Skip to content

DeepInfra

Pricing page

696 listings across 263 models

Page 5 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

22 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
Not enough data yet——Not published by the providerNot enough data yetNot measuredNot measured
Nemotron 3.5 Lightningnvidia/NVIDIA-Nemotron-3.5-Lightning · bf16
Not enough data yet$0.06cache read $0.04$0.16262KNot measuredNot measured
GLM 4.7 Flash
$0.06cache read $0.01$0.40203KNot measuredNot measured
QwQ 32B
$0.15$0.40131KNot measured
Gemini 3.1 Flash Imagegoogle/nano-banana-2
Not enough data yet——Not published by the providerNot enough data yetNot measuredNot measured
Qwen3 32Bfp8
$0.08$0.2841KNot measured
DeepSeek V3
$0.32$0.89164K
DeepSeek V3deepinfra/deepseek-ai/DeepSeek-V3-0324 · 0324
$0.24cache read $0.135$0.90164K
Qwen3 30B A3B
$0.12$0.5041KNot measured
Qwen3 14Bfp8
$0.12$0.2441KNot measured
Gemma 4 E4B-it
$0.02$0.10131KNot enough data yetNot measuredNot measured
Mistral Small 3.2 24B Instructmistralai/Mistral-Small-3.2-24B-Instruct-2506 · 2506
Not enough data yet$0.075$0.20128KNot measuredNot measured
Qwen3.5 9Bbf16
$0.10$0.15262KNot measured
Llama 4 Maverickdeepinfra/meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8 · fp8
$0.20$0.801M
qwen3-vl-30bQwen/Qwen3-VL-30B-A3B-Instruct
Not enough data yet$0.15$0.60262KNot measuredNot measured
GPT OSS 20bbf16
$0.03cache read $0.015$0.14131K
Qwen 2.5 VL 32B Instruct
Not enough data yet$0.20$0.60128KNot measuredNot measured
Granite 4.2 8Bbf16
——Not published by the providerNot enough data yetNot measuredNot measured
Nemotron Nano 9b V2deepinfra/nvidia/NVIDIA-Nemotron-Nano-9B-v2
Not enough data yet$0.04$0.16131KNot measuredNot measured
Veo 3.1
Not enough data yet——Not published by the providerNot enough data yetNot measuredNot measured
Qwen3 Embedding 0.6B
Not enough data yet——Not published by the providerNot enough data yetNot measuredNot measured
Nemotron 3 Nano 30B A3B
$0.05cache read $0.025$0.20262KNot measuredNot measured

Run by DeepInfra

55 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
Nemotron 3.5 Lightningbf16 · 🇺🇸 US
 NanoGPTNot enough data yet$0.063cache read $0.0315$0.168Not published by the providerNot measuredNot measured
GLM 4.7 Flash
 Eden AI$0.06cache read $0.01$0.40203KNot measuredNot measured
Qwen3 32B
 Hugging Face$0.08$0.2841KNot measured
DeepSeek V3
 Eden AI$0.32$0.89164K
Nemotron 3.5 Lightning 30B A3Bnvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16 · bf16
 Hugging Face$0.06$0.16262KNot measuredNot measured
Qwen3 30B A3B
 Hugging Face$0.12$0.5041KNot measured
Granite 4.2 30B
 Hugging Face$0.16$0.65131KNot enough data yetNot measuredNot measured
Qwen3 14B
 Hugging Face$0.12$0.2441KNot measured
Mistral Small 3.2 24B Instructfp8
 OpenRouterNot enough data yet$0.075$0.20128KNot measuredNot measured
Qwen3.5 9B
 Hugging Face$0.10$0.15262KNot measured
Llama 3.1 405B Instructdeepinfra/meta-llama/Meta-Llama-3.1-405B-Instruct
 Requesty$0.80$0.80131KNot measuredNot measured
qwen3-vl-30bdeepinfra/Qwen/Qwen3-VL-30B-A3B-Instruct
 Eden AINot enough data yet$0.15$0.60262KNot measuredNot measured
GPT OSS 20b
 Eden AI$0.03cache read $0.015$0.14131K
Granite 4.2 8B
 Eden AI$0.06cache read $0.015$0.25131KNot enough data yetNot measuredNot measured
Qwen3 Embedding 0.6B
 LlmgatewayNot enough data yet$0.01—Not published by the providerNot enough data yetNot measuredNot measured
Nemotron 3 Nano 30B A3B
 Eden AI$0.05cache read $0.025$0.20262KNot measuredNot measured
Granite 4.2 3B
 Hugging Face$0.03$0.12131KNot enough data yetNot measuredNot measured
Show all 55 listings

Showing 17 of 55: one listing for each model.

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

How this data works