Open source AI models
375 open-weight models you can download or call through any host, ranked by quality.
/
| Kimi K3Moonshot AIOpen weights · with termsPrompt caching+4 | $8.28/1Mvia Kenari | 1.05M | $2.78/1M | $13.89/1M | 658K | Jun 13 | |
 GLM-5.3Zhipu AIOpen weights · with termsPrompt caching+3 | $1.10/1Mvia NanoGPT | 1.05M | $1.40/1M | $4.40/1M | 276K | Aug 25 | |
 Qwen3.8 2.4T A95BAlibabaOpen weights · with termsPrompt caching+3 | $4.11/1Mvia APIMart | 1M | $2/1M | $6/1M | 234K | Aug 8 | |
 DeepSeek V4.1 FlashDeepSeekMITPrompt caching+4 | $0.03/1Mvia UnoRouter | 1.05M | $0.007/1M | $0.03/1M | 138K | Sep 10 | |
| GLM-5.3-FlashZhipu AIMITPrompt caching+4 | $0.20/1Mvia APIMart | 1.05M | $0.15/1M | $0.50/1M | 121K | Aug 25 | |
| Qwen3.8 27BAlibabaApache 2.0Prompt caching+4 | $0.50/1Mvia EmpirioLabs AI | 262K | $0.50/1M | $3/1M | 120K | Aug 5 | |
| GLM-5.2Zhipu AIMITPrompt caching+3 | $1.80/1Mvia Deep Infra | 1M | $1.40/1M | $4.40/1M | 109K | Jun 16 | |
| Qwen3.8 Flash NextAlibabaOpen weights · with termsPrompt caching+4 | $0.376/1Mvia CometAPI | 262K | $0.12/1M | $0.376/1M | 63K | Aug 24 | |
| DeepSeek V4 FlashDeepSeekMITPrompt caching+3 | $0.17/1Mvia Opper | 1.05M | $0.07/1M | $0.17/1M | 51K | Apr 22 | |
| DeepSeek V4 Flash Vision ExpDeepSeekMITPrompt caching+4 | $0.294/1Mvia Deep Infra | 1.05M | $0.15/1M | $0.60/1M | 47K | Oct 17 | |
| DeepSeek V4 ProDeepSeekMITPrompt caching+3 | $0.418/1Mvia OpenRouter | 1.05M | $0.209/1M | $0.418/1M | 40K | Apr 22 | |
 Ling 3.1 FlashInclusionaiMITPrompt caching+2 | $0.225/1Mvia Deep Infra | 262K | $0.075/1M | $0.225/1M | 38K | Oct 13 | |
| Qwen2-1.5B-InstructAlibabaApache 2.0 | $0.20/1Mvia AIHubMix | — | $0.20/1M | $0.20/1M | 37K | Jun 3, 2024 | |
| GPT OSS 120BOpenAIApache 2.0Prompt caching+3 | $0.14/1Mvia Requesty | 131K | $0.032/1M | $0.14/1M | 35K | Aug 4, 2025 | |
| Qwen3 1.7BAlibabaApache 2.0 | $0.46/1Mvia AIHubMix | — | $0.046/1M | $0.46/1M | 33K | Apr 27, 2025 | |
 MiniMax-M3.1-FlashMiniMaxOpen weights · with termsPrompt caching+4 | $0.45/1Mvia EmpirioLabs AI | 1.05M | $0.15/1M | $0.60/1M | 29K | Oct 17 | |
| Kimi K2 InstructMoonshot AIOpen weights · with termsTool calling | $1.68/1Mvia APIMart | 131K | $0.40/1M | $1.68/1M | 26K | Jul 11, 2025 | |
| MiniMax-M3MiniMaxOpen weights · with termsPrompt caching+4 | $0.90/1Mvia EmpirioLabs AI | 1M | $0.30/1M | $1.20/1M | 26K | Jun 2 | |
| GLM-5Zhipu AIMITPrompt caching+3 | $1.28/1Mvia APIMart | 205K | $1/1M | $3.20/1M | 23K | Feb 11 | |
| DeepSeek R1DeepSeekMITReasoning+1 | $1.79/1Mvia APIMart | 164K | $0.448/1M | $1.79/1M | 22K | Jan 20, 2025 | |
| Kimi K2.5Moonshot AIOpen weights · with termsPrompt caching+4 | $0.555/1Mvia APIMart | 262K | $0.411/1M | $0.555/1M | 22K | Jan 1 | |
 Gemma 4 31BGoogleApache 2.0Prompt caching+1 | $0.404/1Mvia Poe | 262K | $0.151/1M | $0.404/1M | 20K | Mar 12 | |
| Qwen3.5 9BAlibabaApache 2.0Prompt caching+4 | $0.13/1Mvia EmpirioLabs AI | 262K | $0.09/1M | $0.13/1M | 19K | Feb 27 | |
| Gemma 2 27BGoogleGemmaJSON | $0.65/1Mvia OpenRouter | 8K | $0.65/1M | $0.65/1M | 14K | Jun 24, 2024 | |
| GPT OSS 20BOpenAIApache 2.0JSON+2 | $0.09/1Mvia OpenRouter | 131K | $0.018/1M | $0.09/1M | 12K | Aug 4, 2025 | |
| Qwen3 8BAlibabaApache 2.0 | $0.06/1Mvia SiliconFlow | — | $0.06/1M | $0.06/1M | 12K | Apr 27, 2025 | |
| Qwen3.6 35B-A3BAlibabaApache 2.0Prompt caching+4 | $0.95/1Mvia Deep Infra | 262K | $0.375/1M | $2.25/1M | 11K | Apr 15 | |
| Kimi K2.6Moonshot AIOpen weights · with termsPrompt caching+4 | $2.40/1Mvia APIYI | 262K | $0.903/1M | $3.75/1M | 11K | Apr 14 | |
 MiMo-V2.5XiaomiMITPrompt caching+4 | $0.224/1Mvia CometAPI | 1.05M | $0.112/1M | $0.224/1M | 10K | Apr 27 | |
| GLM OCRZhipu AIMITVision | $0.028/1Mvia AIHubMix | 32K | $0.03/1M | $0.03/1M | 10K | Jan 30 | |
| Gemma 4 E2B ITGoogleApache 2.0 | $0.08/1Mvia Amazon Bedrock | — | $0.04/1M | $0.08/1M | 10K | Mar 2 | |
| Qwen3-4BAlibabaApache 2.0 | $0.03/1Mvia Hugging Face | — | $0.01/1M | $0.03/1M | 10K | Apr 27, 2025 | |
| Qwen2-7B-InstructAlibabaApache 2.0 | $0.08/1Mvia AIHubMix | — | $0.08/1M | $0.08/1M | 9K | Jun 4, 2024 | |
| DeepSeek V3DeepSeekOpen weightsReasoning+1 | $0.89/1Mvia Deep Infra | 64K | $0.32/1M | $0.89/1M | 9K | Dec 25, 2024 | |
| MiniMax M2.5MiniMaxOpen weights · with termsPrompt caching+3 | $0.95/1Mvia Venice AI | 205K | $0.27/1M | $0.95/1M | 9K | Feb 12 | |
| Qwen3-Coder-NextAlibabaApache 2.0JSON+1 | $0.548/1Mvia AIHubMix | 262K | $0.137/1M | $0.548/1M | 8K | Jan 30 | |
| Qwen-Image-2.1AlibabaNon-commercial | $0.02/imgvia Kie.ai | — | — | $0.02/img | 270K | Sep 14 | |
| Z Image TurboAlibabaApache 2.0 | $0.005/imgvia Atlas Cloud | — | — | $0.005/img | 35K | Nov 25, 2025 | |
| Qwen Image EditAlibabaApache 2.0 | $0.03/imgvia Replicate | — | — | $0.03/img | 29K | Aug 17, 2025 | |
| Qwen Image 2.1 TurboAlibabaNon-commercial | $0.014/imgvia AIHubMix | — | — | $0.014/img | 24K | Oct 9 | |
| Z ImageAlibabaApache 2.0 | $0.005/runvia WaveSpeedAI | — | — | $0.005/run | 20K | Jan 23 | |
| FLUX 3 Image KleinBlack Forest LabsOpen weights · with terms | $0.007/imgvia APIMart | — | — | $0.007/img | 16K | Oct 13 | |
| FLUX.1-schnellBlack Forest LabsApache 2.0 | $0.003/MPvia Fal | — | — | $0.003/MP | 10K | Jul 31, 2024 | |
| FLUX 2 Klein Base 4BBlack Forest LabsApache 2.0 | $0.01/runvia WaveSpeedAI | — | — | $0.01/run | 10K | Jan 14 | |
| FLUX.2 Klein 4BBlack Forest LabsApache 2.0Vision | $0.008/runvia WaveSpeedAI | 128K | — | $0.008/run | 10K | Jan 14 | |
| MiniMax H3MiniMaxOpen weights · with termsVision | $0.02/secvia WaveSpeedAI | 13K | — | $0.08/sec | 582K | Jul 28 | |
| LTX 2.5LightricksOpen weights · with terms | $0.10/runvia WaveSpeedAI | — | — | $0.10/run | 91K | Jul 23 | |
| LTX 2.3LightricksOpen weights · with terms | $0.03/secvia WaveSpeedAI | — | — | $0.03/sec | 25K | Mar 4 | |
 Stable Audio 3Stability AIOpen weights · with terms | $0.038/runvia Fal | — | — | $0.038/run | 10K | May 17 | |
| BGE M3BAAIMIT | $0.01/1Mvia APIYI | — | $0.01/1M | $0.01/1M | 17K | Jan 27, 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