# claude-sonnet-5-5 — API, Pricing & Context Window | Vivgrid

> Source: https://vivgrid.com/docs/models/claude-sonnet-5-5

Run Anthropic's claude-sonnet-5-5 on Vivgrid: the latest Sonnet model with the best balance of speed and intelligence, a 1M-token context window, 128K max output, and geo-distributed acceleration.

`claude-sonnet-5-5` is the latest model in Anthropic's Sonnet tier, offering the best combination of speed and intelligence in the Claude lineup. It keeps the **1M-token context window** and **128K-token max output** of `claude-sonnet-5` at the same per-token price, and runs with adaptive thinking on by default.

On Vivgrid, `claude-sonnet-5-5` is served through the native **Messages API** (`/messages`) with geo-distributed acceleration across **AMER, EMEA, and APAC**. It uses the same unified Vivgrid API key as the rest of the catalog, so moving an agent from `claude-sonnet-5` is a model-string change.

<ModelSpec slug="claude-sonnet-5-5" />

Prompt caching is billed at **$2.50 per 1M cache-write tokens** on the 5-minute TTL and **$4.00 per 1M** on the 1-hour TTL, with cached reads at $0.20.

## Ideal use cases

- Everyday coding agents balancing quality, speed, and cost
- High-volume tool-calling and agentic workflows
- Long-context analysis within a 1M-token budget
- Teams on `claude-sonnet-5` upgrading at the same price

## Related models

- [claude-sonnet-5](/docs/models/claude-sonnet-5) — the prior Sonnet release
- [claude-opus-5-5](/docs/models/claude-opus-5-5) — the latest frontier Opus model
- [gpt-6.1-sol](/docs/models/gpt-6.1-sol) — OpenAI's latest balanced gpt-6 model