Changelog

A dated log of every change to the Modellane API and its models, so you can see what changed and when.

Every change to the API and the model lineup, grouped by date, newest first.

Every change to the API and the model lineup, newest first. Larger releases also have a post in News.

2026-10-03#

API#

  • Launched the Chat Completions endpoint, POST /v1/chat/completions, in the OpenAI format, with streaming, tool calls, JSON output and image input on models that support them.
  • Launched GET /v1/models to list the models a key can call, and GET /v1/balance to read the balance behind a key.
  • Usage reporting with cached prompt tokens and reasoning tokens in every response; the usage chunk is available on streams with stream_options.include_usage.
  • Per-project limits on concurrent requests and requests per minute, with Retry-After on HTTP 429. See Rate limits.
  • Added the OpenAI Responses API, POST /v1/responses, stateless, with function and custom tools, streaming events and reasoning summaries. See Responses.
  • Added the Anthropic Messages API, POST /v1/messages, and POST /v1/messages/count_tokens, on the base URL https://usemodellane.com, with x-api-key or bearer authentication and Anthropic error types. See Messages.
  • New error code unsupported_parameter for Responses fields that need stored state, such as previous_response_id.

Docs#

Models#