Live Pricing
4557 models across all major providers
| Model | Provider | Input $/1M tokens | Output $/1M tokens | Context | Max Output | Intelligence | Speed tok/s | Arena ELO |
|---|---|---|---|---|---|---|---|---|
|
black-forest-labs/flux.1-dev
|
Nvidia | — | — | — | — | — | — | — |
|
cosmos-nemotron-34b
|
Nvidia | — | — | — | — | — | — | — |
|
deepseek-ai/deepseek-v3.1
|
Nvidia | — | — | — | — | — | — | — |
|
deepseek-r1
|
Nvidia | — | — | — | — | — | — | — |
|
deepseek-v3.1
|
Nvidia | — | — | — | — | — | — | — |
|
flux_1-dev
|
Nvidia | — | — | — | — | — | — | — |
|
gemma-3-27b-it
|
Nvidia | — | — | — | — | — | — | — |
|
google/gemma-2-27b-it
Tools
Open
|
Nvidia | $0.65 | $0.65 | 128K | 4.1K | — | — | — |
|
google/gemma-3-27b-it
|
Nvidia | — | — | — | — | — | — | — |
|
google/gemma-4-31b-it
Reasoning
Tools
Vision
Open
|
Nvidia | $0.14 | $0.40 | 256K | 16.4K | — | — | — |
|
llama-3.1-nemotron-ultra-253b-v1
|
Nvidia | — | — | — | — | — | — | P9 |
|
llama-3.3-nemotron-super-49b-v1.5
|
Nvidia | — | — | — | — | — | — | P9 |
|
microsoft/phi-3-medium-128k-instruct
|
Nvidia | $1.00 | $1.00 | — | — | — | — | — |
|
microsoft/phi-4-mini-instruct
|
Nvidia | — | — | — | — | — | — | — |
|
minimaxai/minimax-m2.7
Reasoning
Tools
Open
|
Nvidia | $0.30 | $1.20 | 204.8K | 131.1K | P87 | P30 | P49 |
|
mistral-small-3.1-24b-instruct-2503
|
Nvidia | — | — | — | — | — | — | — |
|
moonshotai/kimi-k2-0905-preview
|
Nvidia | — | — | — | — | — | — | P59 |
|
moonshotai/kimi-k2.5
Reasoning
Tools
Vision
Open
|
Nvidia | $0.38 | $1.72 | 262.1K | 262.1K | — | — | — |
|
moonshotai/kimi-k2-instruct
|
Nvidia | — | — | — | — | — | — | — |
|
moonshotai/kimi-k2-instruct-0905
|
Nvidia | — | — | — | — | — | — | — |
|
moonshotai/kimi-k2-thinking
Reasoning
Tools
Open
|
Nvidia | $0.60 | $2.50 | 262.1K | 262.1K | — | — | — |
|
nemoretriever-ocr-v1
|
Nvidia | — | — | — | — | — | — | — |
|
nvidia/cosmos-nemotron-34b
|
Nvidia | — | — | — | — | — | — | — |
|
nvidia/llama-3.1-nemotron-70b-instruct
Tools
|
Nvidia | $1.20 | $1.20 | 128K | 4.1K | — | — | — |
|
nvidia/llama-3.1-nemotron-ultra-253b-v1
Reasoning
Tools
|
Nvidia | $0.60 | $1.80 | 131.1K | 8.2K | — | — | P9 |
|
nvidia/llama-3.3-nemotron-super-49b-v1
|
Nvidia | $0.10 | $0.40 | 128K | 4.1K | — | — | — |
|
nvidia/llama-3.3-nemotron-super-49b-v1.5
|
Nvidia | $0.10 | $0.40 | 128K | 4.1K | — | — | P9 |
|
nvidia/nemoretriever-ocr-v1
|
Nvidia | — | — | — | — | — | — | — |
|
nvidia/nemotron-3-super-120b-a12b
Reasoning
Tools
Open
|
Nvidia | $0.20 | $0.80 | 262.1K | 262.1K | — | — | P18 |
|
nvidia/parakeet-tdt-0.6b-v2
|
Nvidia | — | — | — | — | — | — | — |
|
openai/gpt-oss-120b
|
Nvidia | $0.04 | $0.40 | — | — | — | — | — |
|
openai/whisper-large-v3
|
Nvidia | — | — | — | — | — | — | — |
|
parakeet-tdt-0.6b-v2
|
Nvidia | — | — | — | — | — | — | — |
|
phi-4-multimodal-instruct
|
Nvidia | — | — | — | — | — | — | — |
|
qwen3-235b-a22b
|
Nvidia | — | — | — | — | — | — | P26 |
|
qwen3-coder-480b-a35b-instruct
|
Nvidia | — | — | — | — | P26 | P49 | P32 |
|
qwen/qwen2.5-coder-7b-instruct
Tools
Open
|
Nvidia | $0.03 | $0.09 | 128K | 4.1K | — | — | — |
|
qwen/qwen3-235b-a22b
Reasoning
Tools
|
Nvidia | $0.13 | $0.60 | 131.1K | 8.2K | — | — | P26 |
|
qwen/qwen3.5-397b-a17b
Reasoning
Tools
Vision
Open
|
Nvidia | $0.39 | $2.34 | 262.1K | 8.2K | P78 | P37 | P83 |
|
qwen/qwen3-coder-480b-a35b-instruct
|
Nvidia | — | — | — | — | P26 | P49 | P32 |
|
qwen/qwen3-next-80b-a3b-instruct
|
Nvidia | $0.09 | $1.10 | — | — | P18 | P82 | P44 |
|
qwen/qwen3-next-80b-a3b-thinking
Reasoning
Tools
Open
|
Nvidia | $0.10 | $0.78 | 262.1K | 16.4K | — | — | P21 |
|
qwen/qwq-32b
Reasoning
Open
|
Nvidia | $0.15 | $0.58 | 128K | 4.1K | — | — | — |
|
whisper-large-v3
|
Nvidia | — | — | — | — | — | — | — |
|
deepseek-v3.2
Reasoning
Tools
Open
|
Ollama Cloud | $0.40 | $1.20 | 163.8K | 65.5K | — | — | — |
|
gemini-3-flash-preview
Reasoning
Tools
Vision
Open
|
Ollama Cloud | $0.50 | $3.00 | 1.0M | 65.5K | P49 | P88 | — |
|
gemini-3-pro-preview
Reasoning
Tools
Vision
Open
|
Ollama Cloud | $2.00 | $12.00 | 1.0M | 64K | P83 | P71 | — |
|
glm-4.6
Reasoning
Tools
Open
|
Ollama Cloud | $0.30 | $0.90 | 202.8K | 131.1K | P39 | P60 | P60 |
|
glm-4.7
Reasoning
Tools
Open
|
Ollama Cloud | $0.06 | $0.40 | 202.8K | 131.1K | P66 | P68 | P74 |
|
glm-5
Reasoning
Tools
Open
|
Ollama Cloud | $0.95 | $3.15 | 202.8K | 131.1K | P89 | P45 | — |