Skip to content

Microsoft Azure

Pricing page

780 listings across 303 models

Page 3 of 13. The lists below split this page's listings into those sold by Microsoft Azure, run by Microsoft Azure, or sent to Microsoft Azure by a marketplace.

Sold by Microsoft Azure

53 listings on this page sold by Microsoft Azure.

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 4.5
$3.00cache read $0.30$15.00cache write $3.75200K
GLM 5azure_ai/FW-GLM-5
$1.10cache read $0.22$3.52200K
Mistral Large 4azure_ai/mistral-large-4-latest · latest
$0.70$2.101M
Grok 4.20azure_ai/grok-4-20-non-reasoning · non-reasoning
$1.25$2.50262K
DeepSeek V4 Flashazure_ai/FW-DeepSeek-V4-Flash
$0.15cache read $0.03$0.311M
GPT-5.1 Codex
$1.25cache read $0.125$10.00272KNot measured
Not enough data yet$0.58$1.68128KNot measuredNot measured
Kimi K2.5azure_ai/FW-Kimi-K2.5
$0.66cache read $0.11$3.30262K
OpenAI o3o3-0416 · 0416
$2.00cache read $0.50batch $1.00$8.00batch $4.00Not published by the provider
GPT-5.4 mini
$0.75cache read $0.075batch $0.375$4.50batch $2.25272K
GPT-5 Codex
$1.25cache read $0.125$10.00272KNot measuredNot measured
Inkling FP4azure_ai/FW-Inkling
$1.10cache read $0.19$4.461M
Kimi K2.7 Codeazure_ai/FW-Kimi-K2.7-Code
$1.05cache read $0.21$4.40262K
MiniMax M3azure_ai/FW-MiniMax-M3
$0.33cache read $0.066$1.32512K
O1 Preview
$15.00cache read $7.50$60.00Not published by the providerNot measured
Grok 4
$3.00$15.00262KNot measured
DeepSeek V3.2azure_ai/FW-DeepSeek-V3.2
$0.62cache read $0.31$1.85164KNot measured
Not enough data yet$2.00cache read $0.20$8.00256KNot enough data yetNot measuredNot measured
GPT-5 mini
$0.25cache read $0.025batch $0.125$2.00batch $1.00272K
O1 Pro
Not enough data yet$150.00cache read $75.00batch $75.00$600.00batch $300.00Not published by the providerNot measuredNot measured
Grok 4.3
$1.25>200k $2.50cache read $0.20$2.50>200k $5.00200KNot measured
Nemotron 3 Ultraazure_ai/FW-Nemotron-3-Ultra-NVFP4 · nvfp4
$0.66cache read $0.13$2.64262K
o4 Minio4-mini-0416 · 0416
$1.10cache read $0.275batch $0.55$4.40batch $2.20Not published by the provider
GPT-5.1 Codex Mini
Not enough data yet$0.25cache read $0.025$2.00272KNot measuredNot measured
$0.60$2.50262K
Show all 53 listings

Showing 25 of 53: one listing for each model.

Run by Microsoft Azure

26 listings on this page where Microsoft Azure 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
Claude Sonnet 4.5global
 OpenRouter$3.00cache read $0.30$15.00cache write $3.75200K
DeepSeek V4 Flash
 Hugging Face$0.21$0.561M
GPT-5.1 Codex
 Eden AI$1.25cache read $0.125$10.00272KNot measured
OpenAI o3o3
 Llmgateway$2.00cache read $0.50$8.00Not published by the provider
GPT-5.4 mini
 Llmgateway$0.75cache read $0.075$4.50Not published by the provider
GPT-5 mini
 Cortecs AI——400K
Grok 4.3
 Llmgateway$1.25cache read $0.20$2.50Not published by the providerNot measured
o4 Miniazure/o4-mini@eastus2 · 🇺🇸 eastus2
 Requesty$1.10cache read $0.275$4.40200K
 Eden AINot enough data yet$0.25cache read $0.025$2.00272KNot measuredNot measured
Show all 26 listings

Showing 9 of 26: one listing for each model.

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

How this data works