# claude-opus-4-8 — API, Pricing & Context Window 
Run Anthropic's claude-opus-4-8 on Vivgrid: the frontier Opus coding model with a 1M-token context window, the Messages API, and geo-distributed acceleration.

`claude-opus-4-8` is Anthropic's frontier Opus model and the strongest available choice for agentic coding and complex reasoning. It combines a **1M-token context window** with the latest Opus capabilities, served on the **Messages API** (`/messages`).

On Vivgrid, `claude-opus-4-8` is geo-distributed across **AMER, EMEA, and APAC**, giving Claude Code-style agents low-latency access worldwide through a single unified API key.

## Specifications

|     |     |
| --- | --- |
| **Provider** | Anthropic |
| **Model ID** | `claude-opus-4-8` |
| **Best for** | Coding |
| **Context window** | 1,000,000 tokens |
| **Max output** | 128,000 tokens |
| **Modalities** | Text, Image |
| **Tool / function calling** | Yes |
| **Knowledge cutoff** | 2026-01 |
| **Acceleration** | ⚡ Geo-Distributed — AMER, EMEA, APAC |

## Pricing

Pricing in USD per 1M tokens, matching the provider's rates.

| Input | Cached input | Output |
| --- | --- | --- |
| $5.00 | $0.50 | $25.00 |

## Quick start

Call `claude-opus-4-8` through Vivgrid's unified, OpenAI-compatible endpoint. Get an API key from the [Vivgrid Console](https://console.vivgrid.com/).

```
curl https://api.vivgrid.com/v1/messages \
  -H "Authorization: Bearer $VIVGRID_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "claude-opus-4-8",
    "max_tokens": 1024,
    "messages": [\
      { "role": "user", "content": "Say hello in English, Chinese and Spanish." }\
    ],
    "stream": true
  }'
```

## Ideal use cases

- Frontier coding agents and large-scale refactoring
- Complex, multi-step reasoning and planning
- Long-context document and codebase analysis (up to 1M tokens)
- Tool-using agents that demand high reliability

## Related models

- [claude-opus-4-7](/content/docs/models/claude-opus-4-7/index.html) — the prior Opus release
- [claude-sonnet-5](/content/docs/models/claude-sonnet-5/index.html) — faster, lower-cost Claude
- [gpt-5.5](/content/docs/models/gpt-5.5) — OpenAI's flagship coding model