NewYour coding agent can read the release notes before it upgrades.Set up the MCP server →
pub.dev · #2696 most downloaded on pub.dev
Type-safe Dart client for Ollama chat, generation, embeddings, System One decisions, model management, and cloud web search.
Last release 8 days ago
30 Sep 2026
Release timing varies
gaps range from 9 days to 5 months
Nearly every release is documented
notes for 38 of 38 stable releases
Nothing withdrawn
no release was ever pulled
3 years old
38 releases · first in 2023
> 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 System One decision models, binary blob operations, and authenticated hosted web search/fetch, with complete thinking discovery, cached-token metrics, tool replay, context controls, and model metadata for Ollama 0.35.0. ThinkValue gains ThinkWithString for arbitrary model-defined levels, so exhaustive switches must handle the new variant; existing factories remain available. Binary uploads retain their bytes through authentication and logging, and experimental image fields remain available for compatible servers while Ollama 0.35.0 rejects image generation.
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.
Requires Dart 3.12 or later; upgrade your Dart SDK or the Dart SDK bundled with Flutter before updating this package.
Maintenance release with no functional changes: the only commit touching this package since 2.6.0 reformatted its integration tests as part of a cross
Adds the official thinking field to ChatMessage, so a model's reasoning trace can be replayed in the follow-up assistant message. Ollama's tool-callin
Adds the official thinking field to ChatMessage, so a model's reasoning trace can be replayed in the follow-up assistant message. Ollama's tool-calling guidance requires accumulated thinking, content, and tool calls to be sent back together, but the thinking trace was previously dropped from chat history. Set it via ChatMessage.assistant(content, thinking: ...); it round-trips through JSON and is covered by ==, hashCode, and toString.
Adds renderer and parser to CreateRequest, matching the upstream OpenAPI spec's new tool-calling prompt renderer (e.g. qwen3.5) and output parser (e.g
Adds renderer and parser to CreateRequest, matching the upstream OpenAPI spec's new tool-calling prompt renderer (e.g. qwen3.5) and output parser (e.g. harmony) fields. Also adds client-ahead fields for full api/types.go parity that the spec still omits — files/adapters (filename → SHA256 digest maps, per the Create a Model docs) for creating models from GGUF/Safetensors and LoRA adapters, plus draftQuantize/draftFiles, remoteHost, requires, and info. Also fixes CreateRequest's ==/hashCode/toString contract, which previously only compared model, to cover all 18 fields with content-based map/list equality.
Adds the new max thinking level (ThinkLevel.max), matching Ollama's spec update that added "max" to the think enum on ChatRequest and GenerateRequest
Adds the new max thinking level (ThinkLevel.max), matching Ollama's spec update that added "max" to the think enum on ChatRequest and GenerateRequest — use ChatRequest(..., think: ThinkWithLevel(ThinkLevel.max)) to request the highest thinking level on supported reasoning models. Also fixes buildUrl producing a double slash (//api/...) when OllamaConfig.baseUrl (or OLLAMA_HOST) has a trailing slash, and preserves base-URL query params (including repeated keys) that were previously dropped — proxy setups with tokens in the base URL now work correctly.
Adds experimental image generation to the /api/generate endpoint: GenerateRequest gains width/height/steps, and GenerateResponse and the streaming Gen
Adds experimental image generation to the /api/generate endpoint: GenerateRequest gains width/height/steps, and GenerateResponse and the streaming GenerateStreamEvent gain image (base64), completed, and total for diffusion progress. These fields are implemented client-side ahead of the upstream spec, which keeps them out of openapi.yaml while they remain experimental. Also adds the draftNumPredict model option to ModelOptions and completes the previously-partial ==/hashCode/toString contracts on GenerateStreamEvent and ChatStreamEvent, which had compared only a subset of fields.
Fixes browser usage (Flutter Web / dart2wasm) by no longer sending the non-CORS-safelisted X-Request-ID header by default — Ollama's Access-Control-Al
Fixes browser usage (Flutter Web / dart2wasm) by no longer sending the non-CORS-safelisted X-Request-ID header by default — Ollama's Access-Control-Allow-Headers list excludes it, so the preflight previously failed and blocked all browser requests against a real Ollama server. A request ID is still generated internally for logging, error correlation, and retry/abort tracing; the new OllamaConfig(sendRequestIdHeader: true) opt-in restores the wire header for callers behind a proxy configured to accept it, and an X-Request-ID set explicitly via defaultHeaders is always sent.
Annotates llms.txt with per-link token counts and per-package totals so coding agents can budget context before fetching documentation, examples, or c
Annotates llms.txt with per-link token counts and per-package totals so coding agents can budget context before fetching documentation, examples, or changelogs — inspired by Addy Osmani's Agentic Engine Optimization article.
Adds a strict semver bullet to the package README.
> 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.
Replaces untyped Object/Object? fields with sealed union types (KeepAlive, EmbedInput, StopSequence) for improved type safety across request models. Also adds a name field to RunningModel from the upstream Ollama API update and overhauls README documentation with llms.txt ecosystem files.
Fixed verification warnings in generated model classes.
DOCS: Improve READMEs with badges, sponsor section, and vertex_ai deprecation (#90).
Added missing fields to chat, completion, and model response models.
Internal improvements to build tooling and package publishing configuration.
Added baseUrl and defaultHeaders parameters to withApiKey constructors, fixed hashCode for list fields, and unified equality helpers.
Added baseUrl and defaultHeaders parameters to withApiKey constructors, fixed hashCode for list fields, and unified equality helpers.
Added withApiKey convenience constructor for simplified client initialization.
> 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 Ollama API coverage.
client.chat — Chat completions (multi-turn conversations)client.completions — Text generation (single-turn)client.embeddings — Generate text embeddingsclient.models — Model management (list, show, pull, push, copy, delete, create, ps)client.version — Server version infoAuthProvider interface.abortTrigger parameter.OllamaConfig (timeouts, retry policy, log level, baseUrl, auth).http, logging only).copyWith using sentinel pattern.DoneReason enum for completion stop reasons (stop, length, load, unload).ThinkValue sealed class for thinking mode (ThinkEnabled, ThinkWithLevel).ResponseFormat sealed class for format options (JsonFormat, SchemaFormat).MessageRole enum for message roles (system, user, assistant, tool).ChatRequest instead of GenerateChatCompletionRequest).ChatMessage.user(), ChatMessage.system()).createStream() vs create()).client.generateChatCompletion() → client.chat.create()client.generateChatCompletionStream() → client.chat.createStream()client.generateCompletion() → client.completions.generate()client.generateCompletionStream() → client.completions.generateStream()client.generateEmbedding() → client.embeddings.create()client.listModels() → client.models.list()client.showModelInfo() → client.models.show()client.listRunningModels() → client.models.ps()client.getVersion() → client.version.get()GenerateChatCompletionRequest → ChatRequestGenerateChatCompletionResponse → ChatResponseGenerateCompletionRequest → GenerateRequestGenerateCompletionResponse → GenerateResponseGenerateEmbeddingRequest → EmbedRequestGenerateEmbeddingResponse → EmbedResponseMessage → ChatMessageTool → ToolDefinitionRequestOptions → ModelOptionsOllamaConfig with AuthProvider pattern.OllamaClientException with typed hierarchy:
ApiException, ValidationException, RateLimitException, TimeoutException, AbortedException.freezed, json_serializable; now minimal (http, logging)./api suffix — just use http://localhost:11434.See MIGRATION.md for step-by-step examples and mapping tables.
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).
FEAT: Add think/thinking params to ollama_dart (#721).
REFACTOR: Add new lint rules and fix issues (#621).
FEAT: Update Ollama default model to llama-3.2 (#554).
FEAT: Add support for min_p in Ollama (#512).
> 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: Add support for listing running Ollama models (#451).
FEAT: Support buffered stream responses (#445).
FIX: digest path param in Ollama blob endpoints (#430).
> 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.
FIX: Have the == implementation use Object instead of dynamic (#334).
- DOCS: Update CHANGELOG.md.
FEAT: Add support for chat API and multi-modal LLMs (#274).
- DOCS: Update README.me.
FIX: Fetch web requests with big payloads dropping connection (#273).
FEAT: Implement ollama_dart, a Dart client for Ollama API (#238).
Your coding agent can read these notes before it upgrades. Set up the MCP server →