Type Instruct Reasoning Base Vision
Serving Serverless11 Dedicated125
125 models Reset filters
Kimi K3 moonshotai/Kimi-K3 Moonshot AI· Instruct· VisionServerless Dedicated $0.75/M input· $3.75/M output· 1M context
GLM-5.3 zai-org/GLM-5.3 Z.ai· InstructServerless Dedicated $0.35/M input· $1.10/M output· 1M context
NVIDIA Nemotron 3 Ultra nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16 NVIDIA· InstructServerless Dedicated $0.15/M input· $0.60/M output· 1M context
DeepSeek R1 deepseek-ai/DeepSeek-R1 DeepSeek· ReasoningServerless Dedicated $0.15/M input· $0.60/M output· 128K context
MiniMax M3 MiniMaxAI/MiniMax-M3 MiniMax· Instruct· VisionServerless Dedicated $0.075/M input· $0.30/M output· 1M context
DeepSeek V4 Flash deepseek-ai/DeepSeek-V4-Flash DeepSeek· InstructServerless Dedicated $0.075/M input· $0.30/M output· 1M context
GLM-4.6 zai-org/GLM-4.6 Z.ai· InstructServerless Dedicated $0.075/M input· $0.30/M output· 200K context
Qwen3 235B Instruct Qwen/Qwen3-235B-A22B-Instruct-2507 Alibaba (Qwen)· InstructServerless Dedicated $0.075/M input· $0.30/M output· 256K context
gpt-oss-120b openai/gpt-oss-120b OpenAI· ReasoningServerless Dedicated $0.04/M input· $0.15/M output· 128K context
NVIDIA Nemotron 3.5 Lightning 30B nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16 NVIDIA· InstructServerless Dedicated $0.0125/M input· $0.05/M output· 1M context
Qwen3 Coder 30B Qwen/Qwen3-Coder-30B-A3B-Instruct Alibaba (Qwen)· InstructServerless Dedicated $0.0125/M input· $0.05/M output· 256K context
01.AI· BaseDedicated 34.4B· 4K context
01.AI· InstructDedicated 34.4B· 4K context
01.AI· BaseDedicated 6.1B· 4K context
01.AI· InstructDedicated 6.1B· 4K context
01.AI· BaseDedicated 8.8B· 4K context
01.AI· InstructDedicated 8.8B· 4K context
Alibaba (Qwen)· BaseDedicated 0.5B· 32K context
Alibaba (Qwen)· InstructDedicated 0.5B· 32K context
Alibaba (Qwen)· BaseDedicated 1.5B· 32K context
Alibaba (Qwen)· InstructDedicated 1.5B· 32K context
Alibaba (Qwen)· BaseDedicated 14.8B· 128K context
Alibaba (Qwen)· InstructDedicated 14.8B· 128K context
Alibaba (Qwen)· BaseDedicated 32.8B· 128K context
Alibaba (Qwen)· InstructDedicated 32.8B· 128K context
Alibaba (Qwen)· BaseDedicated 3.1B· 32K context
Alibaba (Qwen)· InstructDedicated 3.1B· 32K context
Alibaba (Qwen)· BaseDedicated 72.7B· 128K context
Alibaba (Qwen)· InstructDedicated 72.7B· 128K context
Alibaba (Qwen)· BaseDedicated 7.6B· 128K context
Alibaba (Qwen)· InstructDedicated 7.6B· 128K context
Alibaba (Qwen)· InstructDedicated 0.6B· 32K context
Alibaba (Qwen)· BaseDedicated 0.6B· 32K context
Alibaba (Qwen)· InstructDedicated 1.7B· 32K context
Alibaba (Qwen)· BaseDedicated 1.7B· 32K context
Alibaba (Qwen)· InstructDedicated 14.8B· 32K context
Alibaba (Qwen)· BaseDedicated 14.8B· 32K context
Alibaba (Qwen)· InstructDedicated 235B total, 22B active· 32K context
Alibaba (Qwen)· InstructDedicated 30.5B total, 3.3B active· 32K context
Alibaba (Qwen)· InstructDedicated 32.8B· 32K context
Alibaba (Qwen)· InstructDedicated 4B· 32K context
Alibaba (Qwen)· BaseDedicated 4B· 32K context
Alibaba (Qwen)· InstructDedicated 8.2B· 32K context
Alibaba (Qwen)· BaseDedicated 8.2B· 32K context
Alibaba (Qwen)· InstructDedicated 30.5B total, 3.3B active· 256K context
Alibaba (Qwen)· Instruct· VisionDedicated 27B· 256K context
Allen Institute· InstructDedicated 7.3B· 64K context
Allen Institute· ReasoningDedicated 7.3B· 64K context
Allen Institute· InstructDedicated 32.2B· 64K context
Allen Institute· ReasoningDedicated 32.2B· 64K context
DeepSeek· ReasoningDedicated 70.6B· 128K context
DeepSeek· ReasoningDedicated 8B· 128K context
DeepSeek· ReasoningDedicated 1.8B· 128K context
DeepSeek· ReasoningDedicated 14.8B· 128K context
DeepSeek· ReasoningDedicated 32.8B· 128K context
DeepSeek· ReasoningDedicated 7.6B· 128K context
DeepSeek· InstructDedicated 671B total, 37B active· 128K context
DeepSeek· InstructDedicated ~304B· 1M context
Google· BaseDedicated 27.2B· 8K context
Google· InstructDedicated 27.2B· 8K context
Google· BaseDedicated 2.6B· 8K context
Google· InstructDedicated 2.6B· 8K context
Google· BaseDedicated 9.2B· 8K context
Google· InstructDedicated 9.2B· 8K context
Google· Instruct· VisionDedicated 12.2B· 128K context
Google· Base· VisionDedicated 12.2B· 128K context
Google· InstructDedicated 1B· 32K context
Google· BaseDedicated 1B· 32K context
Google· Instruct· VisionDedicated 27.4B· 128K context
Google· Base· VisionDedicated 27.4B· 128K context
Google· Instruct· VisionDedicated 4.3B· 128K context
Google· Base· VisionDedicated 4.3B· 128K context
Google· Base· VisionDedicated 12B· 256K context
Google· Instruct· VisionDedicated 12B· 256K context
Google· Base· VisionDedicated 25.2B total, 3.8B active· 256K context
Google· Instruct· VisionDedicated 25.2B total, 3.8B active· 256K context
Google· Base· VisionDedicated 31B· 256K context
Google· Instruct· VisionDedicated 31B· 256K context
Google· Base· VisionDedicated 5.1B, 2.3B effective· 128K context
Google· Instruct· VisionDedicated 5.1B, 2.3B effective· 128K context
Google· Base· VisionDedicated 8B, 4.5B effective· 128K context
Google· Instruct· VisionDedicated 8B, 4.5B effective· 128K context
Hugging Face· BaseDedicated 1.7B· 8K context
Hugging Face· InstructDedicated 1.7B· 8K context
Hugging Face· InstructDedicated 135M· 8K context
IBM· InstructDedicated 32B total, 9B active· 128K context
IBM· InstructDedicated 7B total, 1B active· 128K context
IBM· InstructDedicated 3B· 128K context
Meta· BaseDedicated 70.6B· 128K context
Meta· InstructDedicated 70.6B· 128K context
Meta· BaseDedicated 8B· 128K context
Meta· InstructDedicated 8B· 128K context
Meta· BaseDedicated 1.2B· 128K context
Meta· InstructDedicated 1.2B· 128K context
Meta· BaseDedicated 3.2B· 128K context
Meta· InstructDedicated 3.2B· 128K context
Meta· InstructDedicated 70.6B· 128K context
Meta· Instruct· VisionDedicated 400B total, 17B active· 1M context
Meta· Base· VisionDedicated 109B total, 17B active· 10M context
Meta· Instruct· VisionDedicated 109B total, 17B active· 10M context
Microsoft· InstructDedicated 3.8B· 128K context
Microsoft· InstructDedicated 14.7B· 16K context
Mistral AI· InstructDedicated 7.2B· 32K context
Mistral AI· BaseDedicated 7.2B· 32K context
Mistral AI· BaseDedicated 12.2B· 128K context
Mistral AI· InstructDedicated 12.2B· 128K context
Mistral AI· BaseDedicated 23.6B· 32K context
Mistral AI· InstructDedicated 23.6B· 32K context
Mistral AI· InstructDedicated ~141B total, 39B active· 64K context
Mistral AI· BaseDedicated ~141B total, 39B active· 64K context
Mistral AI· InstructDedicated ~46.7B total, 12.9B active· 32K context
Mistral AI· BaseDedicated ~46.7B total, 12.9B active· 32K context
NVIDIA· InstructDedicated 70.6B· 128K context
NVIDIA· InstructDedicated 8B· 128K context
NVIDIA· InstructDedicated 49.9B· 128K context
OpenAI· ReasoningDedicated 21B total, 3.6B active· 128K context
TII· InstructDedicated 33.6B· 256K context
TII· InstructDedicated 7.6B· 256K context
TII· BaseDedicated 10.3B· 32K context
TII· InstructDedicated 10.3B· 32K context
TII· BaseDedicated 7.5B· 32K context
TII· InstructDedicated 7.5B· 32K context
Z.ai· InstructDedicated 355B total, 32B active· 128K context
Z.ai· InstructDedicated 106B total, 12B active· 128K context
Z.ai· BaseDedicated 106B total, 12B active· 128K context
No models match. Bring your own and we'll serve it on a dedicated endpoint.
Load more