Chat

Create chat completions using the OpenAI-compatible API format.

Endpoint

POST https://api.scalellm.dev/v1/chat/completions

Examples

Python
JavaScript
cURL

from openai import OpenAI

client = OpenAI(
    base_url="https://api.scalellm.dev/v1",
    api_key="sk_your_key"
)

response = client.chat.completions.create(
    model="claude-sonnet-4.5",
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "Hello!"}
    ],
    max_tokens=1024
)

print(response.choices[0].message.content)

import OpenAI from 'openai';

const client = new OpenAI({
  baseURL: 'https://api.scalellm.dev/v1',
  apiKey: 'sk_your_key'
});

const response = await client.chat.completions.create({
  model: 'claude-sonnet-4.5',
  messages: [
    { role: 'system', content: 'You are a helpful assistant.' },
    { role: 'user', content: 'Hello!' }
  ],
  max_tokens: 1024
});

console.log(response.choices[0].message.content);

curl https://api.scalellm.dev/v1/chat/completions \
  -H "Authorization: Bearer sk_your_key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "claude-sonnet-4.5",
    "messages": [
      {"role": "system", "content": "You are a helpful assistant."},
      {"role": "user", "content": "Hello!"}
    ],
    "max_tokens": 1024,
    "temperature": 0.7
  }'

Request Body

Parameter	Type	Required	Description
`model`	string	Yes	Model ID (e.g., `claude-sonnet-4.5`)
`messages`	array	Yes	Array of message objects
`max_tokens`	integer	No	Maximum tokens to generate
`temperature`	float	No	Randomness (0-2, default 1)
`top_p`	float	No	Nucleus sampling (0-1)
`stream`	boolean	No	Stream responses
`stop`	string/array	No	Stop sequences
`fallback_models`	array	No	Fallback model IDs

Message Object

Field	Type	Description
`role`	string	`system`, `user`, or `assistant`
`content`	string	Message content

Response

{
  "id": "chatcmpl-abc123",
  "object": "chat.completion",
  "created": 1699000000,
  "model": "claude-sonnet-4.5",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Hello! How can I help you today?"
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 20,
    "completion_tokens": 12,
    "total_tokens": 32
  }
}

Streaming

Python
JavaScript
cURL

from openai import OpenAI

client = OpenAI(
    base_url="https://api.scalellm.dev/v1",
    api_key="sk_your_key"
)

stream = client.chat.completions.create(
    model="claude-sonnet-4.5",
    messages=[{"role": "user", "content": "Hello!"}],
    stream=True
)

for chunk in stream:
    if chunk.choices[0].delta.content:
        print(chunk.choices[0].delta.content, end="")

import OpenAI from 'openai';

const client = new OpenAI({
  baseURL: 'https://api.scalellm.dev/v1',
  apiKey: 'sk_your_key'
});

const stream = await client.chat.completions.create({
  model: 'claude-sonnet-4.5',
  messages: [{ role: 'user', content: 'Hello!' }],
  stream: true
});

for await (const chunk of stream) {
  process.stdout.write(chunk.choices[0]?.delta?.content || '');
}

curl https://api.scalellm.dev/v1/chat/completions \
  -H "Authorization: Bearer sk_your_key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "claude-sonnet-4.5",
    "messages": [{"role": "user", "content": "Hello!"}],
    "stream": true
  }'

Streamed response (SSE):

data: {"id":"chatcmpl-abc","choices":[{"delta":{"content":"Hello"}}]}

data: {"id":"chatcmpl-abc","choices":[{"delta":{"content":"!"}}]}

data: [DONE]

With Fallbacks

Python
JavaScript
cURL

from openai import OpenAI

client = OpenAI(
    base_url="https://api.scalellm.dev/v1",
    api_key="sk_your_key"
)

response = client.chat.completions.create(
    model="claude-sonnet-4.5",
    messages=[{"role": "user", "content": "Hello!"}],
    extra_body={
        "fallback_models": ["gemini-3-pro-preview", "claude-haiku-4.5"]
    }
)

print(response.choices[0].message.content)

import OpenAI from 'openai';

const client = new OpenAI({
  baseURL: 'https://api.scalellm.dev/v1',
  apiKey: 'sk_your_key'
});

const response = await client.chat.completions.create({
  model: 'claude-sonnet-4.5',
  messages: [{ role: 'user', content: 'Hello!' }],
  fallback_models: ['gemini-3-pro-preview', 'claude-haiku-4.5']
});

console.log(response.choices[0].message.content);

curl https://api.scalellm.dev/v1/chat/completions \
  -H "Authorization: Bearer sk_your_key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "claude-sonnet-4.5",
    "messages": [{"role": "user", "content": "Hello!"}],
    "fallback_models": ["gemini-3-pro-preview", "claude-haiku-4.5"]
  }'

Available Models

Model	Description
`claude-opus-4.5`	Most capable, best for complex tasks
`claude-sonnet-4.5`	Balanced performance and speed
`claude-haiku-4.5`	Fastest, best for simple tasks
`gemini-3-pro-preview`	Google’s latest with 1M token context
`gemini-3-flash`	Ultra-fast and cost-effective

Headers

Header	Required	Description
`Authorization`	Yes	`Bearer sk_your_key`
`Content-Type`	Yes	`application/json`

OpenAI Compatible

Anthropic Compatible

Google Compatible

Reference

Chat

Chat

Endpoint

Examples

Request Body

Message Object

Response

Streaming

With Fallbacks

Available Models

Headers

OpenAI Compatible

Anthropic Compatible

Google Compatible

Reference

​Chat

​Endpoint

​Examples

​Request Body

​Message Object

​Response

​Streaming

​With Fallbacks

​Available Models

​Headers

Chat

Endpoint

Examples

Request Body

Message Object

Response

Streaming

With Fallbacks

Available Models

Headers