Skip to content

DeepInfra

Pricing page

696 listings across 263 models

Page 3 of 11. The lists below split this page's listings into those sold by DeepInfra, run by DeepInfra, or sent to DeepInfra by a marketplace.

Sold by DeepInfra

23 listings on this page sold by DeepInfra.

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
Claude Sonnet 4deepinfra/anthropic/claude-4-sonnet
$3.30$16.50200K
GLM 4.7fp4
$0.40cache read $0.08$1.75203K
MiMo V2.5
$0.40cache read $0.08$2.00262KNot measured
Inkling FP4deepinfra/thinkingmachines/Inkling · fp8
$0.95cache read $0.16$4.05524K
Kimi K2.7 Code
$0.68cache read $0.136$3.40cache write $0.85262K
MiniMax M3fp8
$0.28cache read $0.056$1.10524K
Qwen3.5 122B-A10B
$0.29$2.40262KNot measuredNot measured
Nemotron 3.5 Super VLnvidia/NVIDIA-Nemotron-3.5-Super-VL · fp4
Not enough data yet$0.15cache read $0.02$0.50262KNot measured
Ling 3.0 Flash
Not enough data yet$0.06cache read $0.012$0.18131KNot measuredNot measured
Qwen3.5 27Bfp8
$0.26$2.60262KNot measured
Gemini 3.1 Flash Lite
$0.25$1.501M
Qwen3 Max
$1.20cache read $0.24$6.00256K
Qwen3 Maxdeepinfra/Qwen/Qwen3-Max-Thinking · thinking
$1.20cache read $0.24$6.00256K
DeepSeek V3.2fp4
$0.26cache read $0.13$0.38164KNot measured
Gemma 4 26B A4Bgoogle/gemma-4-26B-A4B-it · fp8
$0.07$0.34262K
Ling 3.0 Flash VL
Not enough data yet——Not published by the providerNot measuredNot measured
Doubao Seed 1.8ByteDance/Seed-1.8
Not enough data yet$0.25cache read $0.05$2.00256KNot enough data yetNot measuredNot measured
$0.30$2.90262KNot measuredNot measured
Nemotron 3 Ultranvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B
$0.50cache read $0.10$2.20262K
Qwen3 Embedding 4B
Not enough data yet——Not published by the providerNot enough data yetNot measuredNot measured
Claude Sonnet 3.7deepinfra/anthropic/claude-3-7-sonnet-latest · latest
$3.30cache read $0.33$16.50200K
Qwen3.6 27Bfp8
$0.32$3.20262KNot measured
GLM 4.6fp4
$0.50cache read $0.10$2.00203KNot measured

Run by DeepInfra

72 listings on this page where DeepInfra 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
GLM 4.7
 Hugging Face$0.40$1.75203K
MiMo V2.5
 Hugging Face$0.14$0.28262KNot measured
Inkling FP4deepinfra/thinkingmachines/Inkling
 Eden AI$0.95cache read $0.16$4.05524K
Kimi K2.7 Code
 Hugging Face$0.68$3.40262K
MiniMax M3
 Hugging Face$0.28$1.10524K
Qwen3.5 122B-A10B
 Hugging Face$0.29$2.40262KNot measuredNot measured
Ling 3.0 Flash Fin
 Hugging FaceNot enough data yet$0.06$0.18262KNot measuredNot measured
Nemotron 3.5 Super VLfp4 · 🇺🇸 US
 NanoGPTNot enough data yet$0.1575cache read $0.021$0.525Not published by the providerNot measured
Step 3.5 Flash
 Eden AI$0.09cache read $0.02$0.30262KNot measuredNot measured
Ling 3.0 Flash
 Hugging FaceNot enough data yet$0.06$0.18131KNot measuredNot measured
Qwen3.5 27B
 Hugging Face$0.26$2.60262KNot measured
Qwen3 Max
 Eden AI$1.20cache read $0.24$6.00256K
DeepSeek V3.2
 Hugging Face$0.26$0.38164KNot measured
NVIDIA Nemotron 3.5 Super VL 120Bnvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16 · bf16
 Hugging Face$0.15$0.50262KNot measuredNot measured
Gemma 4 26B A4Bgoogle/gemma-4-26B-A4B-it
 Hugging Face$0.07$0.34262K
Ling 3.0 Flash VL
 Hugging FaceNot enough data yet$0.06$0.18131KNot measuredNot measured
Doubao Seed 1.8deepinfra/ByteDance/Seed-1.8
 RequestyNot enough data yet$0.25cache read $0.05$2.00256KNot enough data yetNot measuredNot measured
 Eden AI$0.23cache read $0.20$2.30262KNot measuredNot measured
Nemotron 3 Ultradeepinfra/nemotron-3-ultra-550b-a55b
 Eden AI$0.50cache read $0.10$2.20262K
Qwen3.6 27B
 Hugging Face$0.32$3.20262KNot measured
GLM 4.6
 Hugging Face$0.50$2.00203KNot measured
Show all 72 listings

Showing 21 of 72: one listing for each model.

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

How this data works