Microsoft Azure API Pricing
Complete pricing for all Microsoft Azure models. Input/output costs per 1M tokens, context windows, and rate limits.
Billing terms: priced in USD per 1M tokens unless a row states otherwise; official direct rates are listed separately from third-party channels, and regional prices are kept distinct. Record updated 2026-10-11.
Microsoft Azure API Pricing Calculator
Select a model to estimate monthly cost using its listed rates on each channel.
Workloads reusing system prompts, long documents, or conversation history hit more; channels without a cached rate are billed at the full input rate.
| Channel | Effective input | Output /1M | Est. / month |
|---|---|---|---|
| azure | $5.50(w/ cache) | $50.00 | $51.00 |
Formula: monthly cost = (input tokens × effective input rate + output tokens × output rate) ÷ 1,000,000 × calls. The effective input rate blends list and cached rates at your cache-hit share. Rates share the selected model and billing basis; your vendor bill is authoritative.
Currently available rates
Claude Fable 5
LLMazure-claude-fable-5Claude Fable 5.1
LLMazure-claude-fable-5-1Claude Haiku 4.5
LLMazure-claude-haiku-4-5Claude Haiku 5.5
LLMazure-claude-haiku-5-5Claude Mythos 5
LLMazure-claude-mythos-5Claude Opus 4.1
LLMazure-claude-opus-4-1Claude Opus 4.5
LLMazure-claude-opus-4-5Claude Opus 4.6
LLMazure-claude-opus-4-6Claude Opus 4.7
LLMazure-claude-opus-4-7Claude Opus 4.8
LLMazure-claude-opus-4-8Claude Opus 5
LLMazure-claude-opus-5Claude Opus 5.5
LLMazure-claude-opus-5-5Claude Sonnet 4.5
LLMazure-claude-sonnet-4-5Claude Sonnet 4.6
LLMazure-claude-sonnet-4-6Claude Sonnet 5
LLMazure-claude-sonnet-5Claude Sonnet 5.5
LLMazure-claude-sonnet-5-5Codestral 25.01
LLMazure-codestral-2501Codex Mini
LLMazure-codex-miniDeprecated endpoints may still be callable. Migrate before retirement.
Command A
LLMazure-cohere-command-aDeepSeek-R1
LLMazure-deepseek-r1Deprecated endpoints may still be callable. Migrate before retirement.
DeepSeek-V3.2
LLMazure-deepseek-v3.2DeepSeek-V3.2-Speciale
LLMazure-deepseek-v3.2-specialeDeepSeek-V4-Flash
LLMazure-deepseek-v4-flashDeepSeek-V4-Pro
LLMazure-deepseek-v4-proDeepSeek-V4.1-Flash
LLMazure-deepseek-v4.1-flashEmbed v3 English
Embedazure-cohere-embed-v3-englishEmbed v3 Multilingual
Embedazure-cohere-embed-v3-multilingualEmbed v4
Embedazure-cohere-embed-v-4-0GPT Chat Latest
LLMazure-gpt-chat-latestGPT Image 2.5 Flare
Image Genazure-gpt-image-2.5-flareGPT Image 2.5 Sunburst
Image Genazure-gpt-image-2.5-sunburstGPT-3.5 Turbo 0125
LLMazure-gpt-3.5-turbo-0125Deprecated endpoints may still be callable. Migrate before retirement.
GPT-3.5 Turbo 1106
LLMazure-gpt-3.5-turbo-1106Deprecated endpoints may still be callable. Migrate before retirement.
GPT-3.5 Turbo Instruct
LLMazure-gpt-3.5-turbo-instructDeprecated endpoints may still be callable. Migrate before retirement.
GPT-4 Turbo
LLMazure-gpt-4-turboDeprecated endpoints may still be callable. Migrate before retirement.
GPT-4 Turbo Vision
LLMazure-gpt-4-turbo-visionDeprecated endpoints may still be callable. Migrate before retirement.
GPT-4.1
LLMazure-gpt-4.1Deprecated endpoints may still be callable. Migrate before retirement.
GPT-4.1 mini
LLMazure-gpt-4.1-miniDeprecated endpoints may still be callable. Migrate before retirement.
GPT-4.1 nano
LLMazure-gpt-4.1-nanoDeprecated endpoints may still be callable. Migrate before retirement.
GPT-4o
LLMazure-gpt-4oDeprecated endpoints may still be callable. Migrate before retirement.
GPT-4o mini
LLMazure-gpt-4o-miniDeprecated endpoints may still be callable. Migrate before retirement.
GPT-5
LLMazure-gpt-5GPT-5 Mini
LLMazure-gpt-5-miniGPT-5 Nano
LLMazure-gpt-5-nanoGPT-5 Pro
LLMazure-gpt-5-proGPT-5-Codex
LLMazure-gpt-5-codexGPT-5.1
Image Genazure-gpt-5.1GPT-5.1 Codex
Image Genazure-gpt-5.1-codexGPT-5.1 Codex Max
LLMazure-gpt-5.1-codex-maxGPT-5.1 Codex Mini
LLMazure-gpt-5.1-codex-miniGPT-5.2
LLMazure-gpt-5.2GPT-5.2 Codex
LLMazure-gpt-5.2-codexGPT-5.3 Codex
LLMazure-gpt-5.3-codexGPT-5.4
LLMazure-gpt-5.4GPT-5.4 Mini
LLMazure-gpt-5.4-miniGPT-5.4 Nano
LLMazure-gpt-5.4-nanoGPT-5.4 Pro
LLMazure-gpt-5.4-proGPT-5.5
LLMazure-gpt-5.5GPT-5.6 Luna
LLMazure-gpt-5.6-lunaGPT-5.6 Sol
LLMazure-gpt-5.6-solGPT-5.6 Terra
LLMazure-gpt-5.6-terraGPT-6 Astra
LLMazure-gpt-6-astraGPT-6 Luna
LLMazure-gpt-6-lunaGPT-6 Sol
LLMazure-gpt-6-solGPT-6.1 Sol
LLMazure-gpt-6.1-solGPT-Image-1
Image Genazure-gpt-image-1GPT-Image-1.5
Image Genazure-gpt-image-1.5GPT-Image-2
Image Genazure-gpt-image-2Grok 4.1 Fast (Non-Reasoning)
LLMazure-grok-4-1-fast-non-reasoningGrok 4.1 Fast (Reasoning)
LLMazure-grok-4-1-fast-reasoningGrok 4.20 (Non-Reasoning)
LLMazure-grok-4-20-non-reasoningGrok 4.20 (Reasoning)
LLMazure-grok-4-20-reasoningGrok 4.6
LLMazure-grok-4.6Grok 4.7
LLMazure-grok-4.7Kimi K2.5
LLMazure-kimi-k2.5Kimi K2.6
LLMazure-kimi-k2.6Kimi K2.7 Code
LLMazure-kimi-k2.7-codeLlama 4 Maverick 17B 128E Instruct FP8
LLMazure-llama-4-maverick-17b-128e-instruct-fp8Llama 4 Scout 17B 16E Instruct
LLMazure-llama-4-scout-17b-16e-instructLlama-3.3-70B-Instruct
LLMazure-llama-3.3-70b-instructMinistral 3B
LLMazure-ministral-3bMistral Medium 3
LLMazure-mistral-medium-2505Mistral Small 3.1
LLMazure-mistral-small-2503Model Router
LLMazure-model-routerPhi-4
LLMazure-phi-4Phi-4-mini
LLMazure-phi-4-miniPhi-4-mini-reasoning
LLMazure-phi-4-mini-reasoningPhi-4-multimodal
LLMazure-phi-4-multimodalPhi-4-reasoning
LLMazure-phi-4-reasoningPhi-4-reasoning-plus
LLMazure-phi-4-reasoning-plusWizardLM-2 8x22B
LLMazure-wizardlm-2-8x22bo1
LLMazure-o1Deprecated endpoints may still be callable. Migrate before retirement.
o3
LLMazure-o3o3-mini
LLMazure-o3-miniDeprecated endpoints may still be callable. Migrate before retirement.
o4-mini
LLMazure-o4-miniDeprecated endpoints may still be callable. Migrate before retirement.
text-embedding-3-large
Embedazure-text-embedding-3-largetext-embedding-3-small
Embedazure-text-embedding-3-smalltext-embedding-ada-002
Embedazure-text-embedding-ada-002Does this change your best option?
Check your models and usage for free. See the relevant official changes, estimated cost, and a practical next step.