<!-- Lazu · Claude Sonnet 5.5 on Lazu: native API and cache costs · https://lazu.ai/blog/claude-sonnet-5-5-lazu-api -->

# Claude Sonnet 5.5 on Lazu: native API and cache costs

2026-10-10 · Lazu team

Claude Sonnet 5.5 is available through Lazu’s native Anthropic Messages API. Keep the message structure, point the client at Lazu and use `claude-sonnet-5-5`. Stable-lane input and output cost $2 and $10 per million tokens.

## Start with a task you can verify

Migrate one existing development task with its original acceptance criteria. Check that any tool loop finishes correctly, then compare the cost of the whole task. Cache savings should include the first write as well as later reads.

## Pricing and boundaries

This is a snapshot of Lazu’s stable-lane base rates on October 10, 2026, before any account-specific discount. Consult the catalog for subsequent changes.

| Dimension | USD / million tokens |
| --- | --- |
| Input | $2 |
| Output | $10 |
| Cache read | $0.2 |
| Cache write, 5 minutes | $2.5 |
| Cache write, 1 hour | $4 |

As of October 10, 2026, Lazu’s stable cache-read price is $0.20 per million tokens; Anthropic’s current direct price is $0.10. Budget using Lazu’s live catalog. Discount-lane pricing and availability are separate from the stable lane.

The model card below reads the live catalog:

Model: `claude-sonnet-5-5` — Stable $2.00 / $10.00 · Discount $0.86 / $4.30 — https://lazu.ai/models/anthropic/claude-sonnet-5-5

## A minimal request

Create a key with a model restriction and spending cap, then set `LAZU_API_KEY` in your local environment. Keep the key out of source code. Query `/api/models/catalog` with that key to check permissions and supported endpoints before integration.

```bash
curl --fail-with-body https://api.lazu.ai/v1/messages \
  -H "Authorization: Bearer $LAZU_API_KEY" \
  -H "Content-Type: application/json" \
  -H "anthropic-version: 2023-06-01" \
  -d '{"model":"claude-sonnet-5-5","max_tokens":64,"messages":[{"role":"user","content":"Reply with only OK."}]}'
```

## Verify the result before increasing traffic

On October 10, 2026, a restricted key completed this short-text request through the public API with HTTP 200 and a valid response. This verifies one basic request path, not sustained concurrency, long-context behavior or task quality.

Save `X-Lazu-Request-Id` from the response headers. Inspect the input, output, cache usage and charge in Usage & Logs, or query `GET /api/usage/requests/{request_id}` with the same key. Distinguish quota and budget errors from upstream rate limits; retry only when appropriate and with a limit.

See the [Lazu catalog](https://lazu.ai/models), [pricing and lanes](https://lazu.ai/docs/models/pricing), and [model reference](https://platform.claude.com/docs/en/about-claude/pricing).

