NewYour coding agent can read the release notes before it upgrades.Set up the MCP server →
pub.dev · #4367 most downloaded on pub.dev
Dart client for the Mistral AI API - chat, embeddings, fine-tuning, agents, and more.
Last release 4 days ago
04 Oct 2026
Ships on a steady schedule
a new release about every 3 weeks
Nearly every release is documented
notes for 38 of 38 stable releases
Nothing withdrawn
no release was ever pulled
3 years old
39 releases · first in 2023
Fixes Flutter Web and dart2wasm requests blocked by Mistral CORS by omitting the X-Request-ID header by default. Request IDs remain available for logg
Fixes Flutter Web and dart2wasm requests blocked by Mistral CORS by omitting the X-Request-ID header by default. Request IDs remain available for logging and error correlation; enable MistralConfig.sendRequestIdHeader when using a proxy that accepts the header. Explicit caller-supplied headers are preserved.
> This release has breaking changes. See the Migration Guide for upgrade instructions.
[!CAUTION] This release has breaking changes. See the Migration Guide for upgrade instructions.
Requires Dart 3.12 or later; upgrade your Dart SDK or the Dart SDK bundled with Flutter before updating this package. File uploads now include authentication and request IDs, use the shared error mapping, and retry with a fresh multipart body.
One column per month.
> This release has breaking changes. See the Migration Guide for upgrade instructions.
[!CAUTION] This release has breaking changes. See the Migration Guide for upgrade instructions.
Audio transcription now accepts in-memory bytes with a filename or an audio URL, alongside uploaded file IDs, and sends the multipart requests expected by the Mistral API. Both regular and streaming transcriptions support these sources, with replayable multipart bodies for retries of regular requests. Breaking: TranscriptionRequest.file is now nullable, explicit null arguments to copyWith clear nullable fields, and request equality and hashing include every field.
Adds the official index field to ToolCall, which Mistral sets on streamed tool-call deltas. Without it, deltas from parallel calls to the same tool co
Adds the official index field to ToolCall, which Mistral sets on streamed tool-call deltas. Without it, deltas from parallel calls to the same tool could not be correlated, so their arguments were conflated while accumulating a stream. The field round-trips through JSON and is included in ==, hashCode, and toString.
> This release has breaking changes. See the Migration Guide for upgrade instructions.
[!CAUTION] This release has breaking changes. See the Migration Guide for upgrade instructions.
Adds client.prompts and client.skills v2 registries with versioning and aliases, managed workflow deployments (create/start/stop/restart with SSE log streaming), and new client.users.me() and connector share/deleteAllUserCredentials endpoints. Breaking: the RAG search index API is replaced by a fully Vespa-typed /v1/rag/indexes surface, and the fine-tuning jobs API (along with FineTuningJobPoller) is removed entirely — a confirmed upstream deprecation per the Mistral changelog and deprecated fine-tuning endpoints notice — with only fine-tuned-model management remaining. Connector request fields and observability dataset record types are also renamed/retyped to match the current spec.
> This release has breaking changes. See the Migration Guide for upgrade instructions.
[!CAUTION] This release has breaking changes. See the Migration Guide for upgrade instructions.
Adds OCR-4 paragraph-level block extraction: set OcrRequest.includeBlocks: true to receive OcrPage.blocks, a sealed 13-variant OcrBlock union (text, title, list, table, image, equation, caption, code, and more), each with a bounding box and content in reading order. Breaking: OcrRequest.pages changes from List<int>? to the sealed OcrPages union, which also supports the new comma-separated string/range form (OcrPages.string('0,2-4')) alongside explicit lists (OcrPages.list([0, 1, 2])). Also fixes buildUrl producing a double slash when the base URL has a trailing slash and dropping (or collapsing repeated) base-URL query params, and adds a canonical package example so pub.dev's "Package has an example" check passes.
> This release has breaking changes. See the Migration Guide for upgrade instructions.
[!CAUTION] This release has breaking changes. See the Migration Guide for upgrade instructions.
Syncs mistralai_dart with the latest Mistral OpenAPI spec (+46 paths, +123 schemas over the 2026-06-05 baseline), cross-checked field-by-field against the official mistralai/client-python SDK. Adds four new beta surfaces — Connectors (client.connectors: full CRUD + auth + tools + credentials), Observability traces/spans/logs (client.observability), RAG (client.rag: ingestion pipelines + search index), and new Workflow operations (bulk archive/unarchive, schedule pause/resume/trigger, execution logs + SSE) — plus many additive fields and enum values (ReasoningEffort.minimal/xhigh, expanded ModelCapabilities, ThinkContentPart.signature, and more). The breaking changes mirror server-side removals from the official Python SDK and affect a narrow surface: UsageInfo drops cached-token detail fields, OcrRequest drops its id, ChatChoice.message becomes nullable (with finishReason now non-nullable), and the deleted workers/whoami endpoint plus a few workflow fields are removed. See the Migration Guide for the full list and upgrade paths.
Migrates deprecated Mistral model identifiers to their current replacements (verified against Mistral's docs). The default model on the moderation/cla…
Migrates deprecated Mistral model identifiers to their current replacements (verified against Mistral's docs). The default model on the moderation/classification request classes (ModerationRequest, ChatModerationRequest, ClassificationRequest, ChatClassificationRequest) moves from the deprecated mistral-moderation-latest to mistral-moderation-2603 (Mistral Moderation 2) — so requests that omit model now target the current model — and the deprecated mistral-large-2411 doc examples move to the live mistral-large-latest alias. No schema changes.
Adds promptCacheKey to AgentCompletionRequest, ChatCompletionRequest, and FimCompletionRequest — tokens served from a cached prefix are billed at 10%
Adds promptCacheKey to AgentCompletionRequest, ChatCompletionRequest, and FimCompletionRequest — tokens served from a cached prefix are billed at 10% of the standard input price. Re-introduces OCR confidence scores (OcrConfidenceScore, OcrPageConfidenceScores, the OcrConfidenceScoresGranularity enum, and the related fields on OcrRequest/OcrPage/OcrTable) following their return to the upstream spec, and adds the previously-missing metadata field on FimCompletionRequest for parity with the other completion requests. Refreshes the bundled OpenAPI spec to its 2026-05-09 snapshot. All changes are additive.
> This release has breaking changes. See the Migration Guide for upgrade instructions.
[!CAUTION] This release has breaking changes. See the Migration Guide for upgrade instructions.
Syncs with the 2026-04-22 Mistral AI spec: 9 endpoints and 20 schemas were removed upstream with no additions. Breaking: the entire OCR confidence-score surface has been removed server-side, so OcrConfidenceScore, OcrPageConfidenceScores, OcrConfidenceScoresGranularity, and the related fields on OcrRequest, OcrPage, and OcrTable are gone from the client. The orphan WorkflowListResponse model is also deleted along with its retired GET /v1/workflows endpoint. This release also adds missing copyWith methods on ObservabilityError and ObservabilityErrorDetail.
Adds support for OCR confidence scores with a new confidenceScoresGranularity request parameter (page or word) and per-page/per-word score response ty
Adds support for OCR confidence scores with a new confidenceScoresGranularity request parameter (page or word) and per-page/per-word score response types. Also fills pre-existing spec gaps on OcrPage (tables, header, footer, hyperlinks) and OcrRequest (tableFormat, extractHeader, extractFooter, annotation formats).
Adds two new beta API domains — Observability (41 endpoints for campaigns, datasets, judges, and chat completion monitoring) and Workflows (34 endpoin
Adds two new beta API domains — Observability (41 endpoints for campaigns, datasets, judges, and chat completion monitoring) and Workflows (34 endpoints for workflow execution, scheduling, deployments, and tracing). Refreshes the OpenAPI spec with 75 new endpoints and 126 new schemas.
Adds an extra overflow field to SpeechRequest for passing additional properties to the Mistral speech API, and aligns the README layout with other pac
Adds an extra overflow field to SpeechRequest for passing additional properties to the Mistral speech API, and aligns the README layout with other packages.
Adds ToolFileContentPart and ToolReferenceContentPart sealed variants to ContentPart for built-in tool output content (code interpreter files, web sea
Adds ToolFileContentPart and ToolReferenceContentPart sealed variants to ContentPart for built-in tool output content (code interpreter files, web search references). Also adds unknown fallback values to ReasoningEffort and SpeechOutputFormat enums for forward compatibility.
> This release has breaking changes. See the Migration Guide for upgrade instructions.
[!CAUTION] This release has breaking changes. See the Migration Guide for upgrade instructions.
Major update to the latest Mistral AI spec. Renames ModerationLLMV1Action to ModerationLLMAction, adds Moderation V2 with 11 categories, guardrails on chat requests, CustomConnectorTool, 5 new ContentPart variants, and UnknownContentPart for forward compatibility. Replaces untyped Object fields with sealed union types (MessageContent, EmbedInput) for type safety across all ChatMessage variants. Adds text-to-speech synthesis with streaming support, voice management with CRUD operations, reasoningEffort parameter, and llms.txt ecosystem files.
DOCS: Improve READMEs with badges, sponsor section, and vertex_ai deprecation (#90).
This release adds inline streaming error detection and updates the API spec to the latest version with new models and capabilities including agent aliases, guardrail configuration, tool call confirmations, and batch request types.
AgentAliasResponse, BatchRequest, GuardrailConfig, ToolCallConfirmation, ToolConfiguration), add agent alias CRUD methods, and update existing models with new fields (#89). (4aa455e7)Internal improvements to build tooling and package publishing configuration.
Added baseUrl and defaultHeaders parameters to withApiKey constructors and unified equality helpers across packages.
Added withApiKey convenience constructor and replaced Object? stop with a type-safe StopSequence sealed class for improved API safety.
Added withApiKey convenience constructor and replaced Object? stop with a type-safe StopSequence sealed class for improved API safety.
> This release has breaking changes. See the Migration Guide for upgrade instructions.
[!CAUTION] This release has breaking changes. See the Migration Guide for upgrade instructions.
TL;DR: Complete reimplementation with a new architecture, minimal dependencies, resource-based API, and improved developer experience. Hand-crafted models (no code generation), interceptor-driven architecture, comprehensive error handling, and full Mistral AI API coverage including stable and beta endpoints.
client.chat — Chat completions (streaming, tool calling, multimodal, JSON mode)client.embeddings — Text embeddings for semantic search and clusteringclient.models — Model listing and retrievalclient.fim — Fill-in-the-Middle code completions (Codestral)client.files — File upload and managementclient.fineTuning — Fine-tuning jobs and model managementclient.batch — Asynchronous large-scale batch processingclient.moderations — Content moderation for safetyclient.classifications — Text classification (spam, topic, sentiment)client.ocr — OCR for documents and imagesclient.audio — Speech-to-text transcription with streamingclient.agents — Pre-configured AI assistants (beta)client.conversations — Stateful multi-turn conversations (beta)client.libraries — Document storage and retrieval for RAG (beta)AuthProvider interface.abortTrigger parameter.[DONE] marker handling.MistralConfig (timeouts, retry policy, log level, baseUrl, auth).http, logging only).copyWith using sentinel pattern for nullable fields.ChatMessage, ContentPart, ToolChoice, ResponseFormat, Tool, OcrDocument).ChatMessage.user(), ChatMessage.system(), Tool.function(), Tool.webSearch()).createStream() vs create()).response.text, response.toolCalls, response.hasToolCalls).Paginator) and job polling helpers (FineTuningJobPoller, BatchJobPoller).See MIGRATION.md for step-by-step examples and mapping tables.
FIX: Fix streaming tool calls deserialization error (#913) (#914).
FEAT: Align Chat API with latest Mistral spec (#887).
REFACTOR: Fix pub format warnings (#809).
> This release has breaking changes. See the Migration Guide for upgrade instructions.
[!CAUTION] This release has breaking changes. See the Migration Guide for upgrade instructions.
FEAT: Migrate to Freezed v3 (#773).
BUILD: Update dependencies (#751).
FIX: Have the == implementation use Object instead of dynamic (#334).
FIX: Fix deserialization of sealed classes (#435).
REFACTOR: Migrate conditional imports to js_interop (#453).
REFACTOR: Add new lint rules and fix issues (#621).
FEAT: Update meta and test dependencies (#331).
Update a dependency to the latest release.
REFACTOR: Make all LLM options fields nullable and add copyWith (#284).
REFACTOR: Update safe_mode and max temperature in Mistral chat (#300).
- DOCS: Update CHANGELOG.md.
FEAT: Implement Dart client for Mistral AI API (#261).
FIX: Fetch web requests with big payloads dropping connection (#273).
- Bootstrap project.
Your coding agent can read these notes before it upgrades. Set up the MCP server →