Skip to content

Runanywhere

Pricing page

17 listings across 8 models

Run by Runanywhere

17 listings where Runanywhere runs the model. Another provider sells these listings.

Default order. Select a score for details.

About these columns
llminfo IQ
llminfo IQ (capability index). How llminfo IQ is computed
Coding IQ
llminfo Coding IQ (coding capability, its own scale). How Coding IQ is computed
Value
Value for money. 50 means as expected for its results. Above 50, cheaper per task. How Value for money works
Yap
Tokens used per coding task vs. models with the same results. Includes agents that write code. Chattiness on maths doesn't predict it. How the Yap score works
DeepSeek V4.1 Flash 1017fp8 · 🇺🇸 US
 NanoGPT$0.2048cache read $0.0063$1.05Not published by the provider
Kimi K3mxfp4 · 🇺🇸 US
 NanoGPT$3.0713cache read $0.315$15.75Not published by the provider
GLM 5.3fast · fp8 · 🇺🇸 US
 NanoGPT$1.47cache read $0.273$4.62Not published by the provider
DeepSeek V4.1 Flashfp8 · 🇺🇸 US
 NanoGPT$0.2888cache read $0.0063$1.26Not published by the provider
GLM 5.3 Flashfp8 · 🇺🇸 US
 NanoGPT$0.1575cache read $0.0315$0.525Not published by the provider
DeepSeek V4 Flash 0731fp8 · 🇺🇸 US
 NanoGPT$0.3077cache read $0.0098$0.924Not published by the provider
DeepSeek V4 Flashdeepseek/deepseek-v4-flash-latest · latest · fp8 · 🇺🇸 US
 NanoGPT$0.2048cache read $0.0063$1.05Not published by the provider
MiniMax M3minimax/minimax-m3:thinking · thinking · bf16 · 🇺🇸 US
 NanoGPT$0.315cache read $0.063$1.26Not published by the provider
Hermes Highfast · fp8 · 🇺🇸 US
 NanoGPTNot enough data yetNot enough data yet$1.47cache read $0.273$4.62Not published by the providerNot enough data yetNot measuredNot measured
Hermes Lowfast · fp8 · 🇺🇸 US
 NanoGPTNot enough data yetNot enough data yet$1.47cache read $0.273$4.62Not published by the providerNot enough data yetNot measuredNot measured
Hermes Mediumfast · fp8 · 🇺🇸 US
 NanoGPTNot enough data yetNot enough data yet$1.47cache read $0.273$4.62Not published by the providerNot enough data yetNot measuredNot measured
Show all 17 listings

Showing 11 of 17: one listing for each model.

Data credits: Epoch AI Benchmarking Hub, CC BY 4.0 (licence)

How this data works