StarCoder
Open source code-generation model from the BigCode project, trained on 80+ programming languages.
Pricing Open sourceOpen source yesStars 7.5k
Anthropic Claude alternatives
9 tools you can use instead of Anthropic Claude, ranked by live GitHub stars and npm downloads. StarCoder, Gemma 4 and DeepSeek V4 are the most used. Stats updated 5 hours ago.
Gemini 3.1 Pro and Mistral Large 3 are the closest alternatives among hosted proprietary models. If you need to run a model on your own hardware, DeepSeek V4 and Gemma 4 are open-weight.
When Anthropic Claude is not a good fit
Claude is Anthropic's family of large language models, offered through the Claude apps (web, desktop and mobile), the pay-per-token Claude API, and major cloud platforms including Amazon Bedrock and Google Cloud Vertex AI. As of September 2026 the current models are Claude Fable 5.1, Opus 5.5, Sonnet 5 and Haiku 4.5, each at a different price and speed point, with Fable 5.1, Opus 5.5 and Sonnet 5 supporting up to 1 million tokens of context.
It is a weaker choice for:
- Running a model on your own hardware, since Anthropic doesn't release open-weight models
- Image or video generation, since Claude reads images but doesn't create them
- Fixed, predictable costs at high volume, since API spend grows with tokens used
The alternatives
Most used first.
View StarCoder
Gemma 4
Google DeepMind's current generation of lightweight, open-weight language models.
Pricing Open sourceOpen source noStars 5.8k
DeepSeek V4
DeepSeek's current open-weight model family, including V4.1-Flash and V4-Pro.
Pricing Open sourcePaid from $0.15 per million input tokens off-peak (V4.1-Flash, cache miss)Open source yes
Devstral
Mistral AI's open-weight model built specifically for coding and software engineering agents.
Pricing Open sourcePaid from Priced per million tokens via Mistral's API; see Mistral's pricing page for current ratesOpen source yes
Gemini 3.1 Pro
Google's third-generation Gemini Pro model, currently in preview, for complex reasoning tasks.
Pricing Pay as you goPaid from $2.00 per million input tokens (up to 200k tokens)Open source no
GPT-5.3 Codex
OpenAI's specialized coding model, priced separately from its general-purpose GPT models.
Pricing Pay as you goPaid from $1.75 per million input tokens (standard mode)Open source no
Jev
TypeSafe AI's System One model: returns typed decisions with probabilities instead of text.
Pricing Pay as you goPaid from $0.042 per million input tokens; output tokens are freeOpen source no
Meta Muse Spark
Meta's proprietary flagship AI model, its first major release since the Llama line.
Pricing Pay as you goPaid from Priced per million tokens via API partners; check current provider pricingOpen source no
Mistral Large 3
Mistral AI's flagship large language model for complex reasoning and general-purpose tasks.
Pricing Pay as you goPaid from Around $0.50 per million input tokens (Mistral Large tier, per Mistral's example pricing)Open source no
Anthropic Claude and its alternatives, side by side
| Tool | Pricing | Free plan | Paid from | Open source | GitHub stars |
|---|---|---|---|---|---|
| Anthropic Claude | Pay as you go | Yes, in the Claude apps; the API has no free tier and is billed per token | $20 a month for Claude Pro; API from $1 input per million tokens on Haiku 4.5 | No | 2.1k |
| StarCoder | Open source | Yes, free to download and use, subject to accepting the OpenRAIL-M license terms | Not listed | Yes, BigCode OpenRAIL-M | 7.5k |
| Gemma 4 | Open source | Yes, weights are free to download and run | Not listed | No | 5.8k |
| DeepSeek V4 | Open source | Yes, open-weight models free to download and self-host; API access is pay-as-you-go | $0.15 per million input tokens off-peak (V4.1-Flash, cache miss) | Yes, MIT (weights and code) | None |
| Devstral | Open source | Yes, open-weight model free to download and self-host; API access is pay-as-you-go | Priced per million tokens via Mistral's API; see Mistral's pricing page for current rates | Yes, Apache-2.0 | None |
| Gemini 3.1 Pro | Pay as you go | Limited free access is available through Google AI Studio and Gemini app tiers | $2.00 per million input tokens (up to 200k tokens) | No | None |
| GPT-5.3 Codex | Pay as you go | No free tier for API access; usable through ChatGPT plans with usage limits | $1.75 per million input tokens (standard mode) | No | None |
| Jev | Pay as you go | Not stated on the official site. Usage is billed per input token. | $0.042 per million input tokens; output tokens are free | No | None |
| Meta Muse Spark | Pay as you go | Access is available through Meta AI's consumer products with usage limits | Priced per million tokens via API partners; check current provider pricing | No | None |
| Mistral Large 3 | Pay as you go | Limited free access is available through La Plateforme's free tier | Around $0.50 per million input tokens (Mistral Large tier, per Mistral's example pricing) | No | None |
Pricing facts come from each tool's official pricing page, with the checked date on the tool's own page.
Questions
What is the most popular alternative to Anthropic Claude?
By GitHub stars, StarCoder is the most used alternative to Anthropic Claude listed on ScratchDB, with 7.5k stars.
Which Anthropic Claude alternatives are open source?
StarCoder, DeepSeek V4 and Devstral are open source.
Which Anthropic Claude alternatives have a free plan?
StarCoder, Gemma 4, DeepSeek V4 and Devstral have a free plan. The table on this page shows what each one includes.