Guides, model notes and product updates

We pulled 30 days of TokenLab production traffic on GPT Image 2. About 4.3% of tasks came back as moderation_blocked 400s, reference images doubled the block rate, and not one retry ever recovered. Here is the pattern data and the prompt rewrites that fix it.

A practical Nano Banana API guide for TokenLab covering model IDs with per-image prices, text-to-image and reference-image requests, async polling, errors, and billing.

A runnable FastAPI chatbot on one TokenLab API key, with SSE streaming, server-side memory, a model allowlist, error handling, dated per-1M-token prices and a smoke test.

A developer-focused guide to choosing the best AI video models API by workflow, async job handling, output format, and pricing.

Migrating from OpenAI to TokenLab starts with changing base_url and api_key, then checking model IDs, streaming, tool calls, error shapes, timeouts and billing against dated documentation.

Hitting a 404 because a model string moved is a bad way to start an agent loop. Here is how to pin `gemini-3.5-flash`, read Google Cloud pricing, and build a loop that survives deprecations.