Open source AI models
375 open-weight models you can download or call through any host, ranked by quality.
/
| $10/1Mvia AIHubMix | 256K | $2.50/1M | $10/1M | — | Mar 11, 2025 | ||
| $1.50/1Mvia OpenRouter | 192K | $0.30/1M | $1.50/1M | — | May 11 | ||
| $2/1Mvia AIHubMix | — | $1/1M | $2/1M | — | Apr 7, 2023 | ||
| $0.60/1Mvia OpenRouter | 128K | $0.15/1M | $0.60/1M | — | Aug 19, 2024 | ||
| $10/1Mvia Cohere | 128K | $2.50/1M | $10/1M | — | Aug 21, 2024 | ||
| $0.15/1Mvia OpenRouter | 128K | $0.037/1M | $0.15/1M | — | Dec 11, 2024 | ||
| Free/1Mvia Nvidia | — | Free/1M | Free/1M | — | Dec 12, 2025 | ||
| TCydonia 24B V4.1ThedrummerOpen weightsPrompt caching+1 | $0.50/1Mvia OpenRouter | 131K | $0.30/1M | $0.50/1M | — | Aug 17, 2025 | |
| Free/1Mvia Vercel AI Gateway | 262K | $0.01/1M | Free/1M | — | Oct 15 | ||
| $0.308/1Mvia APIMart | 164K | $0.206/1M | $0.308/1M | — | Dec 1, 2025 | ||
| Free/1Mvia Nvidia | — | Free/1M | Free/1M | — | Oct 29, 2023 | ||
| $0.16/1Mvia AIHubMix | — | $0.16/1M | $0.16/1M | — | Nov 29, 2023 | ||
| $0.03/1Mvia Jiekou.AI | — | $0.03/1M | $0.03/1M | — | Jan 27 | ||
| $0.10/1Mvia AIHubMix | — | $0.10/1M | $0.10/1M | — | Apr 30, 2025 | ||
| $1.23/1Mvia APIMart | 164K | $0.408/1M | $1.23/1M | — | May 28, 2025 | ||
| $0.09/1Mvia Novita AI | — | $0.06/1M | $0.09/1M | — | May 29, 2025 | ||
| $0.13/1Mvia Helicone | 32K | $0.03/1M | $0.13/1M | — | Jan 20, 2025 | ||
| $0.01/1Mvia AIHubMix | — | $0.01/1M | $0.01/1M | — | Jan 20, 2025 | ||
| $0.01/1Mvia AIHubMix | — | $0.01/1M | $0.01/1M | — | Jan 20, 2025 | ||
| $0.10/1Mvia AIHubMix | — | $0.10/1M | $0.10/1M | — | Jan 20, 2025 | ||
| $2.20/1Mvia AIHubMix | — | $2.20/1M | $2.20/1M | — | Jan 20, 2025 | ||
| $0.32/1Mvia AIHubMix | — | $0.16/1M | $0.32/1M | — | Apr 22, 2024 | ||
| $0.32/1Mvia AIHubMix | — | $0.16/1M | $0.32/1M | — | Sep 5, 2024 | ||
| $1.14/1Mvia OpenRouter | 164K | $0.29/1M | $1.14/1M | — | Mar 24, 2025 | ||
| $0.822/1Mvia APIMart | 128K | $0.206/1M | $0.822/1M | — | Mar 24, 2025 | ||
| $0.95/1Mvia Hugging Face | 164K | $0.27/1M | $0.95/1M | — | Sep 22, 2025 | ||
| $0.48/1Mvia CometAPI | 1.05M | $0.12/1M | $0.48/1M | — | Aug 31 | ||
| $1.58/1Mvia CometAPI | 1M | $0.66/1M | $1.98/1M | — | Apr 22 | ||
| $0.16/1Mvia AIHubMix | — | $0.16/1M | $0.16/1M | — | Dec 13, 2024 | ||
| $0.02/1Mvia AIHubMix | 8K | $0.02/1M | $0.02/1M | — | Oct 17, 2025 | ||
| $0.798/1Mvia Poe | 164K | $0.212/1M | $0.798/1M | — | Aug 21, 2025 | ||
| $0.308/1Mvia APIMart | 164K | $0.206/1M | $0.308/1M | — | Sep 29, 2025 | ||
| $1.68/1Mvia Impossibl | — | $0.58/1M | $1.68/1M | — | Nov 28, 2025 | ||
| Free/1Mvia Nvidia | — | Free/1M | Free/1M | — | Apr 3, 2023 | ||
| Free/1Mvia Nvidia | — | Free/1M | Free/1M | — | Jun 9 | ||
| $0.28/1Mvia Helicone | — | $0.07/1M | $0.28/1M | — | Sep 8, 2025 | ||
| $0.03/1Mvia Helicone | — | $0.01/1M | $0.03/1M | — | Jun 24, 2024 | ||
| $0.20/1Mvia AIHubMix | — | $0.20/1M | $0.20/1M | — | Jun 3, 2025 | ||
| $0.10/1Mvia AIHubMix | — | $0.10/1M | $0.10/1M | — | Feb 13, 2024 | ||
Gemma SEA-LION v4 27BAI SingaporeGemma | $0.40/1Mvia Hugging Face | — | $0.20/1M | $0.40/1M | — | Aug 11, 2025 | |
| $0.05/1Mvia AIHubMix | — | $0.05/1M | $0.05/1M | — | Apr 7, 2025 | ||
| $0.04/runvia WaveSpeedAI | — | — | $0.04/run | — | Oct 9, 2025 | ||
| $0.04/imgvia Fal | — | — | $0.04/img | — | Jan 4 | ||
| $0.036/imgvia Fal | — | — | $0.036/img | — | Nov 27, 2025 | ||
| FLUX 2 Klein Base 9BBlack Forest LabsNon-commercial | $0.015/runvia WaveSpeedAI | — | — | $0.015/run | — | Jan 14 | |
| FLUX.1 Krea [dev]Black Forest LabsNon-commercial | $0.025/MPvia Fal | — | — | $0.025/MP | — | Jul 7, 2025 | |
| $0.20/videovia Fal | — | — | $0.20/video | — | Aug 17, 2024 | ||
| $0.05/secvia Fal | — | — | $0.05/sec | — | Mar 10 | ||
| Faster Whisper Large v3OpenAIApache 2.0 | $0.002/minvia Together AI | 0K | — | $0.002/min | — | Nov 7, 2023 | |
| $0.001/GPU-secvia Fal | — | — | $0.001/GPU-sec | — | Jun 15, 2024 |
Frequently asked questions
Ranked here by quality. Open models now trail the best closed ones by little, and the hosts that serve them often charge much less.
Most "open source" models publish their weights under a license, but not their training data. We list every model whose weights you can download.
On your own hardware, or through inference hosts that charge per token. Open a model's providers to compare each host's price, speed and uptime.
Can't find what you're looking for? Contact us
