Chat Completion

Use the chat completion endpoint to drive multi-turn conversations, tool calls, or streaming assistants with stateful message histories.

Endpoint

Base URL: https://devnet.aimo.network/api/v1
POST /chat/completions
Requires Authorization: Bearer <API_KEY> header
Optional X-Request-ID to aid tracing and log correlation

Request Body

Field	Type	Required	Notes
`model`	string	Yes	`provider_pubkey:model_name` (e.g. `8W7X1tGnWh9CXwnPD7wgke31Gdcqmex4LapJvQ2afBUq:deepseek-chat-v3`)
`messages`	array	Yes	OpenAI-compatible role/content messages
`tools`	array	No	Declares tool definitions the model may call
`tool_choice`	string/object	No	Force a specific tool or allow the model to choose
`temperature`	number	No	Float between 0 and 2; defaults to 0.7
`top_p`	number	No	Alternative to `temperature`; defaults to 1
`max_tokens`	integer	No	Caps completion length; provider default if omitted
`stream`	boolean	No	Enables server-sent events response
`metadata`	object	No	Arbitrary key/value pairs forwarded to logs

Response

Returns id, created, and the selected model
choices array includes message text, tool calls, and finish reason
usage block reports input/output token counts
Streaming responses emit SSE data: payloads ending with [DONE]

Examples

Basic request

curl -X POST "https://devnet.aimo.network/api/v1/chat/completions" \
  -H "Authorization: Bearer aimo-sk-dev-your-api-key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "8W7X1tGnWh9CXwnPD7wgke31Gdcqmex4LapJvQ2afBUq:deepseek-chat-v3",
    "messages": [
      {"role": "user", "content": "Explain quantum computing in one paragraph."}
    ],
    "max_tokens": 250,
    "temperature": 0.7
  }'

Sample response

{
  "id": "chatcmpl-abc123",
  "object": "chat.completion",
  "created": 1718822400,
  "model": "8W7X1tGnWh9CXwnPD7wgke31Gdcqmex4LapJvQ2afBUq:deepseek-chat-v3",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Quantum computing leverages..."
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 15,
    "completion_tokens": 72,
    "total_tokens": 87
  }
}

Streaming in JavaScript

const response = await fetch("https://devnet.aimo.network/api/v1/chat/completions", {
  method: "POST",
  headers: {
    "Authorization": "Bearer aimo-sk-dev-your-api-key",
    "Content-Type": "application/json"
  },
  body: JSON.stringify({
    model: "8W7X1tGnWh9CXwnPD7wgke31Gdcqmex4LapJvQ2afBUq:deepseek-chat-v3",
    messages: [
      { role: "user", content: "Tell me about blockchain technology." }
    ],
    stream: true
  })
});
 
const reader = response.body.getReader();
const decoder = new TextDecoder();
 
while (true) {
  const { done, value } = await reader.read();
  if (done) break;
  const chunk = decoder.decode(value);
  console.log(chunk); // Each chunk is an SSE frame such as "data: {...}" or "data: [DONE]"
}

Python example

import requests
 
url = "https://devnet.aimo.network/api/v1/chat/completions"
headers = {
    "Authorization": "Bearer aimo-sk-dev-your-api-key",
    "Content-Type": "application/json"
}
 
payload = {
    "model": "8W7X1tGnWh9CXwnPD7wgke31Gdcqmex4LapJvQ2afBUq:deepseek-chat-v3",
    "messages": [
        {"role": "user", "content": "What is machine learning?"}
    ],
    "stream": False,
    "max_tokens": 300
}
 
response = requests.post(url, headers=headers, json=payload, timeout=30)
response.raise_for_status()
print(response.json())

Error Codes

HTTP Code	Meaning	Guidance
400	Invalid payload	Verify schema and required fields
401	Unauthorized	Check token scope and expiry
429	Rate limit	Slow down or request higher quota
500	Provider failure	Retry with backoff or failover