Chat
nvidia/NVIDIA-Nemotron-3-Super-120B-A12B
Input/1M $0.10
Output/1M $0.50
Parameters 120B (12B active)
Model Catalog
One API for all models. Search our library, deploy and run inference on NVIDIA GPUs in seconds
Unlock $1 free API credit on first recharge - generate up to ~4M tokens
Showing 73 of 73 models
Chat
deepseek-ai/DeepSeek-V3.2
Input/1M $0.56
Output/1M $1.68
Parameters 685B
Chat
zai-org/GLM-5
Input/1M $0.80
Output/1M $3.13
Parameters 744B (40B active)
Chat
MiniMaxAI/MiniMax-M2.5
Input/1M $0.30
Output/1M $1.20
Parameters 230B (10B active)
Vision
moonshotai/Kimi-K2.5
Input/1M $0.60
Output/1M $3.00
Parameters 1T (32B active)
Code
Qwen/Qwen3-Coder-Plus
Input/1M $0.10
Output/1M $5.00
Vision
anthropic/claude-opus-4-6
Input/1M $5.00
Output/1M $25.00
Vision
openai/gpt-5.4
Input/1M $5.00
Output/1M $22.00
Vision
google/gemini-3.1-pro-preview
Input/1M $2.00
Output/1M $12.00
Image
Qwen/WAN 2.7 Image
Per image $0.03
Parameters Undisclosed
Vision
Qwen/Qwen3.6-Plus
Input/1M $0.26
Output/1M $1.80
Parameters Undisclosed (frontier-scale)
Chat
MiniMaxAI/MiniMax-M2.1
Input/1M $0.30
Output/1M $1.20
Parameters 230B (10B active)
Chat
moonshotai/Kimi-K2-Thinking
Input/1M $0.60
Output/1M $2.50
Parameters 1T (32B active)
Vision
Qwen/Qwen3.5-Flash
Input/1M $0.10
Output/1M $0.40
Parameters 35B (3B active) — hosted
Vision
Qwen/Qwen3.5-27B
Input/1M $0.30
Output/1M $2.40
Parameters 27B (dense)
Vision
Qwen/Qwen3.5-35B-A3B
Input/1M $0.25
Output/1M $2.00
Parameters 35B (3B active)
Vision
Qwen/Qwen3.5-122B-A10B
Input/1M $0.40
Output/1M $3.20
Parameters 122B (10B active)
Vision
Qwen/Qwen3.5-397B-A17B
Input/1M $0.60
Output/1M $3.60
Parameters 397B (17B active)
Chat
deepseek-ai/DeepSeek-R1-0528
Input/1M $0.90
Output/1M $3.20
Parameters 671B (37B active)
Chat
Qwen/Qwen3-Max
Input/1M $1.20
Output/1M $6.00
Parameters 235B (22B active)
Vision
Qwen/Qwen3-VL-235B-A22B-Thinking
Input/1M $0.40
Output/1M $4.00
Parameters 235B (22B active)
Code
Qwen/Qwen3-Coder-480B-A35B-Instruct
Input/1M $1.50
Output/1M $7.50
Parameters 480B (35B active)
Chat
Qwen/Qwen3-Next-80B-A3B-Thinking
Input/1M $0.20
Output/1M $1.80
Parameters 80B (3.9B active)
Chat
nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16
Input/1M $0.04
Output/1M $0.22
Parameters 31.6B Total / 3.2B Active
Chat
meta-llama/Llama-3.3-70B-Instruct
Input/1M $0.27
Output/1M $0.85
Parameters 70B
OCR
tencent/HunyuanOCR
Input/1M $0.21
Output/1M $0.35
Parameters 1.0B
Chat
deepseek-ai/deepseek-r1-distill-llama-70b
Input/1M $1.20
Output/1M $1.80
Parameters 70B
Chat
microsoft/Fara-7B
Input/1M $0.21
Output/1M $0.25
Parameters 7B
Code
Qwen/Qwen3-Coder-30B-A3B-Instruct
Input/1M $0.79
Output/1M $0.79
Parameters 1.1B
Chat
openai/gpt-oss-120b
Input/1M $0.15
Output/1M $0.61
Parameters 121.7B
Audio
openai/whisper-large-v3
Audio / sec $0.00002900
Parameters 1.55B
Audio
Qwen/Qwen3-TTS-Flash
Input/1M --
Parameters Multi-billion (approx.)
Code
Qwen/Qwen3-Coder-Next
Input/1M $0.30
Output/1M $1.50
Parameters 79.7B (3B active)
Chat
openai/gpt-oss-20b
Input/1M $0.05
Output/1M $0.28
Parameters 20.9B
Chat
mistralai/Mistral-7B-Instruct-v0.3
Input/1M $0.21
Output/1M $0.25
Parameters 7.3B
Image
p-image
Per image $0.0050
Parameters Not publicly disclosed
Image
p-image-edit
Per image $0.01
Parameters Not publicly disclosed
Image
stabilityai/stable-diffusion-3.5-large
Per image $0.0050
Parameters 8.1B
Image
Tongyi-MAI/Z-Image-Turbo
Per image $0.0050
Parameters 6B
![Z-Image-Turbo [LoRA]](https://github.com/Tongyi-MAI.png)
Image
Z-Image-Turbo [LoRA]
Per image $0.0080
Parameters 6B (~16GB VRAM at bf16)
![FLUX.1 [dev]](https://github.com/black-forest-labs.png)
Image
FLUX.1 [dev]
Per image $0.0050
Parameters 12B (~23GB in bf16)
Image
FLUX.2 [klein] 4B
Per image $0.0001
Parameters 4B (~23.7GB bf16 checkpoint; ~13GB VRAM at runtime)
Image
Qwen/Qwen-Image
Per image $0.03
Parameters 20B (~21.8 GB at Q8, ~11.9 GB at Q4)
Video
p-video
720p / sec $0.02
Parameters Not publicly disclosed
Image
p-image-lora
Per image $0.0050
Parameters Not publicly disclosed
Image
p-image-edit-lora
Per image $0.01
Parameters Base + LoRA adapters
Vision
Qwen/Qwen3-VL-8B-Instruct
Input/1M $0.25
Output/1M $0.44
Parameters 9B
Code
Qwen/Qwen3-Coder-Flash
Input/1M $0.30
Output/1M $5.00
Chat
Qwen/Qwen3-Plus
Input/1M $0.40
Output/1M $1.20
Vision
Qwen/Qwen3-VL-235B-A22B-Instruct
Input/1M $0.40
Output/1M $1.60
Parameters 235B
Vision
Qwen/Qwen3-VL-Flash
Input/1M $0.05
Output/1M $0.40
Vision
Qwen/Qwen3-VL-Plus
Input/1M $0.20
Output/1M $1.60
Vision
Qwen/Qwen3-VL-30B-A3B-Instruct
Input/1M $1.15
Output/1M $1.17
Parameters 30B
Image
Qwen/Qwen-Image-2.0
Per image $0.04
Image
Qwen/Qwen-Image-2.0-Pro
Per image $0.08
Image
Qwen/Qwen-Image-2.0-Edit
Per image $0.04
Image
Qwen/Qwen-Image-2.0-Pro-Edit
Per image $0.08
Chat
deepseek-ai/DeepSeek-V3
Input/1M $0.30
Output/1M $1.30
Parameters 671B (37B active)
Vision
Qwen/Qwen3.5-Plus
Input/1M $0.40
Output/1M $2.40
Parameters 397B (17B active) — hosted
Chat
zai-org/GLM-4.7
Input/1M $0.60
Output/1M $2.20
Parameters 355B (32B active)
Chat
moonshotai/Kimi-K2-Instruct
Input/1M $0.50
Output/1M $2.40
Parameters 1T (32B active)
Vision
google/gemini-3-flash-preview
Input/1M $0.50
Output/1M $3.00
Vision
google/gemini-2.5-pro
Input/1M $1.25
Output/1M $10.00
Vision
google/gemini-2.5-flash
Input/1M $0.15
Output/1M $0.25
Vision
anthropic/claude-opus-4-5
Input/1M $5.00
Output/1M $25.00
Vision
anthropic/claude-sonnet-4-6
Input/1M $3.00
Output/1M $15.00
Vision
anthropic/claude-sonnet-4-5
Input/1M $3.00
Output/1M $15.00
Vision
anthropic/claude-haiku-4-5-20251001
Input/1M $1.00
Output/1M $5.00
Vision
openai/gpt-4o
Input/1M $2.50
Output/1M $10.00
Vision
openai/gpt-4o-mini
Input/1M $0.40
Output/1M $1.60
Vision
openai/gpt-4.1
Input/1M $2.00
Output/1M $8.00
Vision
openai/gpt-5.4-mini
Input/1M $1.50
Output/1M $6.00
Vision
openai/gpt-5.4-nano
Input/1M $0.20
Output/1M $1.25
Sign up to get $1.00 free API credit. Test out the latest models now.
Access enterprise-grade open-source AI models including Llama 3, DeepSeek, Qwen, and more via our high-performance serverless API. Experience low-latency inference on the latest NVIDIA GPUs optimized for production workloads.
"Qubrid's medical OCR and research parsing cut our document extraction time in half. We now have traceable pipelines and reproducible outputs that meet our compliance requirements."
Clinical AI Team
Research & Clinical Intelligence