Skip to main content

Available Models

Claude Opus & Sonnet via a single universal API — Anthropic and OpenAI formats both supported. Use "model": "smart" for automatic selection, or choose a specific model for full control.

Quick Start

Send a request with any model:

curl https://api.drawbridge-tech.com/v1/chat/completions \
  -H "Authorization: Bearer your-api-key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "smart",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

List Models via API

Query available models programmatically:

curl https://api.drawbridge-tech.com/v1/models \
  -H "Authorization: Bearer your-api-key"

# Response:
{
  "object": "list",
  "data": [
    {"id": "smart", "type": "model", "display_name": "smart"},
    {"id": "claude-opus-4-8", "type": "model", "display_name": "claude-opus-4-8"},
    {"id": "claude-sonnet-4-6", "type": "model", "display_name": "claude-sonnet-4-6"}
  ]
}

This returns the real-time list of all models currently available. Use it to populate model selectors in your application.

All Models

Model IDContextList (in / out per 1M)Your rate (0.75×)
smart

Automatic model selection. Drawbridge picks the best model for each request.

1,000,000—Rate of selected model
claude-opus-4-8

Most capable model. 1M context with extended reasoning for complex work.

1,000,000$5.00 / $25.00$3.75 / $18.75
claude-opus-4-7

Opus, prior point release. 1M context with extended reasoning.

1,000,000$5.00 / $25.00$3.75 / $18.75
claude-opus-4-6

Production-grade Opus with 1M context and high-effort reasoning.

1,000,000$5.00 / $25.00$3.75 / $18.75
claude-sonnet-5

Newest Sonnet with 1M context. Latest-generation quality at Sonnet speed and cost.

1,000,000$3.00 / $15.00$2.25 / $11.25
claude-sonnet-4-6

Sonnet with 1M context. Best balance of speed, quality, and cost.

1,000,000$3.00 / $15.00$2.25 / $11.25
claude-sonnet-4-5

Previous-generation Sonnet. Fast and capable, 200K context.

200,000$3.00 / $15.00$2.25 / $11.25

Prices per 1M tokens — list rate struck through, then the flat 0.75× rate you pay (25% off), native tool-use included. See the pricing page for details.

Usage Guide

Which model should I use?

  • smart — Best default. Let Drawbridge pick the optimal model for each task.
  • claude-opus-4-8 — Maximum quality. Complex reasoning, research, architecture design.
  • claude-sonnet-4-6 — Best value. Fast, capable, 1M context. Ideal for most coding tasks.

Streaming

All models support streaming via SSE. Set "stream": true in your request.

SDK Compatibility

Works with the Anthropic or OpenAI SDK. Just set the base URL. The Anthropic SDK targets /v1/messages, which returns native tool-use — included on your key:

from anthropic import Anthropic

# The Anthropic Messages API returns native tool-use — included on your key.
client = Anthropic(
    base_url="https://api.drawbridge-tech.com",
    api_key="your-api-key",
)

message = client.messages.create(
    model="smart",
    max_tokens=1024,
    messages=[{"role": "user", "content": "Hello!"}],
)
print(message.content[0].text)
API Reference →