Mistral opens a Responses API in public preview, using the OpenAI Responses format for agent builders
Mistral's documentation describes a Responses API in public preview that lets developers build with Mistral models using the OpenAI Responses format. The API is stateless, so applications keep and resend conversation history with each request. Supported features in the preview include text and image input, file input, structured output, streaming, client-executed function calling, reasoning effort controls, and input token counting. The page provides Python, TypeScript, and cURL examples.
Open original source docs.mistral.ai⚑ Date unverified · why this is flagged
The primary page's publication date has not been verified. The displayed time may come from discovery rather than the page itself.
The signal remains in the tracker so you can inspect its original source and discovery trail. This flag lowers its source evidence score; it does not judge whether the claim is true.
One primary source; other links are context, not independent corroboration.
- Primary sourceX discovery · source check open
- Discovery linkX
- Linked in sourcecontact Mistral support
Grok Bot submitted this discovery. The primary page's publication date has not been verified. The displayed time may come from discovery rather than the page itself. The original source and submitted evidence remain inspectable; no editor has verified the claim.
Open full article view →- Linked article+30
- Fetched source page+30
- No editor link review+0
- Original non-discussion link+5
- Date unverified-8
This measures the stored source trail and editorial steps. It does not certify accuracy, peer review, or independent corroboration. Popularity adds no points.
View full scoring →Read the scoring rubric →What the source says
Mistral's documentation describes a Responses API in public preview that lets developers build with Mistral models using the OpenAI Responses format. The API is stateless, so applications keep and resend conversation history with each request. Supported features in the preview include text and image input, file input, structured output, streaming, client-executed function calling, reasoning effort controls, and input token counting. The page provides Python, TypeScript, and cURL examples.
A READER'S EVIDENCE CHECKHow to read this signalSix questions about claims, sources, risks, and open checks
This is a signal-level guide until claim-level evidence is available. “Not recorded” means the evidence has not been assessed here; it does not mean a result is false. How we check AI news →
- 01Who is making each claim?
The claimant and whether each claim was measured or asserted are not recorded in this public brief.
- 02What was actually tested?
Not recorded per claim. Check the source for sample size, tasks, model and benchmark versions, and reproducibility.
- 03Where are the sources?
Original link: docs.mistral.ai. Brief basis: fetched source page. Primary page date and quote locations are not established in this panel.
- 04What could mislead?
The primary page's publication date has not been verified. The displayed time may come from discovery rather than the page itself.
- 05What is at risk if wrong?
Not assessed per claim. Consider safety, privacy, cost, and adoption decisions before relying on the result.
- 06What would change the view?
No claim-specific check is recorded. An inspectable primary method or independent replication could change the assessment.
Key findings from the stored brief
- The Responses API is stateless; the application must store conversation history and resend it in input each request.
- Preview supports text, image URLs/base64, file inputs, JSON mode and JSON Schema, and streaming Responses events.
- Client-executed function calling, including namespaces, is supported, along with reasoning.effort depending on the model.
- Input token counting is available via POST /v1/responses/input_tokens.
Source claims not independently checked; the API is in public preview and the page notes issues should go to Mistral support.
This is a source-based abstract, not independent validation of the source's claims.
Evidence & sources
These links show where the signal came from and what the source page linked to. A linked page is context, not independent corroboration.
Grok Bot submitted this discovery. The primary page's publication date has not been verified. The displayed time may come from discovery rather than the page itself. The original source and submitted evidence remain inspectable; no editor has verified the claim.
These are Grok Bot discovery notes. AINewsIQ prepared a brief from available source material. The bot's rationale, linked posts, authors, and stances have not been independently verified.
Mistral launched a stateless /v1/responses endpoint in public preview that follows the OpenAI Responses format, returning answers, reasoning and tool calls as separate output items. Preview supports text, image and file input, JSON Schema output, streaming and client-executed functions; apps must resend conversation history each turn.
Source claims not independently checked; the API is in public preview and the page notes issues should go to Mistral support.
Engagement counts, when shown, are observed snapshots. They do not establish accuracy or corroboration.
- x post ↗ · 373 likes, 39 reposts, 76 replies, 35 quotes · observed 10/28/2026, 4:03:14 PM
Timeline & updates
- Signal dated by source or discovery feed
This timestamp places the signal in the radar. It may be the discovery post date rather than the primary page's first publication date.
- Shared brief stored
AINewsIQ prepared one abstract from fetched source page.
A publication revision history is not stored for this signal. New engagement snapshots do not mean the source itself changed.
Why this may matter
Compatibility with the OpenAI Responses format may let developers port existing integrations to Mistral models with fewer code changes, which is relevant to agent builders evaluating providers.
Limits and open questions
Source claims not independently checked; the API is in public preview and the page notes issues should go to Mistral support.
Organization-specific financial, security, and operational effects require the organization's own context and review.
Discussion
Comments are reviewed before publication. Discuss the evidence, not the person.
No published comments yet.
Reader discussion opens with accounts. You can read the original source and published comments now.