Cost · best for
Top picks for Self-Hosted / Local (2026)
Open-weights models you can run yourself. Ranked from 352 live models on the OpenRouter catalog, weighted for low cost.
What this is
A capability-matched shortlist, not a benchmark-tested winner. Models are scored by the fit of their declared specs (structured output, reasoning, context, modality, price) against Self-Hosted / Local. Pair with benchmark sources like Artificial Analysis or LMSys Arena before you ship. Full methodology →
| # | Model | Score | In / 1M | Out / 1M | Context | |
|---|---|---|---|---|---|---|
| 1 | Google: Gemma 4 26B A4B (free)google/gemma-4-26b-a4b-it:free | 118 | Free | Free | 262,144 | Details → |
| 2 | Google: Gemma 4 31B (free)google/gemma-4-31b-it:free | 118 | Free | Free | 262,144 | Details → |
| 3 | Google: Gemma 4 26B A4B google/gemma-4-26b-a4b-it | 117 | $0.06 | $0.33 | 262,144 | Details → |
| 4 | Qwen: Qwen3.5-9Bqwen/qwen3.5-9b | 117 | $0.10 | $0.15 | 262,144 | Details → |
| 5 | Qwen: Qwen3.5-Flashqwen/qwen3.5-flash-02-23 | 117 | $0.07 | $0.26 | 1,000,000 | Details → |
| 6 | ByteDance Seed: Seed 1.6 Flashbytedance-seed/seed-1.6-flash | 117 | $0.07 | $0.30 | 262,144 | Details → |
| 7 | OpenAI: GPT-5 Nanoopenai/gpt-5-nano | 117 | $0.05 | $0.40 | 400,000 | Details → |
| 8 | Google: Gemini 2.0 Flash Litegoogle/gemini-2.0-flash-lite-001 | 117 | $0.07 | $0.30 | 1,048,576 | Details → |
| 9 | Google: Gemma 4 31Bgoogle/gemma-4-31b-it | 117 | $0.13 | $0.38 | 262,144 | Details → |
| 10 | Mistral: Mistral Small 4mistralai/mistral-small-2603 | 117 | $0.15 | $0.60 | 262,144 | Details → |
| 11 | ByteDance Seed: Seed-2.0-Minibytedance-seed/seed-2.0-mini | 117 | $0.10 | $0.40 | 262,144 | Details → |
| 12 | xAI: Grok 4.1 Fastx-ai/grok-4.1-fast | 117 | $0.20 | $0.50 | 2,000,000 | Details → |
| 13 | Google: Gemini 2.5 Flash Lite Preview 09-2025google/gemini-2.5-flash-lite-preview-09-2025 | 117 | $0.10 | $0.40 | 1,048,576 | Details → |
| 14 | xAI: Grok 4 Fastx-ai/grok-4-fast | 117 | $0.20 | $0.50 | 2,000,000 | Details → |
| 15 | Google: Gemini 2.5 Flash Litegoogle/gemini-2.5-flash-lite | 117 | $0.10 | $0.40 | 1,048,576 | Details → |
How we ranked these
For Self-Hosted / Local, we weight models on low cost. Higher means better. Scores combine each model's public metadata (context length, modality support, tool calling, structured output, reasoning capability) with live pricing. See full methodology →