Clef on Lazu: short-text decisions and API limits

Model launch · 2026-10-10 Clef on Lazu clefStable $0.30 / $0.00 Lazu

Clef is available through Lazu’s /v1/decisions endpoint. Provide a state and typed questions to add a testable decision step to a workflow. Current Lazu pricing is $0.30 per million input tokens and zero per output token.

Start with a task you can verify #

Begin with a short description, such as an unavailable service and a request for immediate help. Define each question precisely and test several phrasings. Keep a review or fallback path when confidence is insufficient.

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 $0.3
Output $0

Lazu currently applies a 2000-byte UTF-8 guard to Clef state. This is a gateway limit, not Cloudflare’s advertised model context window. This article verifies the short-text path; consult the catalog for inline-image limits. Streaming is unsupported. Clef Flash is not included in this launch.

The model card below reads the live catalog:

clefOther · Stable $0.30 / $0.00Model page →

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.

curl --fail-with-body https://api.lazu.ai/v1/decisions \
  -H "Authorization: Bearer $LAZU_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"clef","state":{"ticket":"The service is down. Please help immediately."},"questions":{"urgent":{"type":"noul","instructions":"Does the ticket require immediate attention?"}}}'

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, pricing and lanes, and model reference.

Related
2026-10-28BAAI/bge-m3 embeddings API: 100+ languages, $0.02 per 1M 2026-10-10DeepSeek Flash on Lazu: cache and time-based pricing 2026-10-10GPT-6 Sol on Lazu: validate the stable lane first

Try it with a key

Start free