claude-sonnet-4-6
claude-sonnet-4-6
Our smartest model. Best for complex agents, coding, and most advanced tasks
Price
| Input | $2.85per million tokens$3per million tokens |
| Cached writes(5m) | $3.5625per million tokens$3.75per million tokens |
| Cached writes(1h) | $5.7per million tokens$6per million tokens |
| Cached reads | $0.285per million tokens$0.3per million tokens |
| Output | $14.25per million tokens$15per million tokens |
Tiered billing
| Input length per request | Input | Cached writes(5m) | Cached writes(1h) | Cached reads | Output price |
|---|---|---|---|---|---|
| 0 < tokens <= 200K | $3 | $3.75 | $6 | $0.3 | $15 |
| 200K < tokens <= 1M | $3 | $3.75 | $6 | $0.3 | $15 |
Use the following code example to integrate our API:
1from openai import OpenAI
2
3client = OpenAI(
4 api_key="<Your API Key>",
5 base_url="https://api.highwayapi.ai/openai"
6)
7
8response = client.chat.completions.create(
9 model="claude-sonnet-4-6",
10 messages=[
11 {"role": "system", "content": "You are a helpful assistant."},
12 {"role": "user", "content": "Hello, how are you?"}
13 ],
14 max_tokens=128000,
15 temperature=0.7
16)
17
18print(response.choices[0].message.content)Information
Provider
Quantization
-
Supported Features
Context Length
1M
Maximum Output
128K
Function Calling
Supported
Structured Outputs
Supported
Reasoning
Supported
serverless
Supported
Input Capabilities
text, image
Output Capabilities
text