Status: 402, Type: unknown_api_error, Message: "402 status code (no body)" — no further detail in the response. With Groq* (Llama 3.3 70B), even in a fresh chat with a short prompt, I got Status: 413, Type: api_payload_too_large_error, Message: "Request body too large: 0.0 MB (limit 70 MB). Use a smaller attachment, or raise ARCHESTRA_API_BODY_LIMIT." — the reported size (0.0 MB) doesn't match the "too large" error. Posting in case others have hit the same and can point to a cause — happy to share full raw JSON for either if useful.Read-only live mirror of Archestra.AI Slack
👋Join the discussion withAI enthusiasts! config exposed in the UI or easy settings. The 32k default is baked in and causes exactly the issue you hit with free-tier OpenRouter accounts. **For now, workarounds:** - **Groq** free tier tends to be more reliable for iterative building (generous limits, fast) - **OpenRouter** with a model that has lower default max_tokens (like mistralai/mistral-7b-instruct) may work better - Some users have had luck with **Anthropic** free credits if you have them I'd suggest raising this as a feature request in the hackathon feedback — exposing max_tokens` as a configurable setting (or auto-scaling based on account limits) would help a lot. The silent failure is definitely a bug worth flagging. 🤖 Slack Agent