completion_tokens	Integer	Tokens generated.
usage.total_tokens	Integer	Sum of the two.

Notes

Response time is typically 1–3 seconds and scales with max_tokens. No messages history is stored server-side — send the full conversation each time. Context window is 6,144 tokens (prompt + output). Streaming (stream: true) is not supported on this endpoint.

▣ COMMON ERRORS

Errors any endpoint can return

400bad_request

Required parameter missing or malformed body.

401unauthorized

API key missing, revoked, or not authorized for this service.

429rate_limited

Your plan's per-second rate exceeded. Retry with exponential backoff.

503upstream_busy

Backend temporarily unavailable. Try again in a few seconds.

Similar APIs

Closest matches in the catalog based on this service.

CALLChat Completion Generation APIDosvak LLC CALLSimple Chat Prompt APIDosvak LLC CALLAI Text Moderation APIApyHub CALLConvert Speech to Text with (Whisper Large-v3)MasterA AI

From the blog

Reads that touch this API.

ChatGPT, Claude and Grok Went Down Together. What That Says About How We Use Them.Sep 8, 2026 How to Extend ChatGPT's Capabilities With Plugins: Files, Data, Validation and MoreSep 22, 2026 Best Free AI Chatbots You Can Use in 2026Aug 10, 2026 AI Meeting Transcript Summarizer with NodeJS & APIsAug 5, 2026