--- title: "ax vs litellm" type: "comparison" canonical_url: "https://www.graphcanon.com/compare/ax-llm-ax-vs-berriai-litellm" tools: ["ax-llm-ax", "berriai-litellm"] --- # ax vs litellm *GraphCanon updated Jul 15, 2026* ## Verdict Pick ax when ax is primarily TypeScript; litellm is Python; pick litellm when litellm is primarily Python; ax is TypeScript. [ax](http://axllm.dev) reports 2.8k GitHub stars, 182 forks, and 5 open issues, last pushed Jul 15, 2026. [litellm](https://docs.litellm.ai/docs/) has 53k stars, 9.7k forks, and 3.9k open issues, last pushed Jul 11, 2026. Figures are from public GitHub metadata via [ax's repository](https://github.com/ax-llm/ax) and [litellm's repository](https://github.com/BerriAI/litellm). | | [ax](/tools/ax-llm-ax.md) | [litellm](/tools/berriai-litellm.md) | | --- | --- | --- | | Tagline | The pretty much "official" DSPy framework for Typescript | Python SDK and Proxy Server for calling multiple LLM APIs | | Stars | 2,819 | 53,271 | | Forks | 182 | 9,671 | | Open issues | 5 | 3,915 | | Language | TypeScript | Python | | Adopt for | - | litellm is a Python SDK and Proxy Server that facilitates the interaction with over 100 LLM APIs, offering features such as cost tracking, guardrails, load balancing, and logging. | | Persona | - | - | | Runtime | - | - | | License | Apache-2.0 | The licensing terms for LiteLLM are provided under a license type categorized as 'Other'; details of the exact license should be referenced directly from its source. | | Categories | Inference & Serving, LLM Frameworks, Vector Databases | Inference & Serving, LLM Frameworks | ## Trust and health _Sourced signals - not a safety guarantee. No winner column._ | | [ax](/tools/ax-llm-ax.md) | [litellm](/tools/berriai-litellm.md) | | --- | --- | --- | | Open issues (now) | 5 | 3.9k | | Full report | [trust report](/tools/ax-llm-ax/trust.md) | [trust report](/tools/berriai-litellm/trust.md) | ## Decision facts: litellm - **Pricing:** freemium - While the core functionality is provided free, specific extended features might require a paid plan. - **Requirements:** Requires Docker - **Adopt for:** litellm is a Python SDK and Proxy Server that facilitates the interaction with over 100 LLM APIs, offering features such as cost tracking, guardrails, load balancing, and logging. - **License detail:** The licensing terms for LiteLLM are provided under a license type categorized as 'Other'; details of the exact license should be referenced directly from its source. ## Choose when ### Choose ax if… - ax is primarily TypeScript; litellm is Python. - License: ax is Apache-2.0, litellm is Other. - Tags unique to ax: ai, anthropic, claude, cohere. - Also covers Vector Databases. ### Choose litellm if… - litellm is primarily Python; ax is TypeScript. - License: litellm is Other, ax is Apache-2.0. - Pricing: While the core functionality is provided free, specific extended features might require a paid plan.. - Requirements: Requires Docker. - Tags unique to litellm: ai-gateway, azure-openai, bedrock, llm. - litellm ships Docker support for self-hosted deployment. - When you need to integrate multiple LLM (Language Learning Modelling) APIs into your application across different providers like Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthropic, Sagemaker, Hugging ## When NOT to use ax - Inference & Serving: Self-hosting rarely beats a hosted API on cost until you have steady, high-volume traffic. - LLM Frameworks: Avoid a framework for a single prompt-and-retrieve call; the abstraction can cost more than it saves. - Vector Databases: Don't reach for a dedicated vector DB under ~100k vectors; pgvector on your existing Postgres is simpler to operate. ## When NOT to use litellm - If your project only requires interaction with a single LLM API and basic functionalities, litellm may be overkill. ## Common questions ### What is the difference between ax and litellm? ax: The pretty much "official" DSPy framework for Typescript. litellm: Python SDK and Proxy Server for calling multiple LLM APIs. See the comparison table for live GitHub stats and shared categories. ### When should I choose ax over litellm? Choose ax over litellm when ax is primarily TypeScript; litellm is Python; License: ax is Apache-2.0, litellm is Other; Tags unique to ax: ai, anthropic, claude, cohere; Also covers Vector Databases. ### When should I choose litellm over ax? Choose litellm over ax when litellm is primarily Python; ax is TypeScript; License: litellm is Other, ax is Apache-2.0; Pricing: While the core functionality is provided free, specific extended features might require a paid plan.; Requirements: Requires Docker; Tags unique to litellm: ai-gateway, azure-openai, bedrock, llm; litellm ships Docker support for self-hosted deployment; When you need to integrate multiple LLM (Language Learning Modelling) APIs into your application across different providers like Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthropic, Sagemaker, Hugging. ### When should I avoid ax? Inference & Serving: Self-hosting rarely beats a hosted API on cost until you have steady, high-volume traffic. LLM Frameworks: Avoid a framework for a single prompt-and-retrieve call; the abstraction can cost more than it saves. Vector Databases: Don't reach for a dedicated vector DB under ~100k vectors; pgvector on your existing Postgres is simpler to operate. ### When should I avoid litellm? If your project only requires interaction with a single LLM API and basic functionalities, litellm may be overkill. ### Is ax or litellm more popular on GitHub? litellm has more GitHub stars (53,271 vs 2,819). Stars measure visibility, not whether either tool fits your constraints. ### Are ax and litellm open source? Yes - both are open-source projects on GitHub (ax: Apache-2.0, litellm: Other). ### Where can I find alternatives to ax or litellm? GraphCanon lists graph-backed alternatives at [ax alternatives](/tools/ax-llm-ax/alternatives) and [litellm alternatives](/tools/berriai-litellm/alternatives) ([ax markdown twin](/tools/ax-llm-ax/alternatives.md), [litellm markdown twin](/tools/berriai-litellm/alternatives.md)), ranked by typed relationship edges rather than popularity votes. ### Is there a machine-readable version of this comparison? Yes. The markdown twin at [this comparison](/compare/ax-llm-ax-vs-berriai-litellm.md) mirrors this page for agents and LLM crawlers, with the same stats table and FAQ answers. ### Which is better maintained, ax or litellm? ax: Very active. litellm: Very active. Compare maintenance labels, days since push, and release cadence in the trust section below - stars alone do not measure maintenance. ### Where are the full trust reports for ax and litellm? GraphCanon publishes per-repo trust reports with dated maintenance, provenance, and scan summaries: [ax trust report](/tools/ax-llm-ax/trust); [litellm trust report](/tools/berriai-litellm/trust). --- **Machine-readable endpoints** - JSON: [`/api/graphcanon/graph?tool=ax-llm-ax`](/api/graphcanon/graph?tool=ax-llm-ax) - LLM index: [/llms.txt](/llms.txt) - Full corpus: [/llms-full.txt](/llms-full.txt) _GraphCanon - The knowledge graph for AI development. https://www.graphcanon.com/_