Open-weight models, serverless or dedicated
Call 5 models per token right now, or run any of 284 open-weight models on GPUs reserved for you. Pricing and specs are generated from the live catalog and Hugging Face, so they never drift.
Serverless
Pay per token, no commitment. 5 models from $0.20 / 1M input, up to 1M context.
Artificial Analysis Intelligence Index v4.3 (0–100), measured across all providers by Artificial Analysis, not sference specifically. Blended price weights input and output 3:1. Source
zai-org/GLM-5.3Z.AI's current-generation frontier model: 1M context, thinking, tool calling, and the strongest coding scores in the Z.AI line-up, per its maker and independent benchmarking.
deepseek-ai/DeepSeek-V4.1-Flash-1017DeepSeek's fast tier with vision input: 1M context and the best price-to-throughput ratio in the sference catalog for vision-capable workloads.
zai-org/GLM-5.3-FlashThe fast, cheap tier of Z.AI's GLM 5.3 family: 1M context with vision and thinking, tuned for high-volume interactive traffic where cost per token dominates.
deepseek-ai/DeepSeek-V4-Flash-0731DeepSeek's fast, low-cost text tier, the 0731 release of V4 Flash: 1M context, thinking, and tool calling for high-volume, cost-sensitive workloads.
Cloudflare/clefA 27B decisions model for realtime classification, routing, and scoring: up to 64 questions answered about one input in a single call, billed on input tokens only.
Decisions models answer questions about an input (classify, route, score) and return probabilities instead of generated text. Billed on input tokens only.
Dedicated deployments
284 open-weight models we deploy on GPU capacity reserved for you, with a private endpoint, billed per GPU-hour. Models tagged serverless are also available per token above. How dedicated works
| Model | Type | Params | Context | License |
|---|---|---|---|---|
| DeepSeek | Chat & reasoning | 763B | 1M | MIT |
| Z.ai | Chat & reasoning | 321B | 1M | MIT |
| Z.ai | Chat & reasoning | 753B | 1M | Custom license |
| Moonshot AI | Chat & reasoning | 2.78T | 1M | Custom license |
| DeepSeek | Chat & reasoning | 304B | 1M | MIT |
| Qwen | Chat & reasoning | 28B | 1M | Apache 2.0 |
| Qwen | Chat & reasoning | 180B | 1M | Custom license |
Kokoro-82Mtrending hexgrad | Text-to-speech | — | — | Apache 2.0 |
speaker-diarization-community-1trending pyannote | Speech recognition | — | — | CC BY 4.0 |
| Chat & reasoning | 31B | 256K | Apache 2.0 | |
bge-m3trending BAAI | Embeddings | — | 8K | MIT |
whisper-large-v3trending OpenAI | Speech recognition | 1.5B | — | Apache 2.0 |
whisper-large-v3-turbotrending OpenAI | Speech recognition | 809M | — | MIT |
| OpenAI | Chat & reasoning | 117B | 128K | Apache 2.0 |
| Qwen | Chat & reasoning | 36B | 256K | Apache 2.0 |
| Qwen | Chat & reasoning | 9.7B | 256K | Apache 2.0 |
| Moonshot AI | Chat & reasoning | 2.78T | 1M | Custom license |
embeddinggemma-2trending Google | Embeddings | 744M | 256K | Apache 2.0 |
gpt-oss-20bMoE OpenAI | Chat & reasoning | 21B | 128K | Apache 2.0 |
| Xiaomi MiMo | Chat & reasoning | 311B | 1M | MIT |
Qwen3-0.6Btrending Qwen | Chat & reasoning | 752M | 40K | Apache 2.0 |
| Chat & reasoning | 26B | 256K | Apache 2.0 | |
DeepSeek-R1MoE DeepSeek | Chat & reasoning | 684B | 160K | MIT |
| Chat & reasoning | 8.0B | 128K | Apache 2.0 | |
| Baidu | OCR & documents | 3.3B | 32K | MIT |
| Qwen | Text-to-speech | 1.9B | — | Apache 2.0 |
| DeepSeek | Chat & reasoning | 291B | 1M | MIT |
VoxCPM2trending OpenBMB | Text-to-speech | 2.3B | — | Apache 2.0 |
| Meta Muse | Chat & reasoning | 30B | 128K | Apache 2.0 |
| Chat & reasoning | 4.3B | 128K | Gemma Terms of Use | |
| Qwen | Chat & reasoning | 4.7B | 256K | Apache 2.0 |
| Embeddings | 303M | — | Gemma Terms of Use | |
| OpenBMB | Chat & reasoning | 2.5B | 128K | Apache 2.0 |
gemma-4-12B-itvision Google | Chat & reasoning | 12B | 256K | Apache 2.0 |
| Thinking Machines | Chat & reasoning | 952B | 512K | Apache 2.0 |
| MiniMax | Chat & reasoning | 220B | 1M | Custom license |
| DeepSeek | Chat & reasoning | 1.6T | 1M | MIT |
| Meta Llama | Chat & reasoning | 71B | 128K | Llama 3.3 Community License |
| Z.ai | Chat & reasoning | 753B | 1M | MIT |
| Resemble AI | Text-to-speech | — | — | MIT |
| Chat & reasoning | 5.1B | 128K | Apache 2.0 | |
| Z.ai | Chat & reasoning | 31B | 195K | MIT |
| Qwen | Coding | 31B | 256K | Apache 2.0 |
| Qwen | Speech recognition | 2.3B | — | Apache 2.0 |
| StepFun | Chat & reasoning | 604B | 1M | Custom license |
| DeepSeek | OCR & documents | 3.3B | 8K | MIT |
parakeet-tdt-0.6b-v3trending NVIDIA | Speech recognition | 627M | — | CC BY 4.0 |
nemotron-3.5-asr-streaming-0.6btrending NVIDIA | Speech recognition | 638M | — | OpenMDW 1.1 |
MiniCPM-o-4_5vision OpenBMB | Vision & multimodal | 9.4B | 40K | Apache 2.0 |
Qwen3.6-27Bvision Qwen | Chat & reasoning | 28B | 256K | Apache 2.0 |
Qwen3.5-0.8Bvision Qwen | Chat & reasoning | 873M | 256K | Apache 2.0 |
medgemma-4b-itvision Google | Chat & reasoning | 4.3B | — | Custom license |
| Microsoft | Speech recognition | 8.7B | — | MIT |
Qwen3-VL-8B-Instructvision Qwen | Vision & multimodal | 8.8B | 256K | Apache 2.0 |
| Qwen | Chat & reasoning | 8.2B | 40K | Apache 2.0 |
| Fish Audio | Text-to-speech | 4.6B | 32K | Custom license |
| Qwen | Chat & reasoning | 2.45T | 1M | Custom license |
| MiniMax | Chat & reasoning | 427B | 1M | Custom license |
| Chat & reasoning | 1000M | — | Gemma Terms of Use | |
| Qwen | Embeddings | 596M | 32K | Apache 2.0 |
| Microsoft | Text-to-speech | 1.0B | — | MIT |
| Moonshot AI | Chat & reasoning | 1.03T | 256K | Modified MIT |
| BAAI | Rerankers | 568M | 8K | Apache 2.0 |
| DeepSeek | Chat & reasoning | 685B | 160K | MIT |
| Moonshot AI | Chat & reasoning | 1.03T | 256K | Modified MIT |
| DeepSeek | OCR & documents | 3.4B | 8K | Apache 2.0 |
| Qwen | Coding | 80B | 256K | Apache 2.0 |
| Qwen | Chat & reasoning | 403B | 256K | Apache 2.0 |
| Microsoft | Text-to-speech | 2.7B | — | MIT |
| Qwen | Chat & reasoning | 2.0B | 40K | Apache 2.0 |
| Sesame | Text-to-speech | 1.6B | — | Apache 2.0 |
Laguna-S-2.1MoE poolside | Coding | 118B | 1M | OpenMDW 1.1 |
| Moonshot AI | Coding | 1.03T | 256K | Modified MIT |
| Qwen | Chat & reasoning | 4.0B | 256K | Apache 2.0 |
PaddleOCR-VLvision PaddlePaddle | OCR & documents | 959M | 128K | Apache 2.0 |
| Qwen | Vision & multimodal | 35B | — | Apache 2.0 |
| Tencent | Translation | 2.0B | 8K | Apache 2.0 |
granite-docling-258Mvision IBM | OCR & documents | 258M | 8K | Apache 2.0 |
| NVIDIA | Speech recognition | — | — | CC BY 4.0 |
Qwen3.5-2Bvision Qwen | Chat & reasoning | 2.3B | 256K | Apache 2.0 |
| Hugging Face | Chat & reasoning | 3.1B | 64K | Apache 2.0 |
| XingChen AGI | Chat & reasoning | 31B | 256K | Apache 2.0 |
| Cohere | Speech recognition | 2.1B | — | Apache 2.0 |
| Qwen | Embeddings | 7.6B | 40K | Apache 2.0 |
| Qwen | Chat & reasoning | 15B | 40K | Apache 2.0 |
| Meta Llama | Chat & reasoning | 109B | 1.3M | Llama 4 Community License |
| DeepSeek | Chat & reasoning | 8.2B | 128K | MIT |
Qwen3-VL-4B-Instructvision Qwen | Vision & multimodal | 4.4B | 256K | Apache 2.0 |
MiniCPM-V-4.6vision OpenBMB | Vision & multimodal | 1.3B | 256K | Apache 2.0 |
chandra-ocr-2vision Datalab | OCR & documents | 5.3B | 256K | Custom license |
| FunAudioLLM | Text-to-speech | — | — | Apache 2.0 |
gemma-3-27b-itvision Google | Chat & reasoning | 27B | 128K | Gemma Terms of Use |
| Xiaomi MiMo | Chat & reasoning | 1.02T | 1M | MIT |
| Moonshot AI | Chat & reasoning | 1.03T | 256K | Modified MIT |
MiniMax-M2.5MoE MiniMax | Chat & reasoning | 229B | 193K | Modified MIT |
| Qwen | Chat & reasoning | 125B | 256K | Apache 2.0 |
| Microsoft | Chat & reasoning | 3.8B | 128K | MIT |
Qwen2.5-Omni-7Bvision Qwen | Vision & multimodal | 11B | — | Apache 2.0 |
Hy3MoE Tencent | Chat & reasoning | 299B | 256K | Apache 2.0 |
| DeepSeek | Chat & reasoning | 1.65T | 1M | MIT |
PaddleOCR-VL-1.6vision PaddlePaddle | OCR & documents | 959M | 128K | Apache 2.0 |
| Meta Muse | Chat & reasoning | 822B | 1M | Custom license |
| Liquid AI | Chat & reasoning | 24B | 125K | Custom license |
gemma-3-12b-itvision Google | Chat & reasoning | 12B | 128K | Gemma Terms of Use |
LightOnOCR-2-1Bvision LightOn | OCR & documents | 1.0B | 16K | Apache 2.0 |
dots.ocrvision dots.ocr | OCR & documents | 3.0B | 128K | MIT |
Qwen3.5-27Bvision Qwen | Chat & reasoning | 28B | 256K | Apache 2.0 |
HunyuanOCRvision Tencent | OCR & documents | 1.1B | 128K | Custom license |
| Qwen | Chat & reasoning | 81B | 256K | Apache 2.0 |
| inclusionAI | Chat & reasoning | 7.9B | 256K | MIT |
| Nari Labs | Text-to-speech | 1.6B | — | Apache 2.0 |
| Qwen | Chat & reasoning | 33B | 128K | Apache 2.0 |
MiniMax-M2.7MoE MiniMax | Chat & reasoning | 229B | 192K | Custom license |
| OpenBMB | Vision & multimodal | 35B | 256K | Apache 2.0 |
Hy4-previewMoE Tencent | Chat & reasoning | 780B | 1M | Apache 2.0 |
| NVIDIA | Chat & reasoning | 561B | 1M | OpenMDW 1.1 |
| Qwen | Chat & reasoning | 31B | 40K | Apache 2.0 |
Kolibri-1MoE Aleph Alpha | Chat & reasoning | 78B | 256K | Apache 2.0 |
Qwen3-VL-2B-Instructvision Qwen | Vision & multimodal | 2.1B | 256K | Apache 2.0 |
| Qwen | Coding | 480B | 256K | Apache 2.0 |
| Resemble AI | Text-to-speech | — | — | MIT |
| Qwen | Chat & reasoning | 235B | 40K | Apache 2.0 |
| Qwen | Embeddings | 4.0B | 40K | Apache 2.0 |
| Qwen | Vision & multimodal | 31B | 256K | Apache 2.0 |
| DeepSeek | Chat & reasoning | 685B | 160K | MIT |
| Chat & reasoning | 268M | — | Gemma Terms of Use | |
| Meta Llama | Safety & moderation | 279M | — | Llama 4 Community License |
| Liquid AI | Chat & reasoning | 2.7B | 128K | Custom license |
| Thinking Machines | Chat & reasoning | 266B | 512K | Apache 2.0 |
GLM-5MoE Z.ai | Chat & reasoning | 754B | 200K | MIT |
moondream3-previewvision Moondream | Vision & multimodal | 9.3B | 31K | Custom license |
| Qwen | Embeddings | 2.1B | 256K | Apache 2.0 |
UI-TARS-1.5-7Bvision ByteDance Seed | Vision & multimodal | 8.3B | 125K | Apache 2.0 |
| Moonshot AI | Chat & reasoning | 1.03T | 128K | Modified MIT |
| Liquid AI | Chat & reasoning | 1.2B | 125K | Custom license |
| intfloat | Embeddings | 560M | 1K | MIT |
GLM-4.5-AirMoE Z.ai | Chat & reasoning | 110B | 128K | MIT |
| NVIDIA | Chat & reasoning | 32B | 1M | OpenMDW 1.1 |
| DeepSeek | Chat & reasoning | 685B | 160K | MIT |
| Kwaipilot | Coding | 35B | 256K | Apache 2.0 |
GLM-5.1MoE Z.ai | Chat & reasoning | 754B | 200K | MIT |
| Qwen | Embeddings | 8.1B | 256K | Apache 2.0 |
| Qwen | Chat & reasoning | 36B | 256K | Apache 2.0 |
| Microsoft | Embeddings | 596M | 32K | MIT |
| DeepSeek | Chat & reasoning | 685B | 160K | MIT |
| NVIDIA | Chat & reasoning | 8.9B | 128K | Custom license |
| Mistral AI | Speech recognition | 4.7B | 128K | Apache 2.0 |
| Swiss AI Initiative | Chat & reasoning | 8.1B | 64K | Apache 2.0 |
gemma-3n-E4B-itvision Google | Chat & reasoning | 7.8B | — | Gemma Terms of Use |
| IBM | Chat & reasoning | 8.8B | 128K | Apache 2.0 |
medgemma-27b-itvision Google | Chat & reasoning | 27B | — | Custom license |
| Qwen | Chat & reasoning | 33B | 40K | Apache 2.0 |
| poolside | Coding | 33B | 256K | OpenMDW 1.1 |
| Jina AI | Embeddings | 572M | 8K | CC BY-NC 4.0· non-commercial |
| Mistral AI | Chat & reasoning | 119B | 256K | Apache 2.0 |
| IndexTeam | Text-to-speech | — | — | Custom license |
GLM-4.7MoE Z.ai | Chat & reasoning | 358B | 200K | MIT |
| Reflection AI | Chat & reasoning | 501B | 1M | Apache 2.0 |
| Mistral AI | Text-to-speech | — | — | CC BY-NC 4.0· non-commercial |
| Qwen | Rerankers | 4.0B | 40K | Apache 2.0 |
| Mistral AI | Speech recognition | 4.4B | 128K | Apache 2.0 |
GLM-4.6V-Flashvision Z.ai | Vision & multimodal | 10B | 128K | MIT |
| Tencent | Translation | 30B | 8K | Apache 2.0 |
| Jina AI | Embeddings | 3.8B | 125K | Custom license |
GLM-4.5MoE Z.ai | Chat & reasoning | 358B | 128K | MIT |
MiniMax-M2MoE MiniMax | Chat & reasoning | 229B | 192K | Modified MIT |
| Microsoft | Vision & multimodal | 5.6B | 128K | MIT |
| Qwen | Rerankers | 596M | 40K | Apache 2.0 |
| Upstage | Chat & reasoning | 250B | 1M | Custom license |
| Meta Llama | Chat & reasoning | 402B | 512K | Llama 4 Community License |
| Jina AI | Embeddings | 1.6B | 32K | CC BY-NC 4.0· non-commercial |
| NVIDIA | Chat & reasoning | 32B | 256K | NVIDIA Nemotron Open Model License |
| Moonshot AI | Chat & reasoning | 49B | — | MIT |
| Tencent | Translation | 8.0B | 32K | Custom license |
| Mistral AI | Chat & reasoning | 8.9B | 256K | Apache 2.0 |
| Moonshot AI | Vision & multimodal | 16B | 128K | MIT |
| Qwen | Chat & reasoning | 31B | 256K | Apache 2.0 |
| DeepSeek | Chat & reasoning | 685B | 160K | Apache 2.0 |
| Qwen | Speech recognition | 938M | — | Apache 2.0 |
SmolVLM2-2.2B-Instructvision Hugging Face | Vision & multimodal | 2.2B | 8K | Apache 2.0 |
| NVIDIA | Embeddings | 1.1B | 256K | OpenMDW 1.1 |
| inclusionAI | Chat & reasoning | 127B | 256K | MIT |
| IBM | Embeddings | 48M | 8K | Apache 2.0 |
MiniMax-M2.1MoE MiniMax | Chat & reasoning | 229B | 192K | Modified MIT |
| Cohere | Coding | 30B | 250K | Apache 2.0 |
| LG AI Research | Chat & reasoning | 237B | 256K | Custom license |
| ZeroEntropy | Rerankers | 4.0B | 40K | Apache 2.0 |
| NVIDIA | Vision & multimodal | 33B | 250K | NVIDIA Open Model License |
| Mistral AI | Speech recognition | 24B | 32K | Apache 2.0 |
| StepFun | Chat & reasoning | 199B | 256K | Apache 2.0 |
| Kyutai | Text-to-speech | — | — | CC BY 4.0 |
GLM-4.6MoE Z.ai | Chat & reasoning | 357B | 200K | MIT |
Ling-1TMoE inclusionAI | Chat & reasoning | 1000B | 32K | MIT |
Qianfan-OCRvision Baidu | OCR & documents | 4.7B | 32K | Apache 2.0 |
| Baidu | Chat & reasoning | 22B | 128K | Apache 2.0 |
| Tencent | Chat & reasoning | 80B | 32K | Custom license |
| Qwen | Chat & reasoning | 235B | 256K | Apache 2.0 |
| Qwen | Rerankers | 2.1B | 256K | Apache 2.0 |
| Qwen | Chat & reasoning | 4.0B | 256K | Apache 2.0 |
| Z.ai | Speech recognition | 2.3B | 8K | MIT |
moondream3.1-9B-A2Bvision Moondream | Vision & multimodal | 9.3B | 31K | Custom license |
| Qwen | Rerankers | 8.2B | 40K | Apache 2.0 |
shieldgemma-2-4b-itvision Google | Safety & moderation | 4.3B | — | Gemma Terms of Use |
| Canopy Labs | Text-to-speech | 3.8B | — | Apache 2.0 |
GLM-4.1V-9B-Thinkingvision Z.ai | Vision & multimodal | 10B | 64K | MIT |
Nanonets-OCR2-3Bvision Nanonets | OCR & documents | 3.8B | 125K | Custom license |
| Mistral AI | Chat & reasoning | 24B | 250K | Apache 2.0 |
| Liquid AI | Chat & reasoning | 8.5B | 125K | Custom license |
| Qwen | Safety & moderation | 8.2B | 32K | Apache 2.0 |
| Nomic | Embeddings | 475M | — | Apache 2.0 |
| Alibaba NLP | Chat & reasoning | 31B | 128K | Apache 2.0 |
| NVIDIA | Chat & reasoning | 124B | 256K | NVIDIA Nemotron Open Model License |
Qwen2.5-VL-72B-Instructvision Qwen | Vision & multimodal | 73B | 125K | Custom license |
| Moonshot AI | Coding | 73B | 128K | MIT |
translategemma-27b-itvision Google | Translation | 27B | — | Gemma Terms of Use |
translategemma-12b-itvision Google | Translation | 12B | — | Gemma Terms of Use |
Qwen2.5-VL-32B-Instructvision Qwen | Vision & multimodal | 33B | 125K | Apache 2.0 |
| Xiaomi MiMo | Chat & reasoning | 310B | 256K | MIT |
| Moonshot AI | Chat & reasoning | 1.03T | 256K | Modified MIT |
| Z.ai | Vision & multimodal | 108B | 64K | MIT |
| Mistral AI | Coding | 24B | 384K | Apache 2.0 |
| Xiaomi MiMo | Chat & reasoning | 1.02T | 256K | MIT |
| Alibaba NLP | Embeddings | 305M | 8K | Apache 2.0 |
| Qwen | Rerankers | 8.8B | 256K | Apache 2.0 |
| Qwen | Vision & multimodal | 236B | 256K | Apache 2.0 |
| NVIDIA | Speech recognition | 979M | — | CC BY 4.0 |
| Snowflake | Embeddings | 568M | 8K | Apache 2.0 |
| DeepSeek | Chat & reasoning | 685B | 160K | MIT |
| Upstage | Chat & reasoning | 103B | 128K | Custom license |
| MiniMax | Chat & reasoning | 456B | 9.8M | Apache 2.0 |
| inclusionAI | Vision & multimodal | 125B | 128K | MIT |
| Qwen | Chat & reasoning | 81B | 256K | Apache 2.0 |
| ByteDance Seed | Chat & reasoning | 36B | 512K | Apache 2.0 |
| Meituan LongCat | Chat & reasoning | 562B | 128K | MIT |
Fara-7Bvision Microsoft | Vision & multimodal | 8.3B | 125K | MIT |
| Qwen | Vision & multimodal | 236B | 256K | Apache 2.0 |
MiMo-V2.5MoE Xiaomi MiMo | Chat & reasoning | 311B | 1M | MIT |
| Mistral AI | Chat & reasoning | 14B | 256K | Apache 2.0 |
| NVIDIA | Chat & reasoning | 32B | 256K | Custom license |
RolmOCRvision Reducto | OCR & documents | 8.3B | 125K | Apache 2.0 |
| Qwen | Chat & reasoning | 31B | 256K | Apache 2.0 |
| NVIDIA | Speech recognition | 2.6B | — | CC BY 4.0 |
| Alibaba NLP | Rerankers | 150M | 8K | Apache 2.0 |
| Baidu | Vision & multimodal | 30B | 128K | Apache 2.0 |
MinerU2.5-2509-1.2Bvision OpenDataLab | OCR & documents | 1.2B | 16K | Custom license |
| Jina AI | Rerankers | 597M | 128K | CC BY-NC 4.0· non-commercial |
| Z.ai | Chat & reasoning | 33B | 32K | MIT |
| StepFun | Chat & reasoning | 201B | 256K | Apache 2.0 |
| inclusionAI | Chat & reasoning | 107B | 128K | MIT |
| Nomic | Embeddings | 7.1B | 32K | Apache 2.0 |
| Alibaba NLP | Embeddings | 149M | 8K | Apache 2.0 |
| Qwen | Chat & reasoning | 235B | 125K | Apache 2.0 |
Llama-Guard-4-12Bvision Meta Llama | Safety & moderation | 12B | 160K | Llama 4 Community License |
Step3-VL-10Bvision StepFun | Vision & multimodal | 10B | 64K | Apache 2.0 |
| NVIDIA | Embeddings | 1.2B | 128K | Custom license |
| Perplexity | Embeddings | 596M | 32K | MIT |
| Z.ai | Vision & multimodal | 108B | 128K | MIT |
gemma-3n-E2B-itvision Google | Chat & reasoning | 5.4B | — | Gemma Terms of Use |
| IBM | Chat & reasoning | 32B | 128K | Apache 2.0 |
| DeepSeek | Chat & reasoning | 685B | 160K | MIT |
| OpenBMB | Chat & reasoning | 8.2B | 64K | Apache 2.0 |
| OpenAI | Safety & moderation | 22B | 128K | Apache 2.0 |
olmOCR-2-7B-1025vision Ai2 | OCR & documents | 8.3B | 125K | Apache 2.0 |
| Mistral AI | Chat & reasoning | 24B | 128K | Apache 2.0 |
| Cohere | Chat & reasoning | 111B | — | CC BY-NC 4.0· non-commercial |
LFM2.5-VL-1.6Bvision Liquid AI | Vision & multimodal | 1.6B | 125K | Custom license |
| Mistral AI | Coding | 125B | 256K | Custom license |
| InternLM | Vision & multimodal | 241B | 64K | Apache 2.0 |
| Tencent | Translation | 8.0B | 8K | Apache 2.0 |
| BAAI | Rerankers | 2.5B | 8K | Apache 2.0 |
| NVIDIA | Embeddings | 8.0B | 256K | OpenMDW 1.1 |
| Jina AI | Rerankers | 2.4B | 32K | CC BY-NC 4.0· non-commercial |
aya-vision-8bvision Cohere | Vision & multimodal | 8.6B | — | CC BY-NC 4.0· non-commercial |
| NVIDIA | Rerankers | 1.2B | 128K | OpenMDW 1.1 |
| IBM | Embeddings | 149M | 8K | Apache 2.0 |
Apriel-1.6-15b-Thinkervision ServiceNow | Vision & multimodal | 15B | 256K | MIT |
LongCat-2.0MoE Meituan LongCat | Chat & reasoning | 1.78T | 1M | MIT |
| ByteDance Seed | Translation | 7.5B | 32K | Custom license |
| Mistral AI | Chat & reasoning | — | 256K | Apache 2.0 |
| Swiss AI Initiative | Chat & reasoning | 71B | 64K | Apache 2.0 |
| NVIDIA | Safety & moderation | 4.3B | 128K | OpenMDW |
| Mixedbread | Rerankers | 1.5B | 32K | Apache 2.0 |
| EuroLLM | Chat & reasoning | 23B | 32K | Apache 2.0 |
| IBM | Safety & moderation | 8.2B | 128K | Apache 2.0 |
Specs and licenses from each model's Hugging Face page, synced 2026-11-18. Sorted by popularity: Hugging Face likes, trending, and downloads, plus OpenRouter usage.