# claude-opus-4-6 — API, Pricing & Context Window | Vivgrid

> Source: https://vivgrid.com/docs/models/claude-opus-4-6

claude-opus-4-6 on Vivgrid: Anthropic's high-end Opus coding model with a 1M-token context window, Messages API, and geo-distributed acceleration.

`claude-opus-4-6` is a high-end Anthropic Opus model built for demanding coding and reasoning tasks. With a **1M-token context window** and the **Messages API**, it excels at understanding large codebases and producing careful, well-structured edits.

Vivgrid accelerates `claude-opus-4-6` across **AMER and EMEA**, so agent workloads get consistent, low-latency performance through one API key and billing surface.

## Specifications

| Field | Value |
| --- | --- |
| Provider | Anthropic |
| Model ID | `claude-opus-4-6` |
| Best for | Coding |
| Available on | Vibe coding |
| Context window | 1,000,000 tokens |
| Max output | 128,000 tokens |
| Modalities | Text, Image |
| Tool / function calling | Yes |
| Knowledge cutoff | 2025-03 |
| Acceleration | Geo-distributed — AMER, EMEA |

## Pricing

Pricing in USD per 1M tokens.

| Input | Cached input | Output |
| --- | --- | --- |
| $5.00 | $1.00 | $25.00 |

### What one request costs

The rates above applied to a 20K-token prompt with a 2K-token reply — a typical single agent turn, small enough that every request is billed at the base rate.

| Request | Cost |
| --- | --- |
| Cold prompt, nothing cached | $0.1500 |
| Warm prompt, 90% of the input served from cache | $0.0780 |


## API surfaces

The Vivgrid Console catalogs `claude-opus-4-6` on one surface, all behind the same API key. The endpoint shown is the one the Console previews for that surface.

| Surface | Primary endpoint | Use it for |
| --- | --- | --- |
| Vibe coding | `/messages` | Coding CLIs and IDE agents that drive the model themselves — point the tool at Vivgrid and keep your own loop. |

## Quick start

Get an API key from the Vivgrid Console (https://console.vivgrid.com), then call `claude-opus-4-6` directly.

```bash
curl https://api.vivgrid.com/v1/messages \
  -H "Authorization: Bearer $VIVGRID_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "claude-opus-4-6",
    "max_tokens": 1024,
    "messages": [
      { "role": "user", "content": "Say hello in English, Chinese and Spanish." }
    ],
    "stream": true
  }'
```


## Ideal use cases

- Agentic coding and whole-repository refactors
- Careful reasoning over long documents and specs
- Tool-calling agents needing dependable structured output
- Workloads that value Claude's writing and analysis quality

## Related models

- [gpt-6-astra](/docs/models/gpt-6-astra) — OpenAI's frontier gpt-6 coding model
- [claude-opus-5-5](/docs/models/claude-opus-5-5) — the latest Opus release
- [claude-sonnet-4-6](/docs/models/claude-sonnet-4-6) — faster, cheaper sibling