Provider Models
Nvidia LLM Models
Compare Nvidia models with normalized token pricing, context window limits, modalities, and capability metadata. This page is optimized for provider-level model research.
155 active models listed. Open all Nvidia models filters
| Model | Context | Input Price | Output Price |
|---|---|---|---|
|
Active Speaker Detection
nvidia/nvidia/active-speaker-detection
|
0 | $0/1M | $0/1M |
|
bevformer
nvidia/nvidia/bevformer
|
128,000 | $0/1M | $0/1M |
|
BGE M3
nvidia/baai/bge-m3
|
8,192 | $0/1M | $0/1M |
|
ByteDance-Seed/Seed-OSS-36B-Instruct
nvidia/bytedance/seed-oss-36b-instruct
|
262,000 | $0/1M | $0/1M |
|
Codegemma 1.1 7b
nvidia/google/codegemma-1.1-7b
|
128,000 | $0/1M | $0/1M |
|
Codegemma 7b
nvidia/google/codegemma-7b
|
128,000 | $0/1M | $0/1M |
|
Codellama 70b
nvidia/meta/codellama-70b
|
128,000 | $0/1M | $0/1M |
|
Codestral 22b Instruct V0.1
nvidia/mistralai/codestral-22b-instruct-v0.1
|
128,000 | $0/1M | $0/1M |
|
Cosmos Nemotron 34B
nvidia/nvidia/cosmos-nemotron-34b
|
131,072 | $0/1M | $0/1M |
|
cosmos-predict1-5b
nvidia/nvidia/cosmos-predict1-5b
|
0 | $0/1M | $0/1M |
|
Cosmos Reason2 8B
nvidia/nvidia/cosmos-reason2-8b
|
131,072 | $0/1M | $0/1M |
|
cosmos-transfer1-7b
nvidia/nvidia/cosmos-transfer1-7b
|
0 | $0/1M | $0/1M |
|
cosmos-transfer2.5-2b
nvidia/nvidia/cosmos-transfer2_5-2b
|
0 | $0/1M | $0/1M |
|
Deepseek Coder 6.7b Instruct
nvidia/deepseek-ai/deepseek-coder-6.7b-instruct
|
128,000 | $0/1M | $0/1M |
|
Deepseek R1
nvidia/deepseek-ai/deepseek-r1
|
128,000 | $0/1M | $0/1M |
|
Deepseek R1 0528
nvidia/deepseek-ai/deepseek-r1-0528
|
128,000 | $0/1M | $0/1M |
|
DeepSeek V3.1
nvidia/deepseek-ai/deepseek-v3.1
|
128,000 | $0/1M | $0/1M |
|
DeepSeek V3.1 Terminus
nvidia/deepseek-ai/deepseek-v3.1-terminus
|
128,000 | $0/1M | $0/1M |
|
DeepSeek V3.2
nvidia/deepseek-ai/deepseek-v3.2
|
163,840 | $0/1M | $0/1M |
|
DeepSeek V4.1 Flash
nvidia/deepseek-ai/deepseek-v4.1-flash
|
1,000,000 | $0/1M | $0/1M |
|
DeepSeek V4 Flash
nvidia/deepseek-ai/deepseek-v4-flash
|
1,048,576 | $0.14/1M | $0.28/1M |
|
DeepSeek V4 Flash 0731
nvidia/deepseek-ai/deepseek-v4-flash-0731
|
1,000,000 | $0/1M | $0/1M |
|
DeepSeek V4 Pro
nvidia/deepseek-ai/deepseek-v4-pro
|
1,048,576 | $0.435/1M | $0.87/1M |
|
DeepSeek V4 Pro 0813
nvidia/deepseek-ai/deepseek-v4-pro-0813
|
1,000,000 | $0/1M | $0/1M |
|
Devstral-2-123B-Instruct-2512
nvidia/mistralai/devstral-2-123b-instruct-2512
|
262,144 | $0/1M | $0/1M |
|
DiffusionGemma 26B A4B IT
nvidia/google/diffusiongemma-26b-a4b-it
|
250,000 | $0/1M | $0/1M |
|
dracarys-llama-3.1-70b-instruct
nvidia/abacusai/dracarys-llama-3.1-70b-instruct
|
128,000 | $0/1M | $0/1M |
|
esm2-650m
nvidia/meta/esm2-650m
|
128,000 | $0/1M | $0/1M |
|
esmfold
nvidia/meta/esmfold
|
128,000 | $0/1M | $0/1M |
|
FLUX.1-dev
nvidia/black-forest-labs/flux.1-dev
|
4,096 | $0/1M | $0/1M |