API pricing

Azure OpenAI Pricing

Azure OpenAI charges from $0.040 per 1 million output tokens, depending on the model. Ministral 3B is the cheapest at $0.040/1M output and $0.040/1M input; its current flagship GPT-5.6 Sol costs $30.00/1M output. The largest context window is 1.1M tokens (Eu GPT 5.4). Prices are USD, current as of August 11, 2026.

Azure OpenAI carries the OpenAI model lineup under Azure billing, with regional availability and quota managed per deployment. Standard (pay-as-you-go) token rates are listed below; provisioned throughput units are priced separately.

Last updated · synced weekly from the upstream model catalog

Cheapest input

$0.040/1M

Ministral 3B

Cheapest output

$0.040/1M

Ministral 3B

Longest context

1.1M

Eu GPT 5.4

Models priced

150

Avg $17.36/1M output

Pricing by model

All prices in USD per 1 million tokens. Showing 80 of 150 priced models, cheapest first. The batch column is the asynchronous batch-API rate, 50% below the standard output rate on the 14 models that publish one.

ModelInput / 1MOutput / 1MBatch out / 1MContext
Model Router
VisionTools
$0.140200K
Ministral 3B
Tools
$0.040$0.040128K
Mistral Small 3.1
VisionTools
$0.100$0.300128K
Phi-4-mini
Tools
$0.075$0.300128K
Phi-4-mini-reasoning
ReasoningTools
$0.075$0.300128K
Phi-4-multimodal
Vision
$0.080$0.320128K
GPT-4.1 nano
VisionToolsCache
$0.100$0.400$0.20050%1.0M
GPT-5 Nano
VisionReasoningToolsCache
$0.050$0.400400K
Eu GPT 5 Nano 2025 08.07$0.055$0.440272K
Us GPT 4.1 Nano 2025 04.14$0.110$0.440$0.22050%1.0M
Us GPT 5 Nano 2025 08.07$0.055$0.440272K
Grok 4.1 Fast (Non-Reasoning)
VisionToolsCache
$0.200$0.500128K
Grok 4.1 Fast (Reasoning)
VisionReasoningToolsCache
$0.200$0.500128K
Phi-4$0.125$0.500128K
Phi-4-reasoning
Reasoning
$0.125$0.50032K
Phi-4-reasoning-plus
Reasoning
$0.125$0.50032K
DeepSeek-V4-Flash
Reasoning
$0.190$0.5101.0M
Global Standard GPT 4o Mini$0.150$0.600128K
GPT-4o mini
VisionToolsCache
$0.150$0.600128K
Eu GPT 4o Mini 2024 07.18$0.165$0.660128K
GPT 4o Mini 2024 07.18$0.165$0.660128K
Us GPT 4o Mini 2024 07.18$0.165$0.660128K
Llama-3.3-70B-Instruct
Tools
$0.710$0.710128K
Llama 4 Scout 17B 16E Instruct
VisionTools
$0.200$0.780128K
Codestral 25.01
Tools
$0.300$0.900256K
Llama 4 Maverick 17B 128E Instruct FP8
VisionTools
$0.250$1.001.0M
GPT-5.4 Nano
VisionReasoningToolsCache
$0.200$1.25400K
Eu GPT 5.6 Luna$0.220$1.321.1M
Us GPT 5.6 Luna$0.220$1.321.1M
GPT 3.5 Turbo$0.500$1.504K
GPT-3.5 Turbo 0125$0.500$1.5016K
GPT-4.1 mini
VisionToolsCache
$0.400$1.60$0.80050%1.0M
DeepSeek-V3.2
ReasoningTools
$0.580$1.68128K
DeepSeek-V3.2-Speciale
Reasoning
$0.580$1.68128K
Us GPT 4.1 Mini 2025 04.14$0.440$1.76$0.88050%1.0M
GPT-3.5 Turbo 1106$1.00$2.0016K
GPT-3.5 Turbo Instruct$1.50$2.004K
GPT-5 Mini
VisionReasoningToolsCache
$0.250$2.00400K
GPT-5.1 Codex Mini
VisionReasoningToolsCache
$0.250$2.00400K
Mistral Medium 3
VisionTools
$0.400$2.00128K
Eu GPT 5 Mini 2025 08.07$0.275$2.20272K
Us GPT 5 Mini 2025 08.07$0.275$2.20272K
GPT Audio Mini 2025 10.06$0.600$2.40128K
Kimi K2.5
VisionReasoningTools
$0.600$3.00262K
DeepSeek-V4-Pro
Reasoning
$1.74$3.481.0M
GPT 35 Turbo 16K$3.00$4.0016K
GPT 35 Turbo 16K 0613$3.00$4.0016K
Kimi K2.6
VisionReasoningTools
$0.950$4.00262K
Kimi K2.7 Code
VisionReasoningToolsCache
$0.950$4.00262K
o1 Mini 2024 09.12$1.10$4.40128K
o3-mini
ReasoningToolsCache
$1.10$4.40200K
o4-mini
VisionReasoningToolsCache
$1.10$4.40200K
GPT-5.4 Mini
VisionReasoningToolsCache
$0.750$4.50400K
Eu o1 Mini 2024 09.12$1.21$4.84$2.4250%128K
Eu o3 Mini 2025 01.31$1.21$4.84$2.4250%200K
o1 Mini$1.21$4.84128K
Us o1 Mini 2024 09.12$1.21$4.84$2.4250%128K
Us o3 Mini 2025 01.31$1.21$4.84$2.4250%200K
Us o4 Mini 2025 04.16$1.21$4.84200K
Claude Haiku 4.5
VisionReasoningToolsCache
$1.00$5.00200K
DeepSeek-R1
Reasoning
$1.35$5.40164K
Codex Mini
ReasoningToolsCache
$1.50$6.00200K
GPT-5.6 Luna
VisionReasoningToolsCache
$1.00$6.001.1M
Grok 4.20 (Non-Reasoning)
Tools
$2.00$6.00262K
Grok 4.20 (Reasoning)
ReasoningTools
$2.00$6.00262K
GPT-4.1
VisionToolsCache
$2.00$8.00$4.0050%1.0M
o3
VisionReasoningToolsCache
$2.00$8.00200K
Us GPT 4.1 2025 04.14$2.20$8.80$4.4050%1.0M
Us o3 2025 04.16$2.20$8.80200K
Claude Sonnet 5
VisionReasoningToolsCache
$2.00$10.001.0M
Command A
ReasoningTools
$2.50$10.00131K
Global GPT 4o 2024 08.06$2.50$10.00128K
Global GPT 5.1$1.25$10.00272K
Global GPT 5.1 Chat$1.25$10.00128K
Global Standard GPT 4o 2024 08.06$2.50$10.00128K
GPT 4o Audio Preview 2024 12.17$2.50$10.00128K
GPT 4o Mini Audio Preview 2024 12.17$2.50$10.00128K
GPT 5 Chat$1.25$10.00128K
GPT 5 Chat Latest$1.25$10.00128K
GPT-5.4 Pro
VisionReasoningTools
$30.00$180.001.1M

A dash in the batch column means our catalog carries no published batch rate for that model — not that the model has no batch tier. Batch coverage in the upstream pricing data is uneven.

Frequently asked questions

How much does Azure OpenAI cost per 1M tokens?

Azure OpenAI pricing starts at $0.040 per 1 million output tokens (Ministral 3B) across 150 models, with its current flagship GPT-5.6 Sol at $30.00. Older premium models in the catalog list higher. Rates current as of August 11, 2026.

What is the cheapest Azure OpenAI model?

Ministral 3B is the cheapest Azure OpenAI model on both axes — $0.040 per 1M input tokens and $0.040 per 1M output. It is the right default for high-volume, low-complexity work such as classification, extraction and routing.

What is the largest Azure OpenAI context window?

Eu GPT 5.4 has the largest context window in the Azure OpenAI catalog at 1.1M input tokens, with up to 128K output tokens per response.

Does Azure OpenAI support prompt caching?

Yes. GPT-5 Nano reads cached input at $0.010 per 1M tokens, against $0.050 per 1M uncached. Caching pays off when a long system prompt or document is reused across many requests.

Does Azure OpenAI offer batch pricing?

Yes — 14 Azure OpenAI models in this catalog publish a discounted rate for asynchronous batch jobs, at 50% off output tokens. Us GPT 4.1 2025 04.14 bills $4.40 per 1M output in batch against $8.80 synchronously. Batch trades real-time responses for the lower rate, so it suits backfills, evaluations and bulk enrichment rather than user-facing calls.

Which Azure OpenAI models support reasoning or vision?

The Azure OpenAI catalog includes 50 reasoning models, 53 vision models, 62 with tool calling. Reasoning models bill their internal thinking as output tokens, so they cost more per visible response than the headline rate suggests.

How do I calculate my actual Azure OpenAI bill?

Multiply your input tokens by the input rate and your output tokens by the output rate, both per million, then add retries and any conversation history resent on each turn. Calcaas does this against your real usage pattern and shows the margin left at your price point.

Other providers

What will this actually cost you?

Per-token rates only tell you half the story. Calcaas multiplies them by your real usage — prompt size, response length, retries and conversation history — then shows the margin left at your price point.

Open the free cost calculator