Ollama v0.14.0: Anthropic API Compatibility and Claude Code Support

Ollama v0.14.0 and later versions introduce compatibility with the Anthropic Messages API, allowing users to run Anthropic's agentic coding tool, Claude Code, with open-source models. This update enables developers to leverage local models on their own machines or cloud-hosted models via ollama.com using tools designed for the Anthropic ecosystem.

Integration of Claude Code with Ollama

Claude Code is a terminal-based agentic coding tool developed by Anthropic. By implementing Anthropic API support, Ollama now allows Claude Code to interface with any Ollama model.

Configuration and Setup

To use Claude Code with Ollama, users must install the tool via the provided installation scripts for macOS, Linux, WSL, or Windows (PowerShell/CMD) and configure the following environment variables to redirect requests to the local Ollama instance:

  • ANTHROPIC_AUTH_TOKEN=ollama
  • ANTHROPIC_BASE_URL=http://localhost:11434

Once configured, the tool can be launched with a specific model, such as claude --model gpt-oss:20b for local use or claude --model glm-4.7:cloud for cloud-hosted models.

Context Length Requirements

Ollama recommends using models with a context length of at least 32K tokens for coding tasks. While Ollama's cloud models operate at their full context length by default, local users may need to adjust their context length settings according to Ollama's documentation.

Recommended Models for Coding

Ollama identifies specific models as suitable for use with Claude Code depending on the deployment method:

  • Local Models: gpt-oss:20b and qwen3-coder.
  • Cloud Models: glm-4.7:cloud and minimax-m2.1:cloud.

Anthropic SDK Compatibility

Beyond Claude Code, any existing application utilizing the Anthropic SDK (Python or JavaScript) can now connect to Ollama by updating the base_url to http://localhost:11434 and providing ollama as the API key (which is required by the SDK but ignored by Ollama).

Tool Calling Support

Ollama's compatibility layer supports tool calling (function calling), allowing models to interact with external systems. This is achieved by passing a tools array within the messages.create call, defining the tool's name, description, and input schema.

Supported API Features

Ollama v0.14.0 provides support for several key features of the Anthropic Messages API, including:

  • Multi-turn conversations and messages
  • Streaming responses
  • System prompts
  • Tool and function calling
  • Extended thinking
  • Vision (image input)

Sources

Related

  • Dispatch
    Claude Desktop integration with Ollama enables local and cloud model switching

    Ollama now lets Claude Desktop act as a third‑party gateway, so users can run Claude alongside any local or cloud model in Ollama without sending data to Anthropic.

  • Dispatch
    Ollama launch command release

    Ollama has introduced the 'ollama launch' command in version 0.15+, allowing users to set up and run coding tools like Claude Code and OpenCode without manual environment variables or configuration files.

  • Dispatch
    Ollama adds Subagents and Web Search to Claude Code

    Ollama now supports subagents and web search within Claude Code, allowing models to run parallel tasks and access real-time information without requiring MCP servers or API keys.

  • Project
    Prorise-cool/Claude-Code-Multi-Agent

    Claude Code Multi‑Agent is an open‑source framework that gives Anthropic’s Claude Code project awareness and expert‑agent capabilities. It uses a Python Hook system and a locally‑run Ollama model to automatically detect the codebase type, analyse user intent, load 300+ domain‑specific “Skills” (backend, frontend, testing, security, etc.), and enforce automatic documentation (DEVELOPMENT.md, KNOWLEDGE.md, CHANGELOG.md). After cloning, installing Ollama, a model, and uv, you drop your project into the repo and Claude Code instantly knows its context, suggests appropriate tools, and can be driven with slash commands like `/backend‑specialist` or workflow commands such as `/kiro/spec`. Key points: - Zero‑config start; all configuration lives in `.claude/settings.json` and `prompts.json`. - Hooks run on session start, user prompt, tool use, etc., handling project detection, intent analysis, and doc updates. - Skills are defined by `SKILL.md` files and are auto‑discovered. - Works entirely locally (no external API), integrates with Git, and is MIT‑licensed. Ideal for developers or small teams who want a reproducible, on‑premise AI coding assistant.

  • Dispatch
    Ollama Tool Support Release

    Ollama has introduced tool calling support for models like Llama 3.1, allowing local LLMs to interact with external APIs, functions, and code interpreters.