Chat Models
| Organization | Model Name | API Model String | Context length | Quantization |
|---|---|---|---|---|
| OpenAI | GPT OSS 120B | openai/gpt-oss-120b | 128000 | MXFP4 |
| OpenAI | GPT OSS 20B | openai/gpt-oss-20b | 128000 | MXFP4 |
| DeepSeek | DeepSeek R1 Distill Llama 70B | deepseek-ai/deepseek-r1-distill-llama-70b | 65000 | FP16 |
| DeepSeek | DeepSeek R1 0528 | deepseek-ai/DeepSeek-R1-0528 | 131072 | FP16 |
| DeepSeek | DeepSeek V3.2 | deepseek-ai/DeepSeek-V3.2 | 131072 | FP16 |
| Mistral AI | Mistral (7B) Instruct v0.3 | mistralai/Mistral-7B-Instruct-v0.3 | 32768 | FP16 |
| NVIDIA | Nemotron Orchestrator 8B | nvidia/Orchestrator-8B | 16384 | FP16 |
| NVIDIA | Nemotron 3 Nano 30B | nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16 | 262144 | BF16 |
| NVIDIA | Nemotron 3 Super 120B A12B | nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-FP8 | 262144 | FP8 |
| Microsoft | Fara 7B | microsoft/Fara-7B | 8192 | FP16 |
| Meta | Llama 3.3 70B Instruct | meta-llama/Llama-3.3-70B-Instruct | 8192 | FP16 |
| Qwen | Qwen3 Plus | Qwen/Qwen3-Plus | 131072 | FP16 |
| Qwen | Qwen3 Next 80B A3B Thinking | Qwen/Qwen3-Next-80B-A3B-Thinking | 131072 | FP16 |
| Qwen | Qwen3 Max | Qwen/Qwen3-Max | 131072 | FP16 |
| Moonshot AI | Kimi K2 Thinking | moonshotai/Kimi-K2-Thinking | 131072 | FP16 |
| ZhipuAI | GLM 4.7 FP8 | zai-org/GLM-4.7-FP8 | 131072 | FP8 |
| MiniMax | MiniMax M2.1 | MiniMaxAI/MiniMax-M2.1 | 131072 | FP16 |
Code Models
| Organization | Model Name | API Model String | Context length | Quantization |
|---|---|---|---|---|
| Qwen | Qwen3 Coder 30B A3B Instruct | Qwen/Qwen3-Coder-30B-A3B-Instruct | 131000 | FP16 |
| Qwen | Qwen3 Coder Plus | Qwen/Qwen3-Coder-Plus | ||
| Qwen | Qwen3 Coder Next | Qwen/Qwen3-Coder-Next | ||
| Qwen | Qwen3 Coder Flash | Qwen/Qwen3-Coder-Flash | ||
| Qwen | Qwen3 Coder 480B A35B Instruct | Qwen/Qwen3-Coder-480B-A35B-Instruct |
Image Models
| Organization | Model Name | API Model String | Model Type | Default steps |
|---|---|---|---|---|
| Pruna AI | P-Image | p-image | Image Generation | — |
| Pruna AI | P-Image LoRA | p-image-lora | Image Generation | — |
| Pruna AI | P-Image Edit | p-image-edit | Image Edit | — |
| Pruna AI | P-Image Edit LoRA | p-image-edit-lora | Image Edit | — |
| Qwen Tongyi MAI | Z Image Turbo | Tongyi-MAI/Z-Image-Turbo | Image Generation | 9 |
| Stability AI | Stable Diffusion 3.5 Large | stabilityai/stable-diffusion-3.5-large | Image Generation | 30 |
| Qwen | Qwen Image Edit | Qwen/Qwen-Image-Edit | Image Edit | 20 |
| Black Forest Labs | Flux Dev | black-forest-labs/flux-dev | Image Generation | |
| Black Forest Labs | Flux 2 Klein 4B | black-forest-labs/flux-2-klein-4b | Image Generation |
Audio Models
| Organization | Modality | Model Name | API Model String |
|---|---|---|---|
| OpenAI | Speech-to-Text | Whisper Large v3 | openai/whisper-large-v3 |
| Qwen | Text-to-Speech | Qwen3 TTS Flash | qwen3-tts-flash |
Video Models
| Organization | Model Name | API Model String | Max Duration | Max Resolution |
|---|---|---|---|---|
| Pruna AI | P-Video | p-video | 10 seconds | 1080p |
OCR Models
| Organization | Model Name | API Model String | Context length |
|---|---|---|---|
| Tencent | Hunyuan OCR (1B) | tencent/HunyuanOCR | 16000 |
Vision Models
| Organization | Model Name | API Model String | Context length |
|---|---|---|---|
| Qwen | Qwen3-VL 8B Instruct | Qwen/Qwen3-VL-8B-Instruct | 32768 |
| Qwen | Qwen3-VL 30B A3B Instruct | Qwen/Qwen3-VL-30B-A3B-Instruct | 128000 |
| Qwen | Qwen2.5-VL 7B Instruct | Qwen/Qwen2.5-VL-7B-Instruct | 32768 |
| Qwen | Qwen3-VL Plus | Qwen/Qwen3-VL-Plus | |
| Qwen | Qwen3-VL Flash | Qwen/Qwen3-VL-Flash | |
| Qwen | Qwen3-VL 235B A22B Instruct | Qwen/Qwen3-VL-235B-A22B-Instruct | |
| Qwen | Qwen3-VL 235B A22B Thinking | Qwen/Qwen3-VL-235B-A22B-Thinking | 262144 |
| Qwen | Qwen3.5 397B A17B | Qwen/Qwen3.5-397B-A17B | 262144 |
| Qwen | Qwen3.5 122B A10B | Qwen/Qwen3.5-122B-A10B | 262144 |
| Qwen | Qwen3.5 27B | Qwen/Qwen3.5-27B | 262144 |
| Qwen | Qwen3.5 35B A3B | Qwen/Qwen3.5-35B-A3B | 262144 |
| Qwen | Qwen3.5 Flash | Qwen/Qwen3.5-Flash | 1048576 |
| Moonshot AI | Kimi K2.5 | moonshotai/Kimi-K2.5 | 262144 |
Embedding Models
| Model Name | API Model String | Model Size | Embedding Dimension | Context Window |
|---|---|---|---|---|
| BGE-Large-EN-v1.5 | BAAI/bge-large-en-v1.5 | 326M | 1024 | 512 |