# Mistral AI (La Plateforme) — provider research for PolyLLM

Last documentation audit: 2026-09-08 Probes executed 2026-09-08 with a real key against https://api.mistral.ai/v1 (scripts in research/mistral/*.ts, raw outputs in research/mistral/out/*.json). Everything marked (probed) was observed live; everything marked (docs) comes from the pages listed at the end.

Heads-up 1: the docs site was restructured (May 2026, "Vibe/Studio/Models/Admin"). Most URLs in the brief (/getting-started/models/models_overview/ still works, but /capabilities/structured-output/*, /capabilities/document/, /deployment/laplateforme/tier/, /models/deprecation) are 404. Current paths: /studio/conversations/*, /studio-api/conversations/advanced/*, /inference/*, /models/<card>, /admin/*, /api/endpoint/*. Several FAQ answers (vision limits, structured-output model list, predicted-output caveats) are collapsed accordions that WebFetch cannot expand — marked (docs, FAQ not extractable).

Heads-up 2: Magistral no longer exists as a model. magistral-medium-latest / magistral-small-latest are plain aliases of mistral-medium-2604 (Medium 3.5) and mistral-small-2603 (Small 4), which are hybrid models: reasoning is off by default and only enabled by reasoning_effort: "high". prompt_mode: "reasoning" is dead (400 everywhere). All magistral-*-25xx dated ids return 400.

# 1. Base URL, auth, headers

# 2. SDK recommendation (TypeScript / Node)

• Official SDK: @mistralai/mistralai 2.6.4 (npm, checked 2026-09-08; v2 is ESM-only). client.chat.complete(...) / client.chat.stream(...) (async iterable of {data: chunk}), client.fim.complete, client.models.list, client.beta.conversations.*, client.ocr.process, client.files.*. Params are camelCase (maxTokens, randomSeed, reasoningEffort, promptCacheKey) and responses are camelCased too (finishReason, usage.promptTokens) except usage.prompt_tokens_details which stays snake_case (probed) — a mapping trap. Errors: SDKError with statusCode, body (401 API error occurred: Status 401. Body: {"detail":"Invalid API Key"}) (probed); retry via retryConfig: {strategy: "backoff" | "none"}.
• OpenAI SDK (openai@7.10.0) with baseURL: "https://api.mistral.ai/v1" works for non-streaming, streaming (incl. the array-typed delta.content thinking chunks, which the OpenAI types do not model — cast to any), and errors map to AuthenticationError 401 (probed). It is not documented as an official compatibility mode on docs.mistral.ai (the migration guide says "switch the client"); third-party guides call it wire-compatible. Constraints: Mistral rejects unknown fields with 422 (seed, max_completion_tokens, developer role, any extra key) — see §9 — so the adapter must translate rather than pass OpenAI bodies through.
• Recommendation for PolyLLM: keep the current fetch-based SSE client (or OpenAI SDK) — the wire format is OpenAI-shaped and the deltas below are simple; use random_seed, max_tokens, system role only. If you want typed responses for thinking chunks and the Conversations API, the official SDK is the only typed option. Vercel @ai-sdk/mistral exists (not evaluated).

# 3. Endpoints

# 4. Chat Completions request/response (probed shapes)

Request fields (API ref + probes): model, messages (roles system, user, assistant, tool — developer → 422 union_tag_invalid), temperature 0–1.5, top_p 0–1, max_tokens (any int accepted; docs: "prompt + max_tokens cannot exceed context"; 10 M and 200 k > context were accepted and simply ignored (probed)), n (works on all but Large 3; "input tokens billed once"), stop (string or array, excluded from the output text (probed)), random_seed, frequency_penalty / presence_penalty [-2, 2], stream, stream_options (accepted, redundant — usage is always in the last chunk), safe_prompt, parallel_tool_calls, tools, tool_choice (auto | none | any | required | {type:"function",function:{name}} — all four string values + object probed OK), response_format (text | json_object | json_schema), reasoning_effort (enum none | minimal | low | medium | high | xhigh | max, model-gated §8), prompt_mode ("reasoning" — dead, 400 on every model), prompt_cache_key, prediction {type:"content", content}, service_tier (auto | standard_only), guardrails, metadata, assistant prefix: true (forces the reply to start with that text — probed: "Sure thing: **OK**! 😊").

Strict validation: any unknown top-level key → 422 {"object":"error","message":{"detail":[{"type":"extra_forbidden","loc":["body","foo_bar"],"msg":"Extra inputs are not permitted"}]},"type":"invalid_request_error"} (probed). So seed, max_completion_tokens, top_k(→400 top_k sampling is not enabled for this model), logprobs (→400 Logprobs are not enabled for this model) must never be sent.

Non-streaming response (probed):

{ "id": "c2a8…", "object": "chat.completion", "created": 1788849048, "model": "mistral-large-latest",
  "choices": [{ "index": 0, "finish_reason": "stop",
     "message": { "role": "assistant", "tool_calls": null, "content": "2 + 2 equals 4." } }],
  "usage": { "prompt_tokens": 16, "completion_tokens": 9, "total_tokens": 25,
             "prompt_tokens_details": { "cached_tokens": 0 }, "service_tier": "standard" } }

• message.tool_calls is always present (null when none). message.content is a string normally and an array of chunks when reasoning is on (§8). Small 4 / Medium 3.5 sometimes return both content text and tool_calls in one message ("I'll get the current weather for Paris for you." + call) (probed).
• finish_reason: stop, length (probed with max_tokens: 5, and when truncated inside thinking), tool_calls. No content_filter observed.
• usage: no separate reasoning-token field — thinking tokens are inside completion_tokens. service_tier echoed (standard); GLM omits it. Docs mention prompt_audio_seconds for Voxtral.
• Hidden system prompt: Small 4 / Medium 3.5 add ~12 prompt tokens (Say OK. = 6 tokens on Large/Ministral/Codestral/GLM, 18 on Small/Medium). With safe_prompt: true Small's count dropped to 6 (the injected safety prompt is not counted and seems to replace the hidden one) (probed).
• model in the response echoes the alias you sent (mistral-large-latest), except retired slugs which echo the redirect target (§15).

# 5. Streaming protocol (probed)

SSE, Content-Type: text/event-stream; charset=utf-8, no event: field on chat completions, data: {json} lines, terminated by data: [DONE]. Every data chunk after the first carries a random-length "p": "abcdefghijklmnopq…" padding field (ignore it).

data: {"id":"…","object":"chat.completion.chunk","created":…,"model":"mistral-medium-latest","choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null}]}
data: {…,"choices":[{"index":0,"delta":{"content":"Bon"},"finish_reason":null}],"p":"abcdefghijklmnopqrstu"}
data: {…,"choices":[{"index":0,"delta":{"content":"jour !"},"finish_reason":"stop"}],"usage":{"prompt_tokens":25,"completion_tokens":4,"total_tokens":29,"prompt_tokens_details":{"cached_tokens":0},"service_tier":"standard"},"p":"abc"}
data: [DONE]

• Delta keys: role, content, tool_calls. Usage arrives in the same chunk as finish_reason (no extra choices: [] chunk, stream_options.include_usage not needed). The last content delta can be non-empty in that chunk.
• Reasoning stream (Medium 3.5 / Small 4 / GLM with reasoning_effort ≥ high): delta.content changes type during the stream — sequence observed "string" (role chunk, "") → [{type:"thinking", thinking:[{type:"text", text:"Let"}]}] × N → transition chunk [{type:"thinking", thinking:[{type:"text",text:"."}], closed:true}, {type:"text", text:"No."}] → "string" deltas for the rest of the answer → final chunk with finish_reason + usage. When the answer is cut during thinking, the closing chunk has only the closed:true thinking part and finish_reason: "length" (probed). Adapter: treat each thinking[].text as a thinking delta, {type:"text"} parts and plain strings as text deltas.
• Tool calls: for Mistral models the whole call arrives in one chunk with complete arguments (§6). GLM 5.2 streams arguments across several chunks and adds delta.index and logprobs: null — use standard OpenAI accumulation by tool_calls[].index to cover both.
• Conversations API streams do use event: names (§11). Docs: streaming connections time out after 10 min of inactivity.

# 6. Tool / function calling (probed on 7 models + GLM)

• OpenAI nested format {type:"function", function:{name, description, parameters}}; max 128 tools per request (docs, known limitations); parallel_tool_calls default true; tool_choice auto | none | any | required | {type:"function",function:{name}}.
• Streamed shape (Mistral models): single delta {"tool_calls":[{"id":"m82GbeK4G","type":"function","function":{"name":"get_weather","arguments":"{\"city\": \"Montreal\"}"},"index":0}]} then finish_reason: "tool_calls" + usage. Ids are 9 alphanumeric chars (m82GbeK4G, DxeWRMxcs…). GLM ids: chatcmpl-tool-ba59f9d9d6ffc20b, arguments chunked.
• Round trip: {role:"assistant", content:"", tool_calls:[…]} then {role:"tool", tool_call_id, name, content} → 200 on all models. A long OpenAI-style id (call_abc123def456ghi789) in the replayed history was accepted (200) — the historical 9-char constraint is no longer enforced on input (probed), but keep ids verbatim anyway.
• No strict flag on tools (docs). Citations from tool results: model can emit {type:"reference", reference_ids:[…]} content chunks when the tool result is a reference dictionary (docs, chat completions).

# 7. Structured output (probed on 7 models + GLM)

• response_format: {type:"json_schema", json_schema:{name, schema, strict:true, description?}} → valid JSON matching the schema on all models incl. Codestral, Ministral 8B, GLM. minimum/maximum keywords accepted (200). Output is the JSON string in content (pretty-printed by some models — parse, don't display raw).
• {type:"json_object"} works even without "JSON" in the prompt (probed on Small 4), though docs insist you must instruct the model to output JSON.
• No documented list of unsupported schema keywords (docs, FAQ not extractable); SDK helper client.chat.parse() (Python) / Zod helpers in TS docs not surfaced. Docs: "Custom structured outputs are more reliable and are recommended".

# 8. Reasoning controls (probed matrix)

Non-stream reasoning message (probed):

"content": [
  {"type":"thinking","thinking":[{"type":"text","text":"Let me think about this. A prime number is …"}],"closed":true},
  {"type":"text","text":"No, 221 is not a prime number (13 × 17)."}
]

• No thinking budget, no summary control, no encrypted reasoning. Reasoning tokens are billed as output and counted in completion_tokens (Medium 3.5 spent 345 tokens on "is 221 prime"; max_tokens caps thinking + answer together → set a generous cap or you get finish_reason: "length" with only a thinking chunk).
• Multi-turn: docs say to replay the full assistant message including the thinking chunk; replaying it verbatim worked (probed). Replaying an assistant message whose content is an empty string → 400 code 3240 Assistant message must have either content or tool_calls, but not none. (happens if you strip thinking from a truncated answer). Safe rule: replay the whole content array as received; when the model returned tool_calls with content: "" that is fine.
• prompt_mode: "reasoning" (old Magistral switch) → 400 Reasoning prompt mode is not enabled for this model on every model — drop it.

# 9. Sampling & other parameters — support matrix (probed, chat completions)

Adapter rules: clamp temperature to [0, 1.5]; map seed → random_seed; map maxTokens → max_tokens (never max_completion_tokens); map developer → system; never send top_k, logprobs, stream_options(harmless but useless), prompt_mode; send reasoning_effort only when model.capabilities.reasoning and only high/none for Mistral hybrids (all values for GLM); send n > 1 never to Large 3.

# 10. Modalities, context, output limits

• Input: text everywhere; images on Large 3, Medium 3.5, Small 4, Ministral 3/8/14B (and Leanstral per listing) — capabilities.vision in /models is authoritative (probed 4/4 vision models OK, Codestral & GLM → 400 code 3051 Image input is not enabled for this model). Audio input only on voxtral-small-* (input_audio part, docs). Output: text only (image generation exists only as a Conversations-API tool, $100 / 1k images).
• Image format: {type:"image_url", image_url:"<https url or data:image/png;base64,…>"} — string form (docs) and OpenAI object form {url, detail} both accepted (probed). Accepted formats (from the error text): JPEG, PNG, WEBP, GIF, MPO, HEIF, AVIF, BMP, TIFF; invalid data → 400 code 3310 invalid_request_file. No minimum size (2×2 PNG accepted). Token cost: 32×32 ≈ 15 tokens, 512×512 ≈ 390 tokens on Small 4 (≈ 28×28 px per token); billed at the text input price (no separate image price). Limits (docs, known-limitations page): 20 MB per image, resolution > 10 000×10 000 rejected (older FAQ: 8 images / request, 10 MB) — FAQ answers not extractable, treat 8 images as the safe cap.
• Documents: {type:"document_url", document_url:"https://…pdf" | "data:application/pdf;base64,…", document_name?} → server-side OCR then QnA; probed OK on Small 4, Ministral 8B and Codestral; usage shows only ~50 prompt tokens for a 1-page PDF (OCR cost is not in usage — pricing of Document QnA unclear, docs say OCR $4/1k pages). {type:"file", file_id} also valid (bogus id → 400 3310 File … could not be found or may have expired). Limits (docs, FAQ not extractable).
• Context: from /models.max_context_length — 262 144 (Large 3, Medium 3.5, Small 4, Ministral 8B/14B, Leanstral), 256 000 (Codestral), 131 072 (Ministral 3B), 1 048 576 (GLM 5.2), 32 768 (Voxtral Small). Exceeding it → 400 (docs). Max output: not published per model except GLM (128k, model card); max_tokens above context is accepted silently (probed) → registry maxOutputTokens: null, cap in UI at context − prompt.

# 11. Server-side tools, Conversations API, citations (probed)

• On /v1/chat/completions: tools:[{type:"web_search"}] → 400 code 1800 {"type":"invalid_tools","message":"WebSearchTool connector is not supported"}. Docs: web_search, web_search_premium, code_interpreter are Conversations/Agents-API only; image_generation is claimed to work on chat completions (not probed, $0.10/image).
• POST /v1/conversations {model, inputs:"…", tools:[{type:"web_search"}], store:false, completion_args:{max_tokens, temperature, response_format, …}} → 200 (probed):

{ "object":"conversation.response", "conversation_id":"conv_01a0…",
  "outputs":[
    {"object":"entry","type":"tool.execution","name":"web_search","arguments":"{\"query\": \"…\"}","info":{"result":"{\"D5PmwtGh\": {\"url\":…,\"title\":…,\"snippets\":[…]}}"},"id":"tool_exec_…","created_at":…,"completed_at":…},
    {"object":"entry","type":"message.output","role":"assistant","id":"msg_…","content":[
       {"type":"text","text":"The latest stable Node.js version is **26.8.1**…"},
       {"type":"tool_reference","tool":"web_search","title":"…","url":"https://versionlog.com/nodejs/","favicon":"https://imgs.search.brave.com/…","description":"…"},
       {"type":"text","text":"."}]}],
  "usage":{"prompt_tokens":779,"completion_tokens":66,"total_tokens":6582,"connector_tokens":5737,"connectors":{"web_search":1}},
  "guardrails":null }

Citations = inline tool_reference chunks (title, url, favicon, description) placed where the model cites; the raw search results sit in tool.execution.info.result (Brave-backed). Billing trap: connector_tokens (5 737 here, the search results fed to the model) are billed as input tokens on top of the $30 / 1k web_search calls.

• Streaming (stream:true): SSE with event: names — conversation.response.started {conversation_id}, message.output.delta {output_index, id, content_index, role, content:"Hi"} (content is a plain string per delta; tool_reference deltas presumably arrive as chunk objects — not observed), conversation.response.done {usage}; docs also list tool.execution.started/done, function.call.delta, agent.handoff.*, conversation.response.error.
• Client function tools, handoff_execution, instructions, previous-style continuation (POST /v1/conversations/{id}), restart, history GET/DELETE exist (docs). store defaults to true — send store:false for BYOK privacy.
• Pricing (docs): web search $30 / 1k calls, premium news $50 / 1k, code interpreter $30 / 1k, image generation $100 / 1k, document library $0.01 / call + OCR/indexing.

# 12. Model listing & pricing (probed + docs)

GET /v1/models → {object:"list", data:[…]} with 50 rows (aliases are separate rows). Fields: id, object:"model", created (= request time, useless), owned_by ("mistralai"), name (canonical, e.g. "mistral-large-2512"), description, max_context_length, aliases[], deprecation (null everywhere today), deprecation_replacement_model, default_model_temperature (0.3 most; **1** for Medium 3.5 & Leanstral; 0.2 Voxtral; null GLM), billing_model_name (canonical billing id — use it to dedupe), type ("base"), capabilities {completion_chat, function_calling, reasoning, completion_fim, fine_tuning, vision, ocr, classification, moderation, audio, audio_transcription, audio_transcription_realtime, audio_speech, unified_resources}. No pricing, no max output in the API. capabilities.audio is false even for voxtral-small (looks wrong vs docs). Docs' /models schema (root, archived, job) is outdated.

Dedupe by billing_model_name → 10 chat-capable models (the 10 entries in mistral.models.json):

Cached input = 10 % of input everywhere. Batch −50 %. Priority tier ×1.75. Regional +10 %. Non-chat: OCR 4.1 $4 / 1k pages, Voxtral Mini Transcribe 2 $0.003/min, TTS $0.016 / 1k chars, embeddings $0.10–0.15, moderation free.

# 13. Prompt caching & provider-side state

• Explicit, key-based: send the same prompt_cache_key (session/conversation id) on requests sharing a prefix; 64-token blocks (cached_tokens is a multiple of 64, prompts < 64 tokens never hit); billed at 10 %; reported in usage.prompt_tokens_details.cached_tokens; no TTL documented (docs). Probed: identical 3 273-token prefix — call 1 cached_tokens: 0, call 2 (same key) cached_tokens: 3248, call 3 (no key) 0; the rate-limit header x-ratelimit-tokens-query-cost went 3 276 → 28, so cache hits also spare TPM. Adapter: always send prompt_cache_key = conversationId.
• Chat completions are stateless. The Conversations API stores by default (store:true) — pass store:false.

# 14. Errors, rate limits, retries

Two error envelopes (probed):

1. Business errors: {"object":"error","message":"…","type":"<type>","param":null,"code":"<numeric string>","raw_status_code":400}.
2. Validation errors (422) and auth: {"detail": …} (pydantic list, or "Invalid API Key"); some 422s are wrapped in envelope 1 with message.detail[].

Rate limits (docs + headers): scoped per workspace, per model, expressed as requests/min + tokens/min headers (docs talk RPS + tokens/month). Tiers by cumulative spend: Free → Tier 1 (pay-as-you-go on) → Tier 2 (> $20) → Tier 3 (> $100) → Tier 4 (> $500) → custom. Observed on this key (req/min · tokens/min): Large 3 75 · 1M (!), Medium 3.5 3000 · 2M, Small 4 2000 · 2M, Ministral 8B 3800 · 2.5M, 14B 500 · 3.8M, 3B 15000 · 5M, Codestral 2500 · 2.5M, GLM 3000 · 4M, Voxtral Small 1440 · 500k. Users see theirs at admin.mistral.ai/plateforme/limits.

Retry/timeout recommendation: retry 429 / 5xx with jittered exponential backoff (respect retry-after if present), never retry 400/401/403/422; surface x-kong-request-id in error toasts; read timeout ≥ 5 min for reasoning_effort: "high" (thinking deltas arrive quickly as liveness). Map 401 Invalid API Key → invalid credentials; map 403 Labs → model not enabled for this workspace.

# 15. Lifecycle / aliases / deprecations

• Policy (docs /inference/model-lifecycle): notice before retirement = 6 months GA, 1 month Labs / Public Preview / third-party; retired ids "fail with 404" (actually 400 invalid_model (probed)). -latest aliases move automatically to the next GA model ("silent updates in model behaviour and pricing") → pin dated ids in the registry, show -latest as aliases.
• deprecation / deprecation_replacement_model are null for every current model (probed); the docs table (models overview) lists retired ones: mistral-medium-2508 (ret. 2026-08-31), mistral-small-2506 (2026-07-31), magistral-medium-2509 / magistral-small-2509 (2026-07-31), devstral-2512 (2026-07-31), mistral-large-2411, pixtral-large-2411, devstral-*-2507 (2026-05-31), open-mistral-nemo-2407 (2026-07-31), labs-leanstral-2603 (2026-06-30), mistral-moderation-2411, voxtral-mini-2507, older 2024/25 models.
• Silent redirects (probed): mistral-small-2506 → served as mistral-small-latest; mistral-medium-2508 / -2505 → mistral-medium-3-5; pixtral-12b-2409 → ministral-14b-latest; open-mistral-7b, ministral-8b-2410, open-mistral-nemo → Ministral 8B; codestral-2501 → codestral-latest; mistral-small-2501, mistral-saba-latest → Small 4; mistral-large-2407 → Large 3. Hard 400: magistral-*-25xx, mistral-large-2411, pixtral-large-latest, devstral-medium-2507. Don't list any of these; if a user types one, show the redirect from response.model.
• Alias sprawl worth knowing: mistral-medium, mistral-medium-3, mistral-medium-3.5, mistral-vibe-cli-latest, mistral-vibe-cli-with-tools (Vibe CLI product aliases) → Medium 3.5; mistral-vibe-cli-fast → Small 4; mistral-code-latest, mistral-code-fim-latest → Codestral; glm-5-2 ↔ zai-glm-5-2.
• Changelog 2026: Medium 3.5 GA 2026-04-28; Small 4 (2603); GLM 5.2 preview 2026-08-06; OCR 4.1 GA Aug 2026; Leanstral 1.5 June 2026 (retire 2026-09-30); docs moved to /vibe/*, /studio/* May 2026.

# 16. Exact streaming code that worked

Raw fetch SSE (research/mistral/lib.ts → rawSSE) and the OpenAI SDK both worked; the reasoning-aware accumulation used in 08-sdks-cache.ts:

import OpenAI from "openai";
const client = new OpenAI({ apiKey: process.env.MISTRAL_API_KEY, baseURL: "https://api.mistral.ai/v1", timeout: 300_000, maxRetries: 0 });

const stream = await client.chat.completions.create({
  model: "mistral-medium-2604",
  messages: [{ role: "system", content: "Be concise." }, { role: "user", content: "Is 17 prime? One sentence." }],
  stream: true,
  max_tokens: 400,                       // covers thinking + answer
  random_seed: 42,                       // NOT `seed` (422)
  prompt_cache_key: conversationId,      // enables prefix caching
  reasoning_effort: "high",              // only "high" | "none" on Mistral hybrids; omit on Large/Ministral/Codestral
} as any);

for await (const chunk of stream as any) {
  const choice = chunk.choices?.[0];
  const c = choice?.delta?.content;
  if (typeof c === "string") { if (c) onText(c); }
  else if (Array.isArray(c)) {
    for (const part of c) {
      if (part.type === "thinking") for (const t of part.thinking ?? []) if (t.text) onThinking(t.text);
      else if (part.type === "text" && part.text) onText(part.text);
    }
  }
  if (choice?.delta?.tool_calls) accumulateByIndex(choice.delta.tool_calls); // 1 chunk on Mistral, many on GLM
  if (choice?.finish_reason) onFinish(choice.finish_reason);
  if (chunk.usage) onUsage(chunk.usage);  // same chunk as finish_reason; usage.prompt_tokens_details.cached_tokens
}

Official SDK equivalent: for await (const ev of await mistral.chat.stream({ model, messages, maxTokens, reasoningEffort: "high", promptCacheKey })) { const d = ev.data.choices[0].delta; … ev.data.choices[0].finishReason; ev.data.usage?.promptTokens } (camelCase, except prompt_tokens_details).

# 17. Probe results table

# Documentation pages used (all fetched 2026-09-08)

• https://docs.mistral.ai/ · https://docs.mistral.ai/sitemap.xml · https://docs.mistral.ai/llms.txt (stale /docs/*.md links, all 404)
• Models: https://docs.mistral.ai/getting-started/models/models_overview/ (deprecation table) · https://docs.mistral.ai/models · https://docs.mistral.ai/models/mistral-medium-3-5-26-04 · https://docs.mistral.ai/models/mistral-large-3-25-12 · https://docs.mistral.ai/models/codestral-25-08 · https://docs.mistral.ai/models/zai-glm-5-2 · https://docs.mistral.ai/inference/model-lifecycle · https://docs.mistral.ai/inference/model-selection-guide · https://docs.mistral.ai/inference/labs
• API reference: https://docs.mistral.ai/api/ · https://docs.mistral.ai/api/endpoint/chat · https://docs.mistral.ai/api/endpoint/models · https://docs.mistral.ai/api/endpoint/fim · https://docs.mistral.ai/api/endpoint/beta/conversations
• Capabilities: https://docs.mistral.ai/capabilities/reasoning/ · https://docs.mistral.ai/studio/conversations/reasoning · https://docs.mistral.ai/capabilities/function_calling/ · https://docs.mistral.ai/studio/conversations/function-calling · https://docs.mistral.ai/capabilities/vision/ · https://docs.mistral.ai/studio/conversations/vision · https://docs.mistral.ai/studio-api/conversations/vision · https://docs.mistral.ai/studio/conversations/structured-output (+ /custom) · https://docs.mistral.ai/studio/conversations/citations · https://docs.mistral.ai/studio/conversations/chat-completion · https://docs.mistral.ai/studio-api/conversations/advanced/prompt-caching · https://docs.mistral.ai/studio-api/conversations/advanced/predicted-outputs · https://docs.mistral.ai/capabilities/document_ai/ · https://docs.mistral.ai/studio/document-processing/document_qna · https://docs.mistral.ai/capabilities/audio/ · https://docs.mistral.ai/studio/audio/overview
• Agents: https://docs.mistral.ai/studio/agents/introduction · https://docs.mistral.ai/studio/agents/agents-api · https://docs.mistral.ai/studio/agents/agent-tools
• Safety: https://docs.mistral.ai/studio/safety-moderation
• Pricing / limits: https://mistral.ai/pricing · https://mistral.ai/pricing/api · https://docs.mistral.ai/inference/pricing · https://docs.mistral.ai/inference/priority-tier · https://docs.mistral.ai/inference/sampling · https://docs.mistral.ai/admin/user-management-finops/tier · https://docs.mistral.ai/admin/workspaces/usage-limits · https://docs.mistral.ai/admin/billing-usage/usage-limits · https://docs.mistral.ai/resources/known-limitations · https://help.mistral.ai/en/articles/698531-why-am-i-hitting-api-rate-limits-and-how-do-i-increase-them
• Misc: https://docs.mistral.ai/getting-started/changelog/ · https://docs.mistral.ai/resources/sdks · https://docs.mistral.ai/resources/migration-guides · https://github.com/mistralai/client-ts
• 404 at audit time: /capabilities/structured-output/custom/, /capabilities/structured-output/, /capabilities/document/, /deployment/laplateforme/tier/, /deployment/laplateforme/, /models/deprecation, /models/mistral-small-4-26-03, /models/mistral-small-26-03, /studio/conversations/prompt-caching, /studio-api/conversations/advanced/prefix, every /docs/*.md from llms.txt.