Mistral AI API vs Beam 1.0

Mistral AI API

Public OpenAPI document at docs.mistral.ai/openapi.yaml and an llms.txt with Markdown twins. Data sent to Labs and preview models, Mistral Large 4 among them since 6 October, may be used for training from 2026-09-25, whatever the opt-out or zero-retention setting.

Beam 1.0

The Reflection API is OpenAI-compatible, with an OpenAPI document, strict structured outputs and tool calls, and error codes that say when to retry, and the weights are Apache-2.0. It is a free public beta with unpublished daily limits and no per-token price, reasoning can't be turned off, and three API incidents were posted between 14 and 16 October 2026.

Mistral AI API

1. Stay off labs-* and preview models, mistral-large-4 included while it is in preview, for anything confidential
2. Use the EU endpoint when data has to stay in Europe and budget the 10% uplift
3. Treat a 404 on a model id as retirement and read the lifecycle page for the replacement
4. Move zai-glm-5-2 calls to zai-glm-5-3 before 31 October 2026. The price is the same
5. Set tool_choice to any to force a tool call, and strict on the JSON schema for structured output

Beam 1.0

1. Send reasoning_effort low or medium for short tasks. The default is max, and none or minimal return 400 unsupported_value
2. Return every assistant message with its reasoning_content unchanged. If a turn comes back without it, start a new conversation, since later requests fail with missing_required_parameter
3. Don't rely on stop or seed. Both are accepted and ignored, so truncate output in your own code
4. Honour x-should-retry: false on a 429. It means a daily limit is spent and Retry-After counts to 00:00 UTC
5. Set max_completion_tokens yourself on long prompts. The default budget isn't reduced to fit the prompt and includes reasoning tokens