# Claude Opus 4.8 Think API Pricing

As of October 10, 2026, Claude Opus 4.8 Think costs $5.00 per 1M input tokens and $25.00 per 1M output tokens on AIHubMix, with cache reads at $0.50 and cache writes at $6.25 per 1M tokens. It has a 1,000,000-token context window and returns up to 128,000 tokens per response.

- Page: https://models.litellm.ai/models/claude-opus-4-8-think
- Lab: Anthropic
- LiteLLM model name: `aihubmix/claude-opus-4-8-think`
- Context window: 1,000,000 tokens
- Max output: 128,000 tokens
- Added to LiteLLM: September 16, 2026
- Prices updated: October 10, 2026

## Pricing by provider

Token prices in USD per 1M tokens.

| Provider | Model name | Input | Output | Cache read | Per image | Per second | Context |
|---|---|---|---|---|---|---|---|
| AIHubMix | `aihubmix/claude-opus-4-8-think` | $5.00 | $25.00 | $0.50 | – | – | 1M |

## Cost examples

1,000 requests with 2,000 input and 500 output tokens each:

- AIHubMix: $22.50

100 long-document requests with 100,000 input and 2,000 output tokens each:

- AIHubMix: $55.00

## Features

Supported: Function calling, Structured output, Image input, Reasoning, Prompt caching.

## Use it with LiteLLM

```python
from litellm import completion

response = completion(
    model="aihubmix/claude-opus-4-8-think",
    messages=[{"role": "user", "content": "Hello!"}],
)
```

## FAQ

### How much does Claude Opus 4.8 Think cost?

Claude Opus 4.8 Think costs $5.00 per 1M input tokens and $25.00 per 1M output tokens on AIHubMix, with cache reads at $0.50 and cache writes at $6.25 per 1M tokens.

### What is the context window of Claude Opus 4.8 Think?

Claude Opus 4.8 Think has a 1,000,000-token context window and returns up to 128,000 tokens per response.

### Which providers offer Claude Opus 4.8 Think?

Claude Opus 4.8 Think is available from AIHubMix through LiteLLM, using the model name aihubmix/claude-opus-4-8-think.

### How do I call Claude Opus 4.8 Think with an OpenAI-compatible API?

Use the LiteLLM Python SDK with model="aihubmix/claude-opus-4-8-think", or add the model to the LiteLLM proxy's config.yaml and send requests to /v1/chat/completions from any OpenAI client. LiteLLM tracks the cost of every request at the prices on this page.

### What features does Claude Opus 4.8 Think support?

Claude Opus 4.8 Think supports function calling, structured output, image input, reasoning and prompt caching.

### When did LiteLLM add Claude Opus 4.8 Think?

Claude Opus 4.8 Think was added to LiteLLM's model price file on September 16, 2026.

Source: LiteLLM model price file, https://github.com/BerriAI/litellm/blob/main/model_prices_and_context_window.json