Skip to content

Requesty

Pricing page

442 listings across 154 models

Page 5 of 7. The lists below split this page's listings into those sold by Requesty, run by Requesty, or sent to Requesty by a marketplace.

Sold by Requesty

51 listings on this page sold by Requesty.

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
Codestral 25.01mistral/codestral-latest · latest
Inference by Mistral AI
Not enough data yet$0.33$0.99131KNot measured
Qwen Plus
Inference by Alibaba Cloud
Not enough data yet$0.40$1.20cache write $0.40131KNot measuredNot measured
Inference by Google
Not enough data yet$0.50$2.00131KNot enough data yetNot measuredNot measured
Qwen3 32B
Inference by DeepInfra
$0.10$0.3041KNot measured
GPT-4.1 miniazure/gpt-4.1-mini@eastus2 · 🇺🇸 eastus2
Inference by Microsoft Azure
$0.40cache read $0.10$1.601MNot measured
GPT-5 nano
Inference by Microsoft Azure
$0.05cache read $0.005$0.40200K
Inference by Mistral AI
$1.65$8.25262KNot measured
Qwen3 30B A3B Instructnebius/qwen/qwen3-30b-a3b-instruct-2507
Inference by Nebius AI Studio
$0.10$0.30128KNot measured
Mistral Mediummistral/mistral-medium-latest · latest
Inference by Mistral AI
$0.44$2.20131KNot measured
DeepSeek V3
Inference by DeepInfra
$0.85$0.90128K
Inference by NVIDIA NIM
——1MNot measuredNot measured
GPT 4o
Inference by OpenAI
$2.50cache read $1.25$10.00128KNot measured
Gemini 2.5 Flash-Lite
Inference by Google
$0.10cache read $0.01$0.40cache write $0.18331M
Devstral Small 2505mistral/devstral-small-latest · latest
Inference by Mistral AI
$0.11$0.33131KNot measuredNot measured
Llama 3.1 405B Instructdeepinfra/meta-llama/Meta-Llama-3.1-405B-Instruct
Inference by DeepInfra
$0.80$0.80131KNot measuredNot measured
Llama 4 Mavericknovita/meta-llama/llama-4-maverick-17b-128e-instruct-fp8 · fp8
Inference by Novita AI
$0.20$0.851M
Qwen Max
Inference by Alibaba Cloud
$1.60$6.40cache write $1.6033KNot measuredNot measured
GPT OSS 20b
Inference by Groq
$0.10$0.50131K
Inference by DeepInfra
$0.05$0.20262KNot measuredNot measured
Inference by DeepInfra
Not enough data yet$0.12$0.30131KNot measuredNot measured
Qwen Turbo
Inference by Alibaba Cloud
Not enough data yet$0.05$0.20cache write $0.051MNot measuredNot measured
Inference by DeepInfra
$0.23$0.40131KNot measuredNot measured
Qwen2.5 VL 72B Instructparasail/parasail-qwen25-vl-72b-instruct
Inference by Parasail
Not enough data yet$0.70$0.7033KNot measuredNot measured
GPT-4o miniazure/gpt-4o-mini@eastus2 · 🇺🇸 eastus2
Inference by Microsoft Azure
$0.15cache read $0.075$0.60128KNot measured
Inference by Nebius AI Studio
$0.10$0.30128KNot measured
Show all 51 listings

Showing 25 of 51: one listing for each model.

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

How this data works