> ## Documentation Index
> Fetch the complete documentation index at: https://docs.venice.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Claude Opus 4.8 API

> Claude Opus 4.8 API on Venice: 1M context, $5.00 input and $25.00 output per 1M tokens. Anonymized access without your identity.

> [accordion] Plain-text specification
>
> ## Claude Opus 4.8 API
>
> Claude Opus 4.8 is a large language model by Anthropic, available on the Venice API as `claude-opus-4-8`. Requests are anonymized, so the provider never sees your identity.
>
> Claude Opus 4.8 is the successor to Opus 4.7 in Anthropic's Opus family. It supports long-horizon agentic work, complex multi-step coding, and memory-driven tasks where coherence over extended sessions matters. It features a 1M token context window, 128K max output tokens, adaptive thinking, and strong multimodal capabilities.
>
> ### Claude Opus 4.8 API pricing
>
> | Model ID | Variant | Privacy | Price |
> | - | - | - | - |
> | `claude-opus-4-8` | Standard | Anonymized | $5.00 / $25.00 per 1M |
> | `claude-opus-4-8-fast` | Fast | Anonymized | $10.00 / $50.00 per 1M |
>
> ### Claude Opus 4.8 specifications
>
> | Spec | Value |
> | - | - |
> | Provider | Anthropic |
> | Released | May 28, 2026 |
> | Privacy | Anonymized |
> | Status | Standard: Stable; Fast: Deprecated, retiring Nov 13, 2026 |
> | Context window | 1M tokens |
> | Max output | 128K tokens |
> | Reasoning effort | low, medium, high, xhigh, max |
>
> ### How to use the Claude Opus 4.8 API
>
> Send requests to `POST https://api.venice.ai/api/v1/chat/completions` with `"model": "claude-opus-4-8"` and your API key.
>
> ```bash theme={"system"}
> curl https://api.venice.ai/api/v1/chat/completions \
>   -H "Authorization: Bearer $VENICE_API_KEY" \
>   -H "Content-Type: application/json" \
>   -d '{
>     "model": "claude-opus-4-8",
>     "messages": [{ "role": "user", "content": "Explain TEE attestation in two sentences." }],
>     "reasoning_effort": "medium"
>   }'
> ```
>
> ### Related models
>
> * [Claude Opus 5.5 API](https://docs.venice.ai/models/claude-opus-5-5.md): $4.00 / $20.00 per 1M
> * [Claude Opus 5 API](https://docs.venice.ai/models/claude-opus-5.md): $5.00 / $25.00 per 1M
> * [Claude Opus 4.7 API](https://docs.venice.ai/models/claude-opus-4-7.md): $5.00 / $25.00 per 1M
> * [Claude Opus 4.6 API](https://docs.venice.ai/models/claude-opus-4-6.md): $5.00 / $25.00 per 1M
> * [Claude Opus 4.5 API](https://docs.venice.ai/models/claude-opus-4-5.md): $5.00 / $25.00 per 1M
> * [GPT-5.5 API](https://docs.venice.ai/models/gpt-5-5.md): $5.00 / $30.00 per 1M
> * [Muse Wonder API](https://docs.venice.ai/models/muse-wonder.md): $5.00 / $25.00 per 1M
> * [Kimi K3.1 Pro Highspeed API](https://docs.venice.ai/models/kimi-k3-1-pro-highspeed.md): $5.00 / $25.00 per 1M
> * [GPT-5.6 Sol API](https://docs.venice.ai/models/gpt-5-6-sol.md): $4.00 / $20.00 per 1M


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.