Skip to content

DeepInfra

Pricing page

696 listings across 263 models

Page 2 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

24 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
Qwen3.7 Max
$2.50cache read $0.50$7.50256K
MiMo V2.6 Flashfp8
$0.14cache read $0.0028$0.281MNot measured
GLM 5.2fp4
$0.75cache read $0.14$2.40cache write $0.93751M
Claude Sonnet 4.6
$3.00$15.001M
GLM 5.3 Flashfp4
$0.15cache read $0.03$0.501M
Step 5 Previewfp8
$1.00cache read $0.10$2.701MNot measuredNot measured
Kimi K2.6fp4
$0.75cache read $0.15$3.50262K
DeepSeek V4 Flash 0731fp8
$0.06cache read $0.015$0.181M
Not enough data yet——Not published by the providerNot enough data yetNot measuredNot measured
GLM 5.1
$1.05cache read $0.205$3.50203K
$1.30cache read $0.10$2.601M
Qwen3.5 397B A17Bfp8
$0.45cache read $0.22$3.00262K
GLM 5
$0.60cache read $0.12$2.08203K
Qwen 3.8 27Bfp8
$0.40cache read $0.04$3.00262KNot measured
DeepSeek V4 Flashfp8
$0.09cache read $0.018$0.18cache write $0.11251M
Doubao Seed 2.0 ProByteDance/Seed-2.0-pro
$0.50cache read $0.10$3.00256KNot enough data yetNot measuredNot measured
$1.25$10.001M
Kimi K2.5
$0.45cache read $0.07$2.25262K
Gemma 4 31B ITfp8
$0.20$0.40262K
Muse Glimmer 30Bbf16
Not enough data yet$0.30cache read $0.04$1.20131KNot measuredNot measured
MiMo V2.5 Pro
$1.00cache read $0.20$3.001MNot measured
Claude Opus 4deepinfra/anthropic/claude-4-opus
$16.50$82.50200K
Inkling Smallfp4
$0.45cache read $0.10$1.20524K
Hy3 (Deep Infra)deepinfra/tencent/Hy3
$0.14cache read $0.035$0.58262KNot measuredNot measured

Run by DeepInfra

100 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
MiMo V2.6 FlashXiaomiMiMo/MiMo-V2.6-Flash-RL
 Hugging Face$0.14$0.281MNot measured
GLM 5.2
 Hugging Face$0.5625$1.801M
 Hugging Face$0.1005$0.3351M
 Eden AI$1.00cache read $0.10$2.701MNot measuredNot measured
Kimi K2.6
 Hugging Face$0.75$3.50262K
DeepSeek V4 Flash 0731
 Eden AI$0.06cache read $0.015$0.181M
 LlmgatewayNot enough data yet$0.01—Not published by the providerNot enough data yetNot measuredNot measured
DeepSeek V4.1 Flash 0910deepseek/deepseek-v4.1-flash:batch · batch+fp8 · fp8
 OpenRouterNot enough data yet$0.112cache read $0.0034$0.3361MNot enough data yetNot measuredNot measured
GLM 5.1
 Hugging Face$1.05$3.50203K
 Hugging Face$1.30$2.601M
 Hugging Face$0.45$3.00262K
GLM 5
 Hugging Face$0.60$2.08203K
Qwen 3.8 27B
 Hugging Face$0.15$1.875262KNot measured
DeepSeek V4 Flash
 Hugging Face$0.09$0.181M
Doubao Seed 2.0 Prodeepinfra/ByteDance/Seed-2.0-pro
 Requesty$0.50cache read $0.10$3.00256KNot enough data yetNot measuredNot measured
Kimi K2.5
 Eden AI$0.45cache read $0.07$2.25262K
 Hugging Face$0.20$0.40262K
 Eden AINot enough data yet$0.30cache read $0.04$1.20131KNot measuredNot measured
MiMo V2.5 Pro
 Hugging Face$1.00$3.001MNot measured
 Eden AI$0.45cache read $0.10$1.20524K
Hy3 (Deep Infra)deepinfra/tencent/Hy3
 Eden AI$0.13cache read $0.033$0.53262KNot measuredNot measured
Show all 100 listings

Showing 21 of 100: one listing for each model.

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

How this data works