# Supported models Modal Endpoints serve the open-weight models listed on this page. [Shared Endpoints](/docs/guide/shared-endpoints) serve models from a Modal-managed compute pool, using token-based billing. [Dedicated Endpoints](/docs/guide/dedicated-endpoints) run the models listed in [Dedicated Endpoint models](#dedicated-endpoint-models), or compatible custom weights, on isolated, autoscaling containers. Learn more about model capabilities in the [Model Library](https://modal.com/library). ## Shared Endpoint models Shared Endpoints are billed per token. Rates are in USD per million tokens and also appear when you create an Endpoint. | Model | Input Modalities | Input ($/Mtok) | Output ($/Mtok) | | ---------------------------------------------------------------------- | ------------------ | ---------------------------------------------------------- | ----------------------------------------------------------- | | [GLM 5.3 Flash NVFP4](/library/zai/glm-5-3-flash-nvfp4) | Text, Image | 0.15 / 0.03 cached | 0.50 | | [DeepSeek V4.1 Flash 1017](/library/deepseek/deepseek-v4-1-flash-1017) | Text, Image | 0.25 / 0.005 cached | 1.00 | | [DeepSeek V4.1 Flash](/library/deepseek/deepseek-v4-1-flash) | Text, Image | 0.30 / 0.03 cached | 1.20 | | [GLM 5.3 Flash](/library/zai/glm-5-3-flash) | Text, Image | 0.45 / 0.09 cached | 1.50 | | [Muse Spark Open](/library/meta/muse-spark-open) | Text, Image, Audio | 1.25 / 0.15 cached | 4.25 | | [GLM 5.3](/library/zai/glm-5-3) | Text | 1.40 / 0.26 cached | 4.40 | | [Inkling NVFP4](/library/thinking-machines/inkling) | Text, Image, Audio | 1.20 / 0.27 cached | 5.00 | | [Qwen3.8-Max](/library/qwen/qwen3-8-max) | Text | 2.00 / 0.25 cached | 6.00 | | [Qwen3.8-Max VL](/library/qwen/qwen3-8-max-vl) | Text, Image | 2.00 / 0.25 cached | 6.00 | | [Kimi K3](/library/moonshot/kimi-k3) | Text, Image | 3.00 / 0.30 cached | 15.00 | ## Dedicated Endpoint models Dedicated Endpoints bill for compute required to serve the model; see [Dedicated Endpoint pricing](/docs/guide/dedicated-endpoints#pricing). For entries shown as model IDs, pass the ID to `modal endpoint create --model`. | Model | Input Modalities | | -------------------------------------------------------------------------------------------------- | ------------------ | | [Beam 1.0 501B-A23B-FP8](/library/reflection/beam) | Text | | [Beam 1.0 501B-A23B-NVFP4](/library/reflection/beam) | Text | | [DeepSeek V4 Flash](/library/deepseek/deepseek-v4-flash) | Text | | [DeepSeek V4 Flash Preview](/library/deepseek/deepseek-v4-flash-preview) | Text | | [DeepSeek V4 Pro](/library/deepseek/deepseek-v4-pro) | Text | | [DeepSeek V4 Pro Preview](/library/deepseek/deepseek-v4-pro-preview) | Text | | [DeepSeek V4.1 Flash](/library/deepseek/deepseek-v4-1-flash) | Text, Image | | [Gemma 3 1B IT](/library/google/gemma-3-1b-it) | Text | | [Gemma 4 26B A4B IT](/library/google/gemma-4-26b-a4b-it) | Text, Image | | [Gemma 4 31B IT](/library/google/gemma-4-31b) | Text, Image | | [Gemma 4 E2B IT](/library/google/gemma-4-e2b-it) | Text, Image | | [Gemma 4 E4B IT](/library/google/gemma-4-e4b-it) | Text, Image | | [GLM 4.7](/library/zai/glm-4-7) | Text | | [GLM 5.2 FP8](/library/zai/glm-5-2-fp8) | Text | | [GLM 5.2 NVFP4](/library/zai/glm-5-2-nvfp4) | Text | | [GLM 5.3](/library/zai/glm-5-3-nvfp4) | Text | | [GLM 5.3 Flash](/library/zai/glm-5-3-flash) | Text, Image | | [GPT-OSS 120B](/library/openai/gpt-oss-120b) | Text | | [Hy3 GPTQ Int4](/library/tencent/hy3-gptq-int4) | Text | | [Inkling NVFP4](/library/thinking-machines/inkling) | Text, Image, Audio | | [K2 Horizon 0.9B](/library/ifm/k2-horizon-0-9b) | Text | | [Kimi K2.6 NVFP4](/library/moonshot/kimi-k2-6-nvfp4) | Text | | [Kimi K3](/library/moonshot/kimi-k3) | Text, Image | | [Muse Glimmer 30B BF16](/library/meta/muse-glimmer-30b-bf16) | Text | | [Muse Glimmer 30B NVFP4](/library/meta/muse-glimmer-30b-nvfp4) | Text | | [Nemotron 3.5 Lightning 30B A3B NVFP4](/library/nvidia/nemotron-3-5-lightning-30b-a3b-nvfp4) | Text | | [Nemotron 3.5 Super VL 120B A12B NVFP4](/library/nvidia/nemotron-3-5-super-vl-120b-a12b-nvfp4) | Text, Image | | [NVIDIA Nemotron 3 Super 120B A12B NVFP4](/library/nvidia/nvidia-nemotron-3-super-120b-a12b-nvfp4) | Text | | [NVIDIA Nemotron 3 Ultra 550B A55B NVFP4](/library/nvidia/nvidia-nemotron-3-ultra-550b-a55b-nvfp4) | Text | | [PhoneLLM Alpha 1](/library/pipecat/phonellm-alpha-1) | Text | | [PhoneLLM Max Alpha 2](/library/pipecat/phonellm-max-alpha-2) | Text | | [PhoneLLM Mini Alpha 2](/library/pipecat/phonellm-mini-alpha-2) | Text | | [Qwen3 Embedding 0.6B](/library/qwen/qwen3-embedding-0-6b) | Text | | [Qwen3 Embedding 8B](/library/qwen/qwen3-embedding-8b) | Text | | [Qwen3.5 0.8B](/library/qwen/qwen3-5-0-8b) | Text, Image | | [Qwen3.5 122B A10B FP8](/library/qwen/qwen3-5-122b-a10b-fp8) | Text, Image | | [Qwen3.5 27B FP8](/library/qwen/qwen3-5-27b-fp8) | Text, Image | | [Qwen3.5 2B](/library/qwen/qwen3-5-2b) | Text, Image | | [Qwen3.5 35B A3B FP8](/library/qwen/qwen3-5-35b-a3b-fp8) | Text, Image | | [Qwen3.5 397B A17B FP8](/library/qwen/qwen3-5-397b-a17b-fp8) | Text, Image | | [Qwen3.5 4B](/library/qwen/qwen3-5-4b) | Text, Image | | [Qwen3.5 9B](/library/qwen/qwen3-5-9b) | Text, Image | | [Qwen3.6 27B](/library/qwen/qwen3-6-27b) | Text, Image | | [Qwen3.6 27B FP8](/library/qwen/qwen3-6-27b-fp8) | Text, Image | | [Qwen3.6 35B A3B](/library/qwen/qwen3-6-35b-a3b) | Text, Image | | [Qwen3.6 35B A3B FP8](/library/qwen/qwen3-6-35b-a3b-fp8) | Text, Image | | [Qwen3.8 2.4T A95B NVFP4](/library/qwen/qwen3-8-2-4t-a95b-nvfp4) | Text | | [Qwen3.8 27B](/library/qwen/qwen3-8-27b) | Text | | [Qwen3.8 Flash Next](/library/qwen/qwen3-8-flash-next-fp8) | Text, Image | | [Qwen3.8 Flash Next FP8](/library/qwen/qwen3-8-flash-next-fp8) | Text, Image | | [Step 5 Preview](/library/stepfun/step-5-preview) | Text, Image |