Oossa

AI prices: what does each model cost?

See what AI models cost to use, find the ones that are free right now and check which open models can run on your own computer.

Updated October 22, 2026. Sources: OpenRouter and Hugging Face.

  • Cohere: North Mini Code (free)coherePrice per 1M tokens (in / out)Free1,000 chat answersFreeContext256K tokensOn your computer≈ 32 GB RAM
  • Google: Gemma 4 26B A4B (free)googlePrice per 1M tokens (in / out)Free1,000 chat answersFreeContext262K tokensOn your computer≈ 32 GB RAM
  • Google: Gemma 4 31B (free)googlePrice per 1M tokens (in / out)Free1,000 chat answersFreeContext262K tokensOn your computer≈ 32 GB RAM
  • LiquidAI: LFM2.5-2.6B (free)liquidPrice per 1M tokens (in / out)Free1,000 chat answersFreeContext66K tokensOn your computer≈ 8 GB RAM
  • NVIDIA: Nemotron 3 Nano Omni (free)nvidiaPrice per 1M tokens (in / out)Free1,000 chat answersFreeContext256K tokensOn your computer≈ 32 GB RAM
  • NVIDIA: Nemotron 3 Super (free)nvidiaPrice per 1M tokens (in / out)Free1,000 chat answersFreeContext262K tokensOn your computer≈ 128 GB RAM
  • NVIDIA: Nemotron 3.5 Content Safety (free)nvidiaPrice per 1M tokens (in / out)Free1,000 chat answersFreeContext128K tokensOn your computer≈ 8 GB RAM
  • NVIDIA: Nemotron 3.5 Lightning (free)nvidiaPrice per 1M tokens (in / out)Free1,000 chat answersFreeContext1000K tokensOn your computer≈ 32 GB RAM
  • Poolside: Laguna S 2.1 (free)poolsidePrice per 1M tokens (in / out)Free1,000 chat answersFreeContext262K tokensOn your computer≈ 128 GB RAM
  • Poolside: Laguna XS 2.1 (free)poolsidePrice per 1M tokens (in / out)Free1,000 chat answersFreeContext262K tokensOn your computer≈ 32 GB RAM
  • Recursive: Flint (free)recursivePrice per 1M tokens (in / out)Free1,000 chat answersFreeContext262K tokensOn your computer≈ 32 GB RAM
  • XingChen: Xing4.0 29B A4B (free)xingchen-agiPrice per 1M tokens (in / out)Free1,000 chat answersFreeContext262K tokensOn your computer≈ 32 GB RAM
  • Mistral: Mistral NemomistralaiPrice per 1M tokens (in / out)$0.029 / $0.031,000 chat answers$0.03Context131K tokensOn your computer≈ 16 GB RAM
  • inclusionAI: Ling 3.0 FlashinclusionaiPrice per 1M tokens (in / out)$0.021 / $0.0631,000 chat answers$0.042Context262K tokensOn your computer≈ 128 GB RAM
  • Google: Gemma 3 4BgooglePrice per 1M tokens (in / out)$0.04 / $0.051,000 chat answers$0.045Context131K tokensOn your computer≈ 8 GB RAM
  • Sao10K: Llama 3 8B Lunarissao10kPrice per 1M tokens (in / out)$0.04 / $0.051,000 chat answers$0.045Context8K tokensOn your computer≈ 8 GB RAM
  • OpenAI: gpt-oss-20bopenaiPrice per 1M tokens (in / out)$0.018 / $0.091,000 chat answers$0.054Context131K tokensOn your computer≈ 16 GB RAM
  • Nex AGI: Nex-N2.5-Mininex-agiPrice per 1M tokens (in / out)$0.025 / $0.101,000 chat answers$0.063Context262K tokensOn your computer≈ 32 GB RAM
  • IBM: Granite 4.0 Microibm-granitePrice per 1M tokens (in / out)$0.017 / $0.111,000 chat answers$0.065Context131K tokensOn your computer≈ 8 GB RAM
  • Meta: Llama 3.1 8B Instructmeta-llamaPrice per 1M tokens (in / out)$0.05 / $0.081,000 chat answers$0.065Context131K tokensOn your computer≈ 8 GB RAM
  • Mistral: Mistral Small 3mistralaiPrice per 1M tokens (in / out)$0.05 / $0.081,000 chat answers$0.065Context33K tokensOn your computer≈ 32 GB RAM
  • OpenAI: gpt-oss-20b (batch)openaiPrice per 1M tokens (in / out)$0.024 / $0.111,000 chat answers$0.068Context131K tokensOn your computer≈ 16 GB RAM
  • Mistral: Ministral 3 8B 2512 (batch)mistralaiPrice per 1M tokens (in / out)$0.075 / $0.0751,000 chat answers$0.075Context262K tokensOn your computer≈ 8 GB RAM
  • OpenAI: gpt-oss-120b (batch)openaiPrice per 1M tokens (in / out)$0.03 / $0.141,000 chat answers$0.083Context131K tokensOn your computer≈ 128 GB RAM
  • Poolside: Laguna XS 2.1poolsidePrice per 1M tokens (in / out)$0.06 / $0.121,000 chat answers$0.09Context262K tokensOn your computer≈ 32 GB RAM
  • Google: Gemma 3 12BgooglePrice per 1M tokens (in / out)$0.05 / $0.151,000 chat answers$0.10Context131K tokensOn your computer≈ 16 GB RAM
  • Mistral: Ministral 3 3B 2512mistralaiPrice per 1M tokens (in / out)$0.10 / $0.101,000 chat answers$0.10Context131K tokensOn your computer≈ 8 GB RAM
  • Reka EdgerekaaiPrice per 1M tokens (in / out)$0.10 / $0.101,000 chat answers$0.10Context16K tokensOn your computer≈ 8 GB RAM
  • Microsoft: Phi 4microsoftPrice per 1M tokens (in / out)$0.07 / $0.141,000 chat answers$0.11Context16K tokensOn your computer≈ 16 GB RAM
  • Qwen: Qwen3.5-9BqwenPrice per 1M tokens (in / out)$0.08 / $0.131,000 chat answers$0.11Context262K tokensOn your computer≈ 16 GB RAM
  • Tencent: Hy-MT2-1.8BtencentPrice per 1M tokens (in / out)$0.044 / $0.181,000 chat answers$0.11Context8K tokensOn your computer≈ 8 GB RAM
  • Meta: Llama 3.2 1B Instructmeta-llamaPrice per 1M tokens (in / out)$0.027 / $0.201,000 chat answers$0.11Context60K tokensOn your computer≈ 8 GB RAM
  • inclusionAI: Ling 3.0 Flash VLinclusionaiPrice per 1M tokens (in / out)$0.06 / $0.181,000 chat answers$0.12Context131K tokensOn your computer≈ 128 GB RAM
  • NVIDIA: Nemotron 3.5 LightningnvidiaPrice per 1M tokens (in / out)$0.07 / $0.201,000 chat answers$0.14Context262K tokensOn your computer≈ 32 GB RAM
  • Poolside: Laguna S 2.1poolsidePrice per 1M tokens (in / out)$0.09 / $0.181,000 chat answers$0.14Context1049K tokensOn your computer≈ 128 GB RAM
  • ByteDance: UI-TARS 7B bytedancePrice per 1M tokens (in / out)$0.10 / $0.201,000 chat answers$0.15Context128K tokensOn your computer≈ 8 GB RAM
  • Mistral: Ministral 3 8B 2512mistralaiPrice per 1M tokens (in / out)$0.15 / $0.151,000 chat answers$0.15Context262K tokensOn your computer≈ 8 GB RAM
  • NVIDIA: Nemotron 3 Nano 30B A3BnvidiaPrice per 1M tokens (in / out)$0.06 / $0.241,000 chat answers$0.15Context262K tokensOn your computer≈ 32 GB RAM
  • Qwen: Qwen2.5 7B InstructqwenPrice per 1M tokens (in / out)$0.10 / $0.201,000 chat answers$0.15Context33K tokensOn your computer≈ 8 GB RAM
  • Reka Flash 3rekaaiPrice per 1M tokens (in / out)$0.10 / $0.201,000 chat answers$0.15Context66K tokensOn your computer≈ 16 GB RAM

1 million tokens is roughly 750,000 English words. A chat answer is counted as 500 tokens in and 500 out. Prices are API prices in US dollars via OpenRouter; apps such as ChatGPT or Claude have their own subscriptions.

RAM estimate for a 4-bit (Q4) version of the open model. Models with many experts still need memory for all parameters.

Free models often have usage limits and some providers may use your prompts for training. Check the terms before you send anything private.