Skip to content
ModelPriceLab

Search model prices

Find source-linked rates by model, vendor, or platform.

Common destinations

All pricesCompare modelsScenario rankings
Vendor Library/NVIDIA/Pricing

NVIDIA API Pricing

Complete pricing for all NVIDIA models. Input/output costs per 1M tokens, context windows, and rate limits.

Billing terms: priced in USD per 1M tokens unless a row states otherwise; official direct rates are listed separately from third-party channels, and regional prices are kept distinct. Record updated 2026-10-11.

NVIDIA API Pricing Calculator

Select a model to estimate monthly cost using its listed rates on each channel.

Quick examples:
Input mode
Cache hit rate (share of input tokens served from cache)50%

Workloads reusing system prompts, long documents, or conversation history hit more; channels without a cached rate are billed at the full input rate.

Estimated monthly cost at current inputs
ChannelEffective inputOutput /1MEst. / month
official$0.0000$0.0000$0.0000

Formula: monthly cost = (input tokens × effective input rate + output tokens × output rate) ÷ 1,000,000 × calls. The effective input rate blends list and cached rates at your cache-hit share. Rates share the selected model and billing basis; your vendor bill is authoritative.

Currently available rates

Active Speaker Detection

LLMnvidia-nvidia-active-speaker-detection
View Details
Platform
Region
Input / 1M
Output / 1M
Cached input
Context
Max Output
Official
global
1M Tokens
$0.0000
$0.0000
—
—
4K
Sources: Official

BGE M3

Embednvidia-baai-bge-m3
View Details
Platform
Region
Input / 1M
Output / 1M
Cached input
Context
Max Output
Official
global
1M Tokens
$0.0000
$0.0000
—
8K
1K
Sources: Official

ByteDance-Seed/Seed-OSS-36B-Instruct

LLMnvidia-bytedance-seed-oss-36b-instruct
View Details
Deprecated

Deprecated endpoints may still be callable. Migrate before retirement.

Platform
Region
Input / 1M
Output / 1M
Cached input
Context
Max Output
Official
global
1M Tokens
$0.0000
$0.0000
—
262K
262K
Sources: Official

Cosmos Reason2 8B

LLMnvidia-nvidia-cosmos-reason2-8b
View Details
Platform
Region
Input / 1M
Output / 1M
Cached input
Context
Max Output
Official
global
1M Tokens
$0.0000
$0.0000
—
131K
16K
Sources: Official

DeepSeek V4 Flash

LLMnvidia-deepseek-ai-deepseek-v4-flash
View Details
Deprecated

Deprecated endpoints may still be callable. Migrate before retirement.

Platform
Region
Input / 1M
Output / 1M
Cached input
Context
Max Output
Official
global
1M Tokens
$0.14
$0.28
$0.0028
1049K
393K
Sources: Official

DeepSeek V4 Flash 0731

LLMnvidia-deepseek-ai-deepseek-v4-flash-0731
View Details
Deprecated

Deprecated endpoints may still be callable. Migrate before retirement.

Platform
Region
Input / 1M
Output / 1M
Cached input
Context
Max Output
Official
global
1M Tokens
$0.0000
$0.0000
—
1000K
384K
Sources: Official

DeepSeek V4 Pro

LLMnvidia-deepseek-ai-deepseek-v4-pro
View Details
Deprecated

Deprecated endpoints may still be callable. Migrate before retirement.

Platform
Region
Input / 1M
Output / 1M
Cached input
Context
Max Output
Official
global
1M Tokens
$0.44
$0.87
$0.0036
1049K
393K
Sources: Official

DeepSeek V4 Pro 0813

LLMnvidia-deepseek-ai-deepseek-v4-pro-0813
View Details
Deprecated

Deprecated endpoints may still be callable. Migrate before retirement.

Platform
Region
Input / 1M
Output / 1M
Cached input
Context
Max Output
Official
global
1M Tokens
$0.0000
$0.0000
—
1000K
384K
Sources: Official

DeepSeek V4.1 Flash

LLMnvidia-deepseek-ai-deepseek-v4.1-flash
View Details
Platform
Region
Input / 1M
Output / 1M
Cached input
Context
Max Output
Official
global
1M Tokens
$0.0000
$0.0000
—
1000K
384K
Sources: Official

DiffusionGemma 26B A4B IT

LLMnvidia-google-diffusiongemma-26b-a4b-it
View Details
Platform
Region
Input / 1M
Output / 1M
Cached input
Context
Max Output
Official
global
1M Tokens
$0.0000
$0.0000
—
250K
33K
Sources: Official

FLUX.1-Kontext-dev

Image Gennvidia-black-forest-labs-flux_1-kontext-dev
View Details
Platform
Region
Input / 1M
Output / 1M
Cached input
Context
Max Output
Official
global
1M Tokens
$0.0000
$0.0000
—
41K
41K
Sources: Official

FLUX.1-dev

Image Gennvidia-black-forest-labs-flux.1-dev
View Details
Platform
Region
Input / 1M
Output / 1M
Cached input
Context
Max Output
Official
global
1M Tokens
$0.0000
$0.0000
—
4K
—
Sources: Official

FLUX.1-schnell

Image Gennvidia-black-forest-labs-flux_1-schnell
View Details
Platform
Region
Input / 1M
Output / 1M
Cached input
Context
Max Output
Official
global
1M Tokens
$0.0000
$0.0000
—
0K
—
Sources: Official

FLUX.2 Klein 4B

Image Gennvidia-black-forest-labs-flux_2-klein-4b
View Details
Platform
Region
Input / 1M
Output / 1M
Cached input
Context
Max Output
Official
global
1M Tokens
$0.0000
$0.0000
—
41K
41K
Sources: Official

GLM-5.2

LLMnvidia-z-ai-glm-5.2
View Details
Deprecated

Deprecated endpoints may still be callable. Migrate before retirement.

Platform
Region
Input / 1M
Output / 1M
Cached input
Context
Max Output
Official
global
1M Tokens
$0.0000
$0.0000
—
1000K
131K
Sources: Official

GLM-5.3

LLMnvidia-z-ai-glm-5.3
View Details
Platform
Region
Input / 1M
Output / 1M
Cached input
Context
Max Output
Official
global
1M Tokens
$0.0000
$0.0000
—
1000K
131K
Sources: Official

GLM-5.3-Flash

LLMnvidia-z-ai-glm-5.3-flash
View Details
Platform
Region
Input / 1M
Output / 1M
Cached input
Context
Max Output
Official
global
1M Tokens
$0.0000
$0.0000
—
1000K
131K
Sources: Official

GPT OSS 20B

LLMnvidia-openai-gpt-oss-20b
View Details
Platform
Region
Input / 1M
Output / 1M
Cached input
Context
Max Output
Official
global
1M Tokens
$0.0000
$0.0000
—
131K
33K
Sources: Official

GPT-OSS-120B

LLMnvidia-openai-gpt-oss-120b
View Details
Platform
Region
Input / 1M
Output / 1M
Cached input
Context
Max Output
Official
global
1M Tokens
$0.0000
$0.0000
—
128K
8K

Gemma 2 2b It

LLMnvidia-google-gemma-2-2b-it
View Details
Deprecated

Deprecated endpoints may still be callable. Migrate before retirement.

Platform
Region
Input / 1M
Output / 1M
Cached input
Context
Max Output
Official
global
1M Tokens
$0.0000
$0.0000
—
128K
4K
Sources: Official

Gemma 3 12B IT

LLMnvidia-google-gemma-3-12b-it
View Details
Platform
Region
Input / 1M
Output / 1M
Cached input
Context
Max Output
Official
global
1M Tokens
$0.0000
$0.0000
—
131K
16K
Sources: Official

Gemma 3 4B IT

LLMnvidia-google-gemma-3-4b-it
View Details
Platform
Region
Input / 1M
Output / 1M
Cached input
Context
Max Output
Official
global
1M Tokens
$0.0000
$0.0000
—
131K
16K
Sources: Official

Gemma 3n E2b It

LLMnvidia-google-gemma-3n-e2b-it
View Details
Deprecated

Deprecated endpoints may still be callable. Migrate before retirement.

Platform
Region
Input / 1M
Output / 1M
Cached input
Context
Max Output
Official
global
1M Tokens
$0.0000
$0.0000
—
128K
4K
Sources: Official

Gemma 3n E4b It

LLMnvidia-google-gemma-3n-e4b-it
View Details
Deprecated

Deprecated endpoints may still be callable. Migrate before retirement.

Platform
Region
Input / 1M
Output / 1M
Cached input
Context
Max Output
Official
global
1M Tokens
$0.0000
$0.0000
—
128K
4K
Sources: Official

Gemma-4-31B-IT

LLMnvidia-google-gemma-4-31b-it
View Details
Platform
Region
Input / 1M
Output / 1M
Cached input
Context
Max Output
Official
global
1M Tokens
$0.0000
$0.0000
—
256K
16K
Sources: Official

Inkling

LLMnvidia-thinkingmachines-inkling
View Details
Deprecated

Deprecated endpoints may still be callable. Migrate before retirement.

Platform
Region
Input / 1M
Output / 1M
Cached input
Context
Max Output
Official
global
1M Tokens
$0.0000
$0.0000
—
1049K
16K
Sources: Official

Kimi K2 0905

LLMnvidia-moonshotai-kimi-k2-instruct-0905
View Details
Platform
Region
Input / 1M
Output / 1M
Cached input
Context
Max Output
Official
global
1M Tokens
$0.0000
$0.0000
—
262K
262K

Kimi K2.6

LLMnvidia-moonshotai-kimi-k2.6
View Details
Deprecated

Deprecated endpoints may still be callable. Migrate before retirement.

Platform
Region
Input / 1M
Output / 1M
Cached input
Context
Max Output
Official
global
1M Tokens
$0.0000
$0.0000
—
262K
262K
Sources: Official

Kimi K3

LLMnvidia-moonshotai-kimi-k3
View Details
Platform
Region
Input / 1M
Output / 1M
Cached input
Context
Max Output
Official
global
1M Tokens
$0.0000
$0.0000
—
1049K
131K
Sources: Official

Laguna XS 2.1

LLMnvidia-poolside-laguna-xs-2.1
View Details
Platform
Region
Input / 1M
Output / 1M
Cached input
Context
Max Output
Official
global
1M Tokens
$0.0000
$0.0000
—
262K
16K
Sources: Official

Llama 3.1 70b Instruct

LLMnvidia-meta-llama-3.1-70b-instruct
View Details
Deprecated

Deprecated endpoints may still be callable. Migrate before retirement.

Platform
Region
Input / 1M
Output / 1M
Cached input
Context
Max Output
Official
global
1M Tokens
$0.0000
$0.0000
—
128K
4K
Sources: Official

Llama 3.1 8B Instruct

LLMnvidia-meta-llama-3.1-8b-instruct
View Details
Deprecated

Deprecated endpoints may still be callable. Migrate before retirement.

Platform
Region
Input / 1M
Output / 1M
Cached input
Context
Max Output
Official
global
1M Tokens
$0.0000
$0.0000
—
16K
4K
Sources: Official

Llama 3.1 Nemotron 70B Instruct

LLMnvidia-nvidia-llama-3.1-nemotron-70b-instruct
View Details
Platform
Region
Input / 1M
Output / 1M
Cached input
Context
Max Output
Official
global
1M Tokens
$0.0000
$0.0000
—
128K
8K
Sources: Official

Llama 3.1 Nemotron Nano 8B v1

LLMnvidia-nvidia-llama-3.1-nemotron-nano-8b-v1
View Details
Deprecated

Deprecated endpoints may still be callable. Migrate before retirement.

Platform
Region
Input / 1M
Output / 1M
Cached input
Context
Max Output
Official
global
1M Tokens
$0.0000
$0.0000
—
131K
16K
Sources: Official

Llama 3.1 Nemotron Nano VL 8B v1

LLMnvidia-nvidia-llama-3.1-nemotron-nano-vl-8b-v1
View Details
Deprecated

Deprecated endpoints may still be callable. Migrate before retirement.

Platform
Region
Input / 1M
Output / 1M
Cached input
Context
Max Output
Official
global
1M Tokens
$0.0000
$0.0000
—
33K
16K
Sources: Official

Llama 3.1 Nemotron Ultra 253B

LLMnvidia-nvidia-llama-3.1-nemotron-ultra-253b-v1
View Details
Platform
Region
Input / 1M
Output / 1M
Cached input
Context
Max Output
Official
global
1M Tokens
$0.0000
$0.0000
—
128K
16K
Sources: Official

Llama 3.2 11b Vision Instruct

LLMnvidia-meta-llama-3.2-11b-vision-instruct
View Details
Platform
Region
Input / 1M
Output / 1M
Cached input
Context
Max Output
Official
global
1M Tokens
$0.0000
$0.0000
—
128K
4K
Sources: Official

Llama 3.2 1b Instruct

LLMnvidia-meta-llama-3.2-1b-instruct
View Details
Deprecated

Deprecated endpoints may still be callable. Migrate before retirement.

Platform
Region
Input / 1M
Output / 1M
Cached input
Context
Max Output
Official
global
1M Tokens
$0.0000
$0.0000
—
128K
4K
Sources: Official

Llama 3.2 3B Instruct

LLMnvidia-meta-llama-3.2-3b-instruct
View Details
Deprecated

Deprecated endpoints may still be callable. Migrate before retirement.

Platform
Region
Input / 1M
Output / 1M
Cached input
Context
Max Output
Official
global
1M Tokens
$0.0000
$0.0000
—
33K
32K
Sources: Official

Llama 3.3 70b Instruct

LLMnvidia-meta-llama-3.3-70b-instruct
View Details
Deprecated

Deprecated endpoints may still be callable. Migrate before retirement.

Platform
Region
Input / 1M
Output / 1M
Cached input
Context
Max Output
Official
global
1M Tokens
$0.0000
$0.0000
—
128K
4K
Sources: Official

Llama 3.3 Nemotron Super 49B v1

LLMnvidia-nvidia-llama-3.3-nemotron-super-49b-v1
View Details
Deprecated

Deprecated endpoints may still be callable. Migrate before retirement.

Platform
Region
Input / 1M
Output / 1M
Cached input
Context
Max Output
Official
global
1M Tokens
$0.0000
$0.0000
—
131K
66K
Sources: Official

Llama 3.3 Nemotron Super 49B v1.5

LLMnvidia-nvidia-llama-3.3-nemotron-super-49b-v1.5
View Details
Deprecated

Deprecated endpoints may still be callable. Migrate before retirement.

Platform
Region
Input / 1M
Output / 1M
Cached input
Context
Max Output
Official
global
1M Tokens
$0.0000
$0.0000
—
131K
66K
Sources: Official

Llama 4 Maverick 17b 128e Instruct

LLMnvidia-meta-llama-4-maverick-17b-128e-instruct
View Details
Deprecated

Deprecated endpoints may still be callable. Migrate before retirement.

Platform
Region
Input / 1M
Output / 1M
Cached input
Context
Max Output
Official
global
1M Tokens
$0.0000
$0.0000
—
128K
4K
Sources: Official

Llama Guard 4 12B

LLMnvidia-meta-llama-guard-4-12b
View Details
Platform
Region
Input / 1M
Output / 1M
Cached input
Context
Max Output
Official
global
1M Tokens
$0.0000
$0.0000
—
128K
16K
Sources: Official

Llama-3.2-90B-Vision-Instruct

LLMnvidia-meta-llama-3.2-90b-vision-instruct
View Details
Platform
Region
Input / 1M
Output / 1M
Cached input
Context
Max Output
Official
global
1M Tokens
$0.0000
$0.0000
—
128K
8K
Sources: Official

Magistral Small 2506

LLMnvidia-mistralai-magistral-small-2506
View Details
Platform
Region
Input / 1M
Output / 1M
Cached input
Context
Max Output
Official
global
1M Tokens
$0.0000
$0.0000
—
33K
33K
Sources: Official

MiniMax-M2.7

LLMnvidia-minimaxai-minimax-m2.7
View Details
Deprecated

Deprecated endpoints may still be callable. Migrate before retirement.

Platform
Region
Input / 1M
Output / 1M
Cached input
Context
Max Output
Official
global
1M Tokens
$0.0000
$0.0000
—
205K
131K
Sources: Official

MiniMax-M3

LLMnvidia-minimaxai-minimax-m3
View Details
Deprecated

Deprecated endpoints may still be callable. Migrate before retirement.

Platform
Region
Input / 1M
Output / 1M
Cached input
Context
Max Output
Official
global
1M Tokens
$0.0000
$0.0000
—
1000K
16K
Sources: Official

Ministral 3 14B Instruct 2512

LLMnvidia-mistralai-ministral-14b-instruct-2512
View Details
Deprecated

Deprecated endpoints may still be callable. Migrate before retirement.

Platform
Region
Input / 1M
Output / 1M
Cached input
Context
Max Output
Official
global
1M Tokens
$0.0000
$0.0000
—
262K
16K
Sources: Official

Mistral Large 3 675B Instruct 2512

LLMnvidia-mistralai-mistral-large-3-675b-instruct-2512
View Details
Deprecated

Deprecated endpoints may still be callable. Migrate before retirement.

Platform
Region
Input / 1M
Output / 1M
Cached input
Context
Max Output
Official
global
1M Tokens
$0.0000
$0.0000
—
262K
262K
Sources: Official

Mistral Medium 3

LLMnvidia-mistralai-mistral-medium-3-instruct
View Details
Platform
Region
Input / 1M
Output / 1M
Cached input
Context
Max Output
Official
global
1M Tokens
$0.0000
$0.0000
—
131K
33K
Sources: Official

Mistral Medium 3.5

LLMnvidia-mistralai-mistral-medium-3.5-128b
View Details
Deprecated

Deprecated endpoints may still be callable. Migrate before retirement.

Platform
Region
Input / 1M
Output / 1M
Cached input
Context
Max Output
Official
global
1M Tokens
$0.0000
$0.0000
—
262K
33K
Sources: Official

Mistral-7B-Instruct-v0.3

LLMnvidia-mistralai-mistral-7b-instruct-v0.3
View Details
Platform
Region
Input / 1M
Output / 1M
Cached input
Context
Max Output
Official
global
1M Tokens
$0.0000
$0.0000
—
66K
66K
Sources: Official

Mistral: Mixtral 8x22B Instruct

LLMnvidia-mistralai-mixtral-8x22b-instruct
View Details
Deprecated

Deprecated endpoints may still be callable. Migrate before retirement.

Platform
Region
Input / 1M
Output / 1M
Cached input
Context
Max Output
Official
global
1M Tokens
$0.0000
$0.0000
—
66K
13K
Sources: Official

Mistral: Mixtral 8x7B Instruct

LLMnvidia-mistralai-mixtral-8x7b-instruct
View Details
Deprecated

Deprecated endpoints may still be callable. Migrate before retirement.

Platform
Region
Input / 1M
Output / 1M
Cached input
Context
Max Output
Official
global
1M Tokens
$0.0000
$0.0000
—
33K
16K
Sources: Official

Muse Glimmer 30B

LLMnvidia-meta-muse-glimmer-30b
View Details
Platform
Region
Input / 1M
Output / 1M
Cached input
Context
Max Output
Official
global
1M Tokens
$0.0000
$0.0000
—
131K
131K
Sources: Official

Nemotron 3 Nano Omni

LLMnvidia-nvidia-nemotron-3-nano-omni-30b-a3b-reasoning
View Details
Platform
Region
Input / 1M
Output / 1M
Cached input
Context
Max Output
Official
global
1M Tokens
$0.0000
$0.0000
—
256K
66K
Sources: Official

Nemotron 3 Nano Omni (free)

LLMnvidia-nemotron-3-nano-omni-30b-a3b-reasoning-free
View Details
Platform
Region
Input / 1M
Output / 1M
Cached input
Context
Max Output
OpenRouter
global
1M Tokens
$0.0000
$0.0000
—
256K
66K
Sources: OpenRouter

Nemotron 3 Super

LLMnvidia-nemotron-3-super-120b-a12b
View Details
Platform
Region
Input / 1M
Output / 1M
Cached input
Context
Max Output
OpenRouter
global
1M Tokens
$0.08
$0.45
—
262K
236K
Official
global
1M Tokens
$0.20
$0.80
—
262K
262K
Sources: OpenRouter · Official

Nemotron 3 Super (free)

LLMnvidia-nemotron-3-super-120b-a12b-free
View Details
Platform
Region
Input / 1M
Output / 1M
Cached input
Context
Max Output
OpenRouter
global
1M Tokens
$0.0000
$0.0000
—
262K
236K
Sources: OpenRouter

Nemotron 3 Ultra (free)

LLMnvidia-nemotron-3-ultra-550b-a55b-free
View Details
Platform
Region
Input / 1M
Output / 1M
Cached input
Context
Max Output
OpenRouter
global
1M Tokens
$0.0000
$0.0000
—
1000K
66K
Sources: OpenRouter

Nemotron 3 Ultra 550B A55B

LLMnvidia-nemotron-3-ultra-550b-a55b
View Details
Platform
Region
Input / 1M
Output / 1M
Cached input
Context
Max Output
OpenRouter
global
1M Tokens
$0.50
$2.20
$0.10
262K
16K
Official
global
1M Tokens
$0.50
$2.50
$0.15
1000K
66K
Sources: OpenRouter · Official

Nemotron 3.5 Content Safety

LLMnvidia-nemotron-3.5-content-safety
View Details
Platform
Region
Input / 1M
Output / 1M
Cached input
Context
Max Output
OpenRouter
global
1M Tokens
$0.20
$0.20
—
131K
118K
Official
global
1M Tokens
$0.0000
$0.0000
—
128K
8K
Sources: OpenRouter · Official

Nemotron 3.5 Content Safety (free)

LLMnvidia-nemotron-3.5-content-safety-free
View Details
Platform
Region
Input / 1M
Output / 1M
Cached input
Context
Max Output
OpenRouter
global
1M Tokens
$0.0000
$0.0000
—
128K
8K
Sources: OpenRouter

Nemotron 3.5 Lightning

LLMnvidia-nemotron-3.5-lightning
View Details
Platform
Region
Input / 1M
Output / 1M
Cached input
Context
Max Output
OpenRouter
global
1M Tokens
$0.06
$0.16
$0.03
262K
33K
Sources: OpenRouter

Nemotron 3.5 Lightning (free)

LLMnvidia-nemotron-3.5-lightning-free
View Details
Platform
Region
Input / 1M
Output / 1M
Cached input
Context
Max Output
OpenRouter
global
1M Tokens
$0.0000
$0.0000
—
1000K
66K
Sources: OpenRouter

Nemotron 3.5 Lightning 30B A3B

LLMnvidia-nvidia-nemotron-3.5-lightning-30b-a3b
View Details
Platform
Region
Input / 1M
Output / 1M
Cached input
Context
Max Output
Official
global
1M Tokens
$0.0000
$0.0000
—
262K
262K
Sources: Official

Nemotron Nano 12B v2 VL

LLMnvidia-nvidia-nemotron-nano-12b-v2-vl
View Details
Deprecated

Deprecated endpoints may still be callable. Migrate before retirement.

Platform
Region
Input / 1M
Output / 1M
Cached input
Context
Max Output
Official
global
1M Tokens
$0.0000
$0.0000
—
128K
128K
Sources: Official

Phi 4 Multimodal

LLMnvidia-microsoft-phi-4-multimodal-instruct
View Details
Deprecated

Deprecated endpoints may still be callable. Migrate before retirement.

Platform
Region
Input / 1M
Output / 1M
Cached input
Context
Max Output
Official
global
1M Tokens
$0.0000
$0.0000
—
128K
16K
Sources: Official

Phi-4-Mini

LLMnvidia-microsoft-phi-4-mini-instruct
View Details
Deprecated

Deprecated endpoints may still be callable. Migrate before retirement.

Platform
Region
Input / 1M
Output / 1M
Cached input
Context
Max Output
Official
global
1M Tokens
$0.0000
$0.0000
—
131K
8K
Sources: Official

Qwen Image

Image Gennvidia-qwen-qwen-image
View Details
Platform
Region
Input / 1M
Output / 1M
Cached input
Context
Max Output
Official
global
1M Tokens
$0.0000
$0.0000
—
—
—
Sources: Official

Qwen Image Edit

Image Gennvidia-qwen-qwen-image-edit
View Details
Platform
Region
Input / 1M
Output / 1M
Cached input
Context
Max Output
Official
global
1M Tokens
$0.0000
$0.0000
—
—
—
Sources: Official

Qwen2.5 Coder 32b Instruct

LLMnvidia-qwen-qwen2.5-coder-32b-instruct
View Details
Deprecated

Deprecated endpoints may still be callable. Migrate before retirement.

Platform
Region
Input / 1M
Output / 1M
Cached input
Context
Max Output
Official
global
1M Tokens
$0.0000
$0.0000
—
128K
4K
Sources: Official

Qwen3 Coder 480B A35B Instruct

LLMnvidia-qwen-qwen3-coder-480b-a35b-instruct
View Details
Deprecated

Deprecated endpoints may still be callable. Migrate before retirement.

Platform
Region
Input / 1M
Output / 1M
Cached input
Context
Max Output
Official
global
1M Tokens
$0.0000
$0.0000
—
262K
67K
Sources: Official

Qwen3-Next-80B-A3B-Instruct

LLMnvidia-qwen-qwen3-next-80b-a3b-instruct
View Details
Deprecated

Deprecated endpoints may still be callable. Migrate before retirement.

Platform
Region
Input / 1M
Output / 1M
Cached input
Context
Max Output
Official
global
1M Tokens
$0.0000
$0.0000
—
262K
16K
Sources: Official

Qwen3.5 122B-A10B

LLMnvidia-qwen-qwen3.5-122b-a10b
View Details
Deprecated

Deprecated endpoints may still be callable. Migrate before retirement.

Platform
Region
Input / 1M
Output / 1M
Cached input
Context
Max Output
Official
global
1M Tokens
$0.0000
$0.0000
—
262K
66K
Sources: Official

Qwen3.5-397B-A17B

LLMnvidia-qwen-qwen3.5-397b-a17b
View Details
Deprecated

Deprecated endpoints may still be callable. Migrate before retirement.

Platform
Region
Input / 1M
Output / 1M
Cached input
Context
Max Output
Official
global
1M Tokens
$0.0000
$0.0000
—
262K
8K
Sources: Official

Step 3.5 Flash

LLMnvidia-stepfun-ai-step-3.5-flash
View Details
Deprecated

Deprecated endpoints may still be callable. Migrate before retirement.

Platform
Region
Input / 1M
Output / 1M
Cached input
Context
Max Output
Official
global
1M Tokens
$0.0000
$0.0000
—
256K
16K
Sources: Official

Step 3.7 Flash

LLMnvidia-stepfun-ai-step-3.7-flash
View Details
Deprecated

Deprecated endpoints may still be callable. Migrate before retirement.

Platform
Region
Input / 1M
Output / 1M
Cached input
Context
Max Output
Official
global
1M Tokens
$0.0000
$0.0000
—
256K
16K
Sources: Official

Switchyard

LLMnvidia-switchyard
View Details
Platform
Region
Input / 1M
Output / 1M
Cached input
Context
Max Output
OpenRouter
global
1M Tokens
-
-
—
1000K
—
Sources: OpenRouter

Whisper Large v3

LLMnvidia-openai-whisper-large-v3
View Details
Platform
Region
Input / 1M
Output / 1M
Cached input
Context
Max Output
Official
global
1M Tokens
$0.0000
$0.0000
—
—
4K
Sources: Official

bevformer

Specializednvidia-nvidia-bevformer
View Details
Platform
Region
Input / 1M
Output / 1M
Cached input
Context
Max Output
Official
global
1M Tokens
$0.0000
$0.0000
—
128K
8K
Sources: Official

cosmos-predict1-5b

Videonvidia-nvidia-cosmos-predict1-5b
View Details
Platform
Region
Input / 1M
Output / 1M
Cached input
Context
Max Output
Official
global
1M Tokens
$0.0000
$0.0000
—
—
4K
Sources: Official

cosmos-transfer1-7b

Videonvidia-nvidia-cosmos-transfer1-7b
View Details
Platform
Region
Input / 1M
Output / 1M
Cached input
Context
Max Output
Official
global
1M Tokens
$0.0000
$0.0000
—
—
4K
Sources: Official

cosmos-transfer2.5-2b

Videonvidia-nvidia-cosmos-transfer2_5-2b
View Details
Platform
Region
Input / 1M
Output / 1M
Cached input
Context
Max Output
Official
global
1M Tokens
$0.0000
$0.0000
—
—
4K
Sources: Official

dracarys-llama-3.1-70b-instruct

LLMnvidia-abacusai-dracarys-llama-3.1-70b-instruct
View Details
Deprecated

Deprecated endpoints may still be callable. Migrate before retirement.

Platform
Region
Input / 1M
Output / 1M
Cached input
Context
Max Output
Official
global
1M Tokens
$0.0000
$0.0000
—
128K
8K
Sources: Official

esm2-650m

Specializednvidia-meta-esm2-650m
View Details
Platform
Region
Input / 1M
Output / 1M
Cached input
Context
Max Output
Official
global
1M Tokens
$0.0000
$0.0000
—
128K
8K
Sources: Official

esmfold

Specializednvidia-meta-esmfold
View Details
Platform
Region
Input / 1M
Output / 1M
Cached input
Context
Max Output
Official
global
1M Tokens
$0.0000
$0.0000
—
128K
8K
Sources: Official

gliner-pii

Specializednvidia-nvidia-gliner-pii
View Details
Deprecated

Deprecated endpoints may still be callable. Migrate before retirement.

Platform
Region
Input / 1M
Output / 1M
Cached input
Context
Max Output
Official
global
1M Tokens
$0.0000
$0.0000
—
128K
4K
Sources: Official

llama-3.1-nemotron-safety-guard-8b-v3

LLMnvidia-nvidia-llama-3.1-nemotron-safety-guard-8b-v3
View Details
Platform
Region
Input / 1M
Output / 1M
Cached input
Context
Max Output
Official
global
1M Tokens
$0.0000
$0.0000
—
128K
4K
Sources: Official

llama-3_2-nemoretriever-300m-embed-v1

Embednvidia-nvidia-llama-3_2-nemoretriever-300m-embed-v1
View Details
Platform
Region
Input / 1M
Output / 1M
Cached input
Context
Max Output
Official
global
1M Tokens
$0.0000
$0.0000
—
33K
2K
Sources: Official

llama-nemotron-embed-vl-1b-v2

Embednvidia-nvidia-llama-nemotron-embed-vl-1b-v2
View Details
Platform
Region
Input / 1M
Output / 1M
Cached input
Context
Max Output
Official
global
1M Tokens
$0.0000
$0.0000
—
33K
2K
Sources: Official

llama-nemotron-rerank-vl-1b-v2

Reranknvidia-nvidia-llama-nemotron-rerank-vl-1b-v2
View Details
Platform
Region
Input / 1M
Output / 1M
Cached input
Context
Max Output
Official
global
1M Tokens
$0.0000
$0.0000
—
128K
4K
Sources: Official

magpie-tts-zeroshot

Audionvidia-nvidia-magpie-tts-zeroshot
View Details
Platform
Region
Input / 1M
Output / 1M
Cached input
Context
Max Output
Official
global
1M Tokens
$0.0000
$0.0000
—
—
4K
Sources: Official

mistral-nemotron

LLMnvidia-mistralai-mistral-nemotron
View Details
Deprecated

Deprecated endpoints may still be callable. Migrate before retirement.

Platform
Region
Input / 1M
Output / 1M
Cached input
Context
Max Output
Official
global
1M Tokens
$0.0000
$0.0000
—
128K
8K
Sources: Official

mistral-small-4-119b-2603

LLMnvidia-mistralai-mistral-small-4-119b-2603
View Details
Deprecated

Deprecated endpoints may still be callable. Migrate before retirement.

Platform
Region
Input / 1M
Output / 1M
Cached input
Context
Max Output
Official
global
1M Tokens
$0.0000
$0.0000
—
128K
8K
Sources: Official

nemotron-3-content-safety

LLMnvidia-nvidia-nemotron-3-content-safety
View Details
Deprecated

Deprecated endpoints may still be callable. Migrate before retirement.

Platform
Region
Input / 1M
Output / 1M
Cached input
Context
Max Output
Official
global
1M Tokens
$0.0000
$0.0000
—
128K
4K
Sources: Official

nemotron-3-nano-30b-a3b

LLMnvidia-nemotron-3-nano-30b-a3b
View Details
Deprecated

Deprecated endpoints may still be callable. Migrate before retirement.

Platform
Region
Input / 1M
Output / 1M
Cached input
Context
Max Output
OpenRouter
global
1M Tokens
$0.05
$0.20
$0.03
262K
236K
Official
global
1M Tokens
$0.0000
$0.0000
—
131K
131K
Sources: OpenRouter · Official

nemotron-content-safety-reasoning-4b

LLMnvidia-nvidia-nemotron-content-safety-reasoning-4b
View Details
Deprecated

Deprecated endpoints may still be callable. Migrate before retirement.

Platform
Region
Input / 1M
Output / 1M
Cached input
Context
Max Output
Official
global
1M Tokens
$0.0000
$0.0000
—
128K
4K
Sources: Official

nemotron-mini-4b-instruct

LLMnvidia-nvidia-nemotron-mini-4b-instruct
View Details
Deprecated

Deprecated endpoints may still be callable. Migrate before retirement.

Platform
Region
Input / 1M
Output / 1M
Cached input
Context
Max Output
Official
global
1M Tokens
$0.0000
$0.0000
—
128K
8K
Sources: Official

nemotron-voicechat

LLMnvidia-nvidia-nemotron-voicechat
View Details
Platform
Region
Input / 1M
Output / 1M
Cached input
Context
Max Output
Official
global
1M Tokens
$0.0000
$0.0000
—
128K
8K
Sources: Official

nv-embed-v1

Embednvidia-nvidia-nv-embed-v1
View Details
Platform
Region
Input / 1M
Output / 1M
Cached input
Context
Max Output
Official
global
1M Tokens
$0.0000
$0.0000
—
33K
2K
Sources: Official

nv-embedcode-7b-v1

Embednvidia-nvidia-nv-embedcode-7b-v1
View Details
Platform
Region
Input / 1M
Output / 1M
Cached input
Context
Max Output
Official
global
1M Tokens
$0.0000
$0.0000
—
33K
2K
Sources: Official

nvidia-nemotron-nano-9b-v2

LLMnvidia-nvidia-nvidia-nemotron-nano-9b-v2
View Details
Deprecated

Deprecated endpoints may still be callable. Migrate before retirement.

Platform
Region
Input / 1M
Output / 1M
Cached input
Context
Max Output
Official
global
1M Tokens
$0.0000
$0.0000
—
131K
131K
Sources: Official

paligemma

LLMnvidia-google-google-paligemma
View Details
Platform
Region
Input / 1M
Output / 1M
Cached input
Context
Max Output
Official
global
1M Tokens
$0.0000
$0.0000
—
128K
8K
Sources: Official

rerank-qa-mistral-4b

Reranknvidia-nvidia-rerank-qa-mistral-4b
View Details
Platform
Region
Input / 1M
Output / 1M
Cached input
Context
Max Output
Official
global
1M Tokens
$0.0000
$0.0000
—
128K
4K
Sources: Official

riva-translate-4b-instruct-v1_1

LLMnvidia-nvidia-riva-translate-4b-instruct-v1.1
View Details
Platform
Region
Input / 1M
Output / 1M
Cached input
Context
Max Output
Official
global
1M Tokens
$0.0000
$0.0000
—
128K
4K
Sources: Official

sarvam-m

LLMnvidia-sarvamai-sarvam-m
View Details
Deprecated

Deprecated endpoints may still be callable. Migrate before retirement.

Platform
Region
Input / 1M
Output / 1M
Cached input
Context
Max Output
Official
global
1M Tokens
$0.0000
$0.0000
—
128K
8K
Sources: Official

solar-10.7b-instruct

LLMnvidia-upstage-solar-10.7b-instruct
View Details
Deprecated

Deprecated endpoints may still be callable. Migrate before retirement.

Platform
Region
Input / 1M
Output / 1M
Cached input
Context
Max Output
Official
global
1M Tokens
$0.0000
$0.0000
—
128K
8K
Sources: Official

sparsedrive

Specializednvidia-nvidia-sparsedrive
View Details
Platform
Region
Input / 1M
Output / 1M
Cached input
Context
Max Output
Official
global
1M Tokens
$0.0000
$0.0000
—
128K
8K
Sources: Official

streampetr

Specializednvidia-nvidia-streampetr
View Details
Platform
Region
Input / 1M
Output / 1M
Cached input
Context
Max Output
Official
global
1M Tokens
$0.0000
$0.0000
—
128K
8K
Sources: Official

studiovoice

LLMnvidia-nvidia-studiovoice
View Details
Platform
Region
Input / 1M
Output / 1M
Cached input
Context
Max Output
Official
global
1M Tokens
$0.0000
$0.0000
—
128K
8K
Sources: Official

synthetic-video-detector

LLMnvidia-nvidia-synthetic-video-detector
View Details
Platform
Region
Input / 1M
Output / 1M
Cached input
Context
Max Output
Official
global
1M Tokens
$0.0000
$0.0000
—
—
4K
Sources: Official

usdcode

LLMnvidia-nvidia-usdcode
View Details
Platform
Region
Input / 1M
Output / 1M
Cached input
Context
Max Output
Official
global
1M Tokens
$0.0000
$0.0000
—
128K
4K
Sources: Official

usdvalidate

LLMnvidia-nvidia-usdvalidate
View Details
Platform
Region
Input / 1M
Output / 1M
Cached input
Context
Max Output
Official
global
1M Tokens
$0.0000
$0.0000
—
—
4K
Sources: Official
NVIDIA Overview
Products, apps, and recent changes
NVIDIA Changes
API changes, pricing updates, and deprecations
AI Cost Optimization

Does this change your best option?

Check your models and usage for free. See the relevant official changes, estimated cost, and a practical next step.

Check my modelsApply for founder pilot