Seed 2.0 Pro on Lazu: pricing and the 128K threshold
Seed 2.0 Pro is available on Lazu’s stable lane under seed-2.0-pro. An existing OpenAI SDK integration can keep its Lazu key and base URL. The main budgeting detail is its context tier: a 256K catalog context window does not mean one token rate across that window.
Start with a task you can verify #
Start with your own document summaries or knowledge questions. Compare Pro and Turbo on the same inputs, checking completeness, output length and the receipt. The model name alone is not a quality evaluation.
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 | $0.5 |
| Output | $3 |
| Cache read | $0.1 |
Above 128,000 input tokens, the request uses $1 input, $6 output and $0.20 cached input per million tokens. At or below the threshold, the corresponding rates are $0.50, $3 and $0.10. A short text call is verified; image, tool and long-output workflows need their own acceptance tests.
The model card below reads the live catalog:
seed-2.0-proByteDance · Seed · 256k · Stable $0.50 / $3.00Model 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/chat/completions \
-H "Authorization: Bearer $LAZU_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"seed-2.0-pro","max_tokens":128,"messages":[{"role":"user","content":"Reply with only OK."}],"thinking":{"type":"disabled"}}'
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.