Model Markets
Get Free API KeyAPI

Hugging Face

External Link

Unified multi-provider inference routing from Hugging Face Inference Providers.

Models tracked
104
Route-ready
41
Input from
—
Output from
—

Catalog Coverage

Model Endpoints

ModelRoute modelContextInput / 1MOutput / 1MRegionEvidence
DeepSeek R1Route-readydeepseek-ai/DeepSeek-R1164K——UsOfficial fact
GLM OCRUnavailablezai-org/GLM-OCR131K——UsOfficial fact
DeepSeek V3.2Route-readydeepseek-ai/DeepSeek-V3.2164K——UsOfficial fact
NVIDIA Nemotron 3 Ultra 550B A55B BF16Route-readynvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16262K——UsOfficial fact
Qwen3.5 397B A17BRoute-readyQwen/Qwen3.5-397B-A17B262K——UsOfficial fact
Molmo2 8BUnavailableallenai/Molmo2-8B37K——UsOfficial fact
GLM 5.1Route-readyzai-org/GLM-5.1203K——UsOfficial fact
Granite Embedding English r2Unavailableibm-granite/granite-embedding-english-r28K——UsOfficial fact
Phi-4 Mini ReasoningUnavailablemicrosoft/Phi-4-mini-reasoning131K——UsOfficial fact
Olmo 3.1 32B InstructUnavailableallenai/Olmo-3.1-32B-Instruct66K——UsOfficial fact
Llama 3.1 405B InstructUnavailablemeta-llama/Llama-3.1-405B-Instruct131K——UsOfficial fact
PaddleOCR VL 1.5UnavailablePaddlePaddle/PaddleOCR-VL-1.5131K——UsOfficial fact
Olmo 3 32B ThinkUnavailableallenai/Olmo-3-32B-Think66K——UsOfficial fact
Llama 4 Maverick 17B 128E InstructUnavailablemeta-llama/Llama-4-Maverick-17B-128E-Instruct1,000K——UsOfficial fact
Hy3Route-readytencent/Hy3262K——UsOfficial fact
Ministral 3 14B Base 2512Unavailablemistralai/Ministral-3-14B-Base-2512262K——UsOfficial fact
DeepSeek V4 Flash Vision ExpUnavailabledeepseek-ai/DeepSeek-V4-Flash-Vision-Exp1,049K——GlobalOfficial fact
GLM 5.3Unavailablezai-org/GLM-5.31,000K——GlobalOfficial fact
GLM 5.3 FlashUnavailablezai-org/GLM-5.3-Flash1,000K——GlobalOfficial fact
GR00T N1.7 3BUnavailablenvidia/GR00T-N1.7-3B———UsOfficial fact
Command A Plus 05 2026 BF16UnavailableCohereLabs/command-a-plus-05-2026-bf16200K——UsOfficial fact
MiniMax M2.5Route-readyMiniMaxAI/MiniMax-M2.5197K——UsOfficial fact
MiniMax M2.7Route-readyMiniMaxAI/MiniMax-M2.7205K——UsOfficial fact
MiniMax M3Route-readyMiniMaxAI/MiniMax-M31,049K——UsOfficial fact
MiniMax Music3UnavailableMiniMaxAI/MiniMax-Music35K——UsOfficial fact
Qwen3 Coder NextRoute-readyQwen/Qwen3-Coder-Next262K——UsOfficial fact
Qwen3 Coder Next BaseUnavailableQwen/Qwen3-Coder-Next-Base262K——UsOfficial fact
Qwen3.5 35B A3BRoute-readyQwen/Qwen3.5-35B-A3B262K——UsOfficial fact
Qwen3.5 35B A3B BaseUnavailableQwen/Qwen3.5-35B-A3B-Base262K——UsOfficial fact
Qwen3.8 2.4T A95BRoute-readyQwen/Qwen3.8-2.4T-A95B262K——UsOfficial fact
Qwen3.8 27BRoute-readyQwen/Qwen3.8-27B262K——UsOfficial fact
MolmoAct 2Unavailableallenai/MolmoAct2———GlobalOfficial fact
MolmoAct2 PretrainUnavailableallenai/MolmoAct2-Pretrain16K——UsOfficial fact
MolmoAct2 ThinkUnavailableallenai/MolmoAct2-Think16K——UsOfficial fact
Olmo 3 7B InstructUnavailableallenai/Olmo-3-7B-Instruct66K——UsOfficial fact
Olmo 3 7B ThinkUnavailableallenai/Olmo-3-7B-Think66K——UsOfficial fact
ERNIE 4.5 0.3B PTUnavailablebaidu/ERNIE-4.5-0.3B-PT131K——UsOfficial fact
FLUX.2 klein 4B FP8Unavailableblack-forest-labs/FLUX.2-klein-4b-fp8———UsOfficial fact
FLUX.2 klein Base 4B FP8Unavailableblack-forest-labs/FLUX.2-klein-base-4b-fp8———UsOfficial fact
DeepSeek V3Route-readydeepseek-ai/DeepSeek-V3164K——UsOfficial fact
DeepSeek V4 FlashRoute-readydeepseek-ai/DeepSeek-V4-Flash1,049K——UsOfficial fact
DeepSeek V4 Flash BaseUnavailabledeepseek-ai/DeepSeek-V4-Flash-Base1,049K——UsOfficial fact
DeepSeek V4 ProRoute-readydeepseek-ai/DeepSeek-V4-Pro1,049K——UsOfficial fact
DeepSeek V4 Pro BaseUnavailabledeepseek-ai/DeepSeek-V4-Pro-Base1,049K——UsOfficial fact
Granite 4.1 30BUnavailableibm-granite/granite-4.1-30b131K——UsOfficial fact
Granite 4.1 3BUnavailableibm-granite/granite-4.1-3b131K——UsOfficial fact
Granite 4.1 8BUnavailableibm-granite/granite-4.1-8b131K——UsOfficial fact
Granite 4.2 30BUnavailableibm-granite/granite-4.2-30b131K——GlobalOfficial fact
Granite 4.2 3BUnavailableibm-granite/granite-4.2-3b131K——GlobalOfficial fact
Granite 4.2 8BUnavailableibm-granite/granite-4.2-8b131K——GlobalOfficial fact
Granite Embedding 107m MultilingualRoute-readyibm-granite/granite-embedding-107m-multilingual1K——UsOfficial fact
Granite Embedding 278m MultilingualRoute-readyibm-granite/granite-embedding-278m-multilingual1K——UsOfficial fact
Granite Embedding 30m EnglishRoute-readyibm-granite/granite-embedding-30m-english1K——UsOfficial fact
Granite Embedding 311m Multilingual r2Route-readyibm-granite/granite-embedding-311m-multilingual-r233K——UsOfficial fact
Granite Guardian 4.1 8BUnavailableibm-granite/granite-guardian-4.1-8b131K——UsOfficial fact
Granite Speech 5.0 TurboCTC NCUnavailableibm-granite/granite-speech-5.0-470m-turboctc-nc———GlobalOfficial fact
Granite Speech 5.0 TurboCTCUnavailableibm-granite/granite-speech-5.0-470m-turboctc———GlobalOfficial fact
Granite Vision 4.1 4BUnavailableibm-granite/granite-vision-4.1-4b131K——UsOfficial fact
Llama 3.1 405BUnavailablemeta-llama/Llama-3.1-405B131K——UsOfficial fact
Llama 3.1 70BRoute-readymeta-llama/Llama-3.1-70B131K——UsOfficial fact
Llama 3.1 70B InstructUnavailablemeta-llama/Llama-3.1-70B-Instruct131K——UsOfficial fact
Llama 3.1 8BRoute-readymeta-llama/Llama-3.1-8B131K——UsOfficial fact
Llama 3.1 8B InstructRoute-readymeta-llama/Llama-3.1-8B-Instruct131K——UsOfficial fact
Llama 3.3 70B InstructRoute-readymeta-llama/Llama-3.3-70B-Instruct131K——UsOfficial fact
Llama 4 Maverick 17B 128EUnavailablemeta-llama/Llama-4-Maverick-17B-128E1,000K——GlobalOfficial fact
Llama 4 Scout 17B 16EUnavailablemeta-llama/Llama-4-Scout-17B-16E10,000K——UsOfficial fact
Llama 4 Scout 17B 16E InstructRoute-readymeta-llama/Llama-4-Scout-17B-16E-Instruct10,000K——UsOfficial fact
Phi-4 Mini InstructRoute-readymicrosoft/Phi-4-mini-instruct131K——UsOfficial fact
Phi-4 Multimodal InstructUnavailablemicrosoft/Phi-4-multimodal-instruct131K——UsOfficial fact
Phi-4 ReasoningUnavailablemicrosoft/Phi-4-reasoning33K——UsOfficial fact
VibeVoice ASR Streaming 1.5BUnavailablemicrosoft/VibeVoice-ASR-Streaming-1.5B———GlobalOfficial fact
VibeVoice ASR Streaming 7BUnavailablemicrosoft/VibeVoice-ASR-Streaming-7B———GlobalOfficial fact
phi-4Route-readymicrosoft/phi-416K——UsOfficial fact
Codestral 22B v0.1Unavailablemistralai/Codestral-22B-v0.133K——UsOfficial fact
Devstral 2 123B Instruct 2512Unavailablemistralai/Devstral-2-123B-Instruct-2512262K——UsOfficial fact
Ministral 3 14B Instruct 2512Unavailablemistralai/Ministral-3-14B-Instruct-2512262K——UsOfficial fact
Ministral 3 14B Reasoning 2512Unavailablemistralai/Ministral-3-14B-Reasoning-2512262K——UsOfficial fact
Ministral 3 3B Base 2512Unavailablemistralai/Ministral-3-3B-Base-2512262K——UsOfficial fact
Ministral 3 3B Instruct 2512Unavailablemistralai/Ministral-3-3B-Instruct-2512262K——UsOfficial fact
Ministral 3 3B Reasoning 2512Unavailablemistralai/Ministral-3-3B-Reasoning-2512262K——UsOfficial fact
Ministral 3 8B Base 2512Unavailablemistralai/Ministral-3-8B-Base-2512262K——UsOfficial fact
Ministral 3 8B Instruct 2512Unavailablemistralai/Ministral-3-8B-Instruct-2512262K——UsOfficial fact
Ministral 3 8B Reasoning 2512Unavailablemistralai/Ministral-3-8B-Reasoning-2512262K——UsOfficial fact
Ministral 8B Instruct 2410Unavailablemistralai/Ministral-8B-Instruct-241033K——UsOfficial fact
Mistral Medium 3.5 128BUnavailablemistralai/Mistral-Medium-3.5-128B262K——UsOfficial fact
Mistral Small 4 119B 2603Unavailablemistralai/Mistral-Small-4-119B-26031,049K——UsOfficial fact
Kimi K2 InstructRoute-readymoonshotai/Kimi-K2-Instruct131K——UsOfficial fact
Kimi K2 ThinkingRoute-readymoonshotai/Kimi-K2-Thinking262K——UsOfficial fact
Kimi K2.5Route-readymoonshotai/Kimi-K2.5262K——UsOfficial fact
Kimi K2.6Route-readymoonshotai/Kimi-K2.6262K——UsOfficial fact
Kimi K3Route-readymoonshotai/Kimi-K31,049K——UsOfficial fact
NVIDIA Nemotron 3 Nano 30B A3B BF16Route-readynvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16262K——UsOfficial fact
NVIDIA Nemotron 3 Nano 30B A3B Base BF16Unavailablenvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-Base-BF16262K——UsOfficial fact
NVIDIA Nemotron 3 Super 120B A12B BF16Route-readynvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16262K——UsOfficial fact
NVIDIA Nemotron 3 Super 120B A12B Base BF16Unavailablenvidia/NVIDIA-Nemotron-3-Super-120B-A12B-Base-BF161,049K——UsOfficial fact
gpt-oss-120bRoute-readyopenai/gpt-oss-120b131K——UsOfficial fact
gpt-oss-20bRoute-readyopenai/gpt-oss-20b131K——UsOfficial fact
Stable Audio 3 MediumRoute-readystabilityai/stable-audio-3-medium———UsOfficial fact
Stable Diffusion 3.5 LargeRoute-readystabilityai/stable-diffusion-3.5-large0K——UsOfficial fact
Stable Diffusion 3.5 MediumRoute-readystabilityai/stable-diffusion-3.5-medium0K——UsOfficial fact
Hunyuan3D 2.1Unavailabletencent/Hunyuan3D-2.1———UsOfficial fact
Hy4 previewUnavailabletencent/Hy4-preview1,000K——GlobalOfficial fact
GLM 5Route-readyzai-org/GLM-5203K——UsOfficial fact
GLM 5.2Route-readyzai-org/GLM-5.21,049K——UsOfficial fact

Routing Contract

Modegateway
Protocolopenai
API basehttps://router.huggingface.co/v1
Last observedSep 2, 2026
Routing Groundwork Only

These public route targets identify where and how a model can be requested. Model Markets does not hold provider keys or send inference traffic from this interface.

Provider records describe a serving surface, not the underlying model. Pricing, quantization, region, service tier, retention policy, and measured performance remain endpoint-specific.

Questions

Hugging Face Questions

Which models does Hugging Face offer?+

The current source snapshot includes 104 model endpoint for Hugging Face: DeepSeek R1, GLM OCR, DeepSeek V3.2, NVIDIA Nemotron 3 Ultra 550B A55B BF16, Qwen3.5 397B A17B, Molmo2 8B, GLM 5.1, Granite Embedding English r2, Phi-4 Mini Reasoning, Olmo 3.1 32B Instruct, Llama 3.1 405B Instruct, PaddleOCR VL 1.5, Olmo 3 32B Think, Llama 4 Maverick 17B 128E Instruct, Hy3, Ministral 3 14B Base 2512, DeepSeek V4 Flash Vision Exp, GLM 5.3, GLM 5.3 Flash, GR00T N1.7 3B, Command A Plus 05 2026 BF16, MiniMax M2.5, MiniMax M2.7, MiniMax M3, MiniMax Music3, Qwen3 Coder Next, Qwen3 Coder Next Base, Qwen3.5 35B A3B, Qwen3.5 35B A3B Base, Qwen3.8 2.4T A95B, Qwen3.8 27B, MolmoAct 2, MolmoAct2 Pretrain, MolmoAct2 Think, Olmo 3 7B Instruct, Olmo 3 7B Think, ERNIE 4.5 0.3B PT, FLUX.2 klein 4B FP8, FLUX.2 klein Base 4B FP8, DeepSeek V3, DeepSeek V4 Flash, DeepSeek V4 Flash Base, DeepSeek V4 Pro, DeepSeek V4 Pro Base, Granite 4.1 30B, Granite 4.1 3B, Granite 4.1 8B, Granite 4.2 30B, Granite 4.2 3B, Granite 4.2 8B, Granite Embedding 107m Multilingual, Granite Embedding 278m Multilingual, Granite Embedding 30m English, Granite Embedding 311m Multilingual r2, Granite Guardian 4.1 8B, Granite Speech 5.0 TurboCTC NC, Granite Speech 5.0 TurboCTC, Granite Vision 4.1 4B, Llama 3.1 405B, Llama 3.1 70B, Llama 3.1 70B Instruct, Llama 3.1 8B, Llama 3.1 8B Instruct, Llama 3.3 70B Instruct, Llama 4 Maverick 17B 128E, Llama 4 Scout 17B 16E, Llama 4 Scout 17B 16E Instruct, Phi-4 Mini Instruct, Phi-4 Multimodal Instruct, Phi-4 Reasoning, VibeVoice ASR Streaming 1.5B, VibeVoice ASR Streaming 7B, phi-4, Codestral 22B v0.1, Devstral 2 123B Instruct 2512, Ministral 3 14B Instruct 2512, Ministral 3 14B Reasoning 2512, Ministral 3 3B Base 2512, Ministral 3 3B Instruct 2512, Ministral 3 3B Reasoning 2512, Ministral 3 8B Base 2512, Ministral 3 8B Instruct 2512, Ministral 3 8B Reasoning 2512, Ministral 8B Instruct 2410, Mistral Medium 3.5 128B, Mistral Small 4 119B 2603, Kimi K2 Instruct, Kimi K2 Thinking, Kimi K2.5, Kimi K2.6, Kimi K3, NVIDIA Nemotron 3 Nano 30B A3B BF16, NVIDIA Nemotron 3 Nano 30B A3B Base BF16, NVIDIA Nemotron 3 Super 120B A12B BF16, NVIDIA Nemotron 3 Super 120B A12B Base BF16, gpt-oss-120b, gpt-oss-20b, Stable Audio 3 Medium, Stable Diffusion 3.5 Large, Stable Diffusion 3.5 Medium, Hunyuan3D 2.1, Hy4 preview, GLM 5, GLM 5.2. Browse all models →

How much does Hugging Face cost?+

No reliable current price is present in this source snapshot.

Is Hugging Face the fastest provider?+

Model Markets has not run approved independent probes for this delivery, so it does not make a fastest-provider claim.

How current is Hugging Face data?+

The cited source snapshot was observed Sep 2, 2026; availability may have changed since then.

How does Model Markets verify Hugging Face?+

Catalog and price claims retain their source classification; independent measurements are labeled separately when available. Read the methodology →

Send Feedback