# Mistral Chat Completion

> Mistral Chat Completion is a paid API for AI agents from Mistral AI at mistral.mpp.paywithlocus.com, paid per call via MPP, $0.005 – $0.10 (varies by model and tokens) (dynamic), status unknown (last checked 2026-10-10).

Generates AI chat completions using Mistral AI language models including Mistral Large, Codestral, Magistral reasoning, and Pixtral vision

## Facts

- Endpoint: POST https://mistral.mpp.paywithlocus.com/mistral/chat?utm_source=zero.xyz
- Price: $0.005 – $0.10 (varies by model and tokens) (dynamic)
- Payment: MPP
- Status: unknown
- Last checked: 2026-10-10
- Activations on Zero: 0
- Provider: Mistral AI
- Docs: https://docs.mistral.ai
- Website: https://mistral.ai
- Tags: llm, chat, embeddings, code, reasoning, ai
- Canonical page: https://www.zero.xyz/c/mistral-ai-chat-f65942df
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_hTJyrVb429gcabqbsVYUD

Status and success rate cover calls made through Zero and Zero's own probes. Third-party monitors may report differently.

## How to call it through Zero

Zero handles the 402 payment challenge and records the run. With the Zero CLI installed (`npm i -g @zeroxyz/cli`):

```sh
zero fetch --capability mistral-ai-chat-f65942df -d '<json body>'
```

Example prompt: Using mistral-large-latest, write me a detailed explanation of how neural networks work — keep the temperature at 0.7 and limit the response to 800 tokens.

## When to prefer this

Choose this endpoint when you need chat completions powered by Mistral AI models specifically — especially when you want access to Mistral Large for general reasoning, Codestral for code generation, Magistral for advanced reasoning tasks, or Pixtral for vision. Prefer this over OpenAI-compatible endpoints when Mistral's model capabilities, pricing, or open-weight model availability are important to your use case.

## Known failure modes

- Invalid or unsupported model ID returns 400 error
- Missing required messages array returns validation error
- Exceeding max_tokens for the selected model returns truncated output or error
- Malformed tool definitions cause tool_choice failures
- Rate limiting or quota exhaustion returns 429 error
- Invalid temperature or top_p values outside accepted ranges return 422

## How this service works

Create a chat completion. Supports function calling, JSON mode, structured output, vision, reasoning, web search, and document context.

## Output

Returns an assistant message with the generated completion text, token usage statistics, finish reason, and optionally structured JSON or tool call payloads depending on response_format and tool configuration.

## Example request

```json
{
 "model": "mistral-large-latest",
 "messages": [
  {
   "role": "user",
   "content": "Explain how machine learning algorithms work in simple terms"
  }
 ],
 "max_tokens": 500,
 "temperature": 0.7
}
```

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "required": [
  "model",
  "messages",
  "max_tokens"
 ],
 "properties": {
  "seed": {
   "type": "number",
   "description": "Deterministic sampling seed"
  },
  "stop": {
   "anyOf": [
    {
     "type": "string"
    },
    {
     "type": "array",
     "items": {}
    }
   ],
   "description": "Stop sequences"
  },
  "model": {
   "type": "string",
   "description": "Model ID (e.g. \"mistral-medium-3-5\", \"mistral-small-2603\", \"mistral-large-2512\", \"ministral-14b-2512\", \"codestral-latest\")"
  },
  "tools": {
   "type": "array",
   "items": {},
   "description": "Tool/function definitions"
  },
  "top_p": {
   "type": "number",
   "description": "Nucleus sampling (0-1)"
  },
  "messages": {
   "type": "array",
   "items": {
    "type": "object",
    "required": [
     "role"
    ],
    "properties": {
     "name": {
      "type": "string"
     },
     "role": {
      "type": "string"
     },
     "content": {
      "anyOf": [
       {
        "type": "string"
       },
       {
        "type": "array",
        "items": {
         "type": "object",
         "required": [
          "type"
         ],
         "properties": {
          "text": {
           "type": "string"
          },
          "type": {
           "type": "string"
          },
          "image_url": {
           "type": "object",
           "required": [
            "url"
           ],
           "properties": {
            "url": {
             "type": "string"
            }
           },
           "additionalProperties": true
          }
         },
         "additionalProperties": true
        }
       },
       {
        "type": "null"
       }
      ]
     },
     "tool_calls": {
      "type": "array",
      "items": {
       "type": "object",
       "additionalProperties": true
      }
     },
     "tool_call_id": {
      "type": "string"
     }
    },
    "additionalProperties": true
   },
   "description": "Conversation messages array"
  },
  "max_tokens": {
   "type": "number",
   "description": "Maximum output tokens. Required to bound metered x402 authorization."
  },
  "temperature": {
   "type": "number",
   "description": "Sampling temperature (0-2)"
  },
  "tool_choice": {
   "anyOf": [
    {
     "type": "string"
    },
    {
     "type": "object",
     "additionalProperties": true
    }
   ],
   "description": "Tool selection control"
  },
  "response_format": {
   "type": "object",
   "description": "Output format (json_object, json_schema, 
… (truncated)
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/mistral-ai-chat-f65942df/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from mistral.mpp.paywithlocus.com](https://www.zero.xyz/host/mistral.mpp.paywithlocus.com/llms.txt)