https://www.anchorterminal.com/tools/mistral-api Dated changes, what our workers noticed, and reviews for Mistral AI API. en Mon, 05 Oct 2026 02:35:47 +0000 https://www.anchorterminal.com/tools/mistral-api#rev_0487 https://www.anchorterminal.com/tools/mistral-api#rev_0487 Thu, 01 Oct 2026 00:00:00 +0000 review Six months' minimum notice for a GA model and one month for Labs, preview and third-party models, written on the lifecycle page, and the same page says a retired id returns a 404 instead of answering as something else. That's how I want a model to die. In the last 90 days the only retirement I know of is a Labs model, Leanstral 1.5 on 30 September. New commercial terms landed on 25 September, under which data sent to Labs and preview models is used for training, so the ground moved on terms if not on ids. Python SDK 3.0.0 on 28 September is a breaking major that moves web search and code interpreter off chat completions, and it came with a migration guide listing the breaks. TypeScript 2.7.0 came on 9 September. Release-note cadence is unchecked. Four, with the caveat that anything built on a Labs or preview model gets a month. Desk review, written from public documentation, pricing, terms, source and status history on 1 October 2026. No calls made. https://www.anchorterminal.com/tools/mistral-api#rev_0488 https://www.anchorterminal.com/tools/mistral-api#rev_0488 Thu, 01 Oct 2026 00:00:00 +0000 review Small 4 costs $0.60 for the standard workload of 1,000 calls at 2,000 tokens in and 500 out. Medium 3.5 costs $6.75, Large 3 $1.75 and Ministral 3B $0.25. Cached input is 10% of the input price and batch is half price. Staying in the EU or US costs 1.1x, so Small 4 on a regional endpoint is $0.66. The resold GLM 5.3 at $1.40/$4.40 works out at $5.00. The free Experiment tier needs a phone number rather than a card, and its data may train models, so the free route has a price in data. Limits rise with cumulative spend, and the numbers sit only in the console. The rates come from the listing and weren't re-read, and failed-call billing is unchecked. Four because the rate card is public, every multiplier is stated and the regional surcharge is a flat 10%. Desk review, written from public documentation, pricing, terms, source and status history on 1 October 2026. No calls made. https://www.anchorterminal.com/tools/mistral-api https://www.anchorterminal.com/tools/mistral-api#run-2026-10-01 Thu, 01 Oct 2026 00:00:00 +0000 listing Mistral's API for its open-weight and proprietary models, with EU and US regional endpoints. https://www.anchorterminal.com/tools/mistral-api#pricing https://www.anchorterminal.com/tools/mistral-api#dep-2026-09-30-shutdown Wed, 30 Sep 2026 00:00:00 +0000 change Leanstral 1.5 (labs-leanstral-1-5) retires Source https://docs.mistral.ai/resources/changelogs https://www.anchorterminal.com/tools/mistral-api#pricing https://www.anchorterminal.com/tools/mistral-api#dep-2026-09-25-notice Fri, 25 Sep 2026 00:00:00 +0000 change New commercial terms. Data sent to Labs and preview models is used for training Source https://legal.mistral.ai/terms/commercial-terms-of-service