Axerity

The Chat API allows you to send messages and receive AI-generated responses from various models.

Credit Usage

Credits are charged per message in your conversation. See Models for pricing.

Endpoints

Method	Endpoint	Description
POST	`/api/v1/chat`	Create chat completion

Create Completion (POST)

POST https://axerity.com/api/v1/chat

Request Body

Prop

Type

Message Object

Prop

Type

Example

curl -X POST https://axerity.com/api/v1/chat \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "model": "openai/gpt-oss-120b",
    "messages": [
      { "role": "system", "content": "You are a helpful assistant." },
      { "role": "user", "content": "Hello!" }
    ],
    "temperature": 0.7
  }'

Response

{
  "id": "chat_abc123",
  "model": "openai/gpt-oss-120b",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Hello! How can I help you today?"
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 12,
    "completion_tokens": 9,
    "total_tokens": 21
  }
}

Streaming

Set stream: true to receive responses as server-sent events.

Example

curl -X POST https://axerity.com/api/v1/chat \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "model": "openai/gpt-oss-120b",
    "messages": [{ "role": "user", "content": "Hello!" }],
    "stream": true
  }'

Response Format

data: {"id":"chat_abc123","choices":[{"delta":{"content":"Hello"}}]}
data: {"id":"chat_abc123","choices":[{"delta":{"content":"!"}}]}
data: {"id":"chat_abc123","choices":[{"delta":{"content":" How"}}]}
data: [DONE]

Best Practices

Optimize Token Usage

Set max_tokens to limit response length when you only need short answers
Use system prompts efficiently—keep them concise

Manage Conversation History

Only include previous messages when context is needed
For long conversations (10+ messages), summarize history and start fresh

Choose the Right Model

Use Case	Recommended Model
Simple tasks	`openai/gpt-oss-20b`
General purpose	`openai/gpt-oss-120b`
Complex reasoning	`google/gemini-2.5-pro`
Cost-sensitive	`google/gemini-2.5-flash-lite`

Pricing

Credits are charged per message in your conversation array.

Model	Credits/Message
GPT OSS 20B	0.1
GPT OSS 120B	0.25
Gemini 2.5 Flash Lite	0.15
Gemini 2.5 Flash	1
Gemini 2.5 Pro	3

See Models for full pricing.

Chat API

On this page