Azure LLM API pricing
Every model Azure serves, with its pricing per 1M tokens and the exact model ID to copy. Sorted cheapest input first, with models Azure lists no paid price for at the end. Listed prices from LiteLLM, OpenRouter and Vercel.
Models served
211
on this provider
Cheapest input
$0.04
per 1M tokens
Cheapest output
$0.04
per 1M tokens
Max context
10.5M
tokens
On-demand listed rates, OpenRouter routed quotes and Vercel reseller quotes. Enterprise commitments (committed-use discounts, provisioned throughput, negotiated rates) can be materially lower.
| Model ID | |||||
|---|---|---|---|---|---|
| Ministral 3B | Mistral | 128K | $0.04 | $0.04 | azure_ai/ministral-3b |
| GPT 5 Nano (2025-08-07) | OpenAI | 272K | $0.05 | $0.40 | azure/gpt-5-nano-2025-08-07 |
| GPT-5 Nano | OpenAI | 5M | $0.05 | $0.40 | azure/gpt-5-nano |
| Fw Nemotron Lightning 3.5 30B A3b | NVIDIA | 262K | $0.06 | $0.22 | azure_ai/FW-Nemotron-Lightning-3.5-30B-A3B |
| Phi 4 Mini Instruct | Microsoft | 131K | $0.075 | $0.30 | azure_ai/Phi-4-mini-instruct |
| Phi 4 Mini Reasoning | Microsoft | 131K | $0.075 | $0.30 | azure_ai/Phi-4-mini-reasoning |
| Phi 4 Multimodal Instruct | Microsoft | 131K | $0.08 | $0.32 | azure_ai/Phi-4-multimodal-instruct |
| Claude Haiku 5.5 | Anthropic | 1M | $0.10 | $0.50 | azure_ai/claude-haiku-5-5 |
| GPT 4.1 Nano (2025-04-14) | OpenAI | 1M | $0.10 | $0.40 | azure/gpt-4.1-nano-2025-04-14 |
| GPT 6 Luna (2026-09-22) | OpenAI | 922K | $0.10 | $0.50 | azure/gpt-6-luna-2026-09-22 |
| GPT-4.1 Nano | OpenAI | 1M | $0.10 | $0.40 | azure/gpt-4.1-nano |
| GPT-6 Luna | OpenAI | 1.1M | $0.10 | $0.50 | azure/gpt-6-luna |
| Mistral Small 2503 | Mistral | 128K | $0.10 | $0.30 | azure_ai/mistral-small-2503 |
| Phi 4 | Microsoft | 16K | $0.125 | $0.50 | azure_ai/Phi-4 |
| Phi 4 Reasoning | Microsoft | 33K | $0.125 | $0.50 | azure_ai/Phi-4-reasoning |
| Phi 3 Mini 128k Instruct | Microsoft | 131K | $0.13 | $0.52 | azure_ai/Phi-3-mini-128k-instruct |
| Phi 3 Mini 4k Instruct | Microsoft | 4K | $0.13 | $0.52 | azure_ai/Phi-3-mini-4k-instruct |
| Phi 3.5 Mini Instruct | Microsoft | 128K | $0.13 | $0.52 | azure_ai/Phi-3.5-mini-instruct |
| Phi 3.5 Vision Instruct | Microsoft | 128K | $0.13 | $0.52 | azure_ai/Phi-3.5-vision-instruct |
| Fw DeepSeek V4 Flash | DeepSeek | 1M | $0.15 | $0.31 | azure_ai/FW-DeepSeek-V4-Flash |
| GPT 4o Mini Audio Preview (2024-12-17) | OpenAI | 128K | $0.15 | $0.60 | azure/gpt-4o-mini-audio-preview-2024-12-17 |
| GPT-4o-mini | OpenAI | 131K | $0.15 | $0.60 | azure/global-standard/gpt-4o-mini |
| GPT-4o-mini (2024-07-18) | OpenAI | 128K | $0.15 | $0.60 | azure/gpt-4o-mini-2024-07-18 |
| gpt-oss-120b | OpenAI | 131K | $0.15 | $0.60 | azure_ai/gpt-oss-120b |
| Mistral Nemo | Mistral | 131K | $0.15 | $0.15 | azure_ai/mistral-nemo |
| Phi 3 Small 128k Instruct | Microsoft | 128K | $0.15 | $0.60 | azure_ai/Phi-3-small-128k-instruct |
| Phi 3 Small 8k Instruct | Microsoft | 8K | $0.15 | $0.60 | azure_ai/Phi-3-small-8k-instruct |
| Phi 3.5 MoE Instruct | Microsoft | 128K | $0.16 | $0.64 | azure_ai/Phi-3.5-MoE-instruct |
| Fw GPT OSS 120B | OpenAI | 131K | $0.165 | $0.66 | azure_ai/FW-GPT-OSS-120B |
| Phi 3 Medium 128k Instruct | Microsoft | 128K | $0.17 | $0.68 | azure_ai/Phi-3-medium-128k-instruct |
| Phi 3 Medium 4k Instruct | Microsoft | 4K | $0.17 | $0.68 | azure_ai/Phi-3-medium-4k-instruct |
| Fw GLM 5.3 Flash | Zhipu | 1M | $0.188 | $0.625 | azure_ai/FW-GLM-5.3-Flash |
| DeepSeek V4 Flash 0423 | DeepSeek | 1M | $0.19 | $0.51 | azure_ai/deepseek-v4-flash |
| GPT 5.4 Nano (2026-03-17) | OpenAI | 272K | $0.20 | $1.25 | azure/gpt-5.4-nano-2026-03-17 |
| GPT 5.6 Luna (2026-07-09) | OpenAI | 922K | $0.20 | $1.20 | azure/gpt-5.6-luna-2026-07-09 |
| GPT-5.4 Nano | OpenAI | 400K | $0.20 | $1.25 | azure/gpt-5.4-nano |
| GPT-5.6 Luna | OpenAI | 1.1M | $0.20 | $1.20 | azure/gpt-5.6-luna |
| Grok 4 Fast Non Reasoning | xAI | 2M | $0.20 | $0.50 | azure_ai/grok-4-fast-non-reasoning |
| Grok 4 Fast Reasoning | xAI | 2M | $0.20 | $0.50 | azure_ai/grok-4-fast-reasoning |
| Grok 4.1 Fast Non Reasoning | xAI | 128K | $0.20 | $0.50 | azure_ai/grok-4-1-fast-non-reasoning |
| Grok 4.1 Fast Reasoning | xAI | 128K | $0.20 | $0.50 | azure_ai/grok-4-1-fast-reasoning |
| Grok Code Fast 1 | xAI | 256K | $0.20 | $1.50 | azure_ai/grok-code-fast-1 |
| Llama 4 Scout 17B 16e Instruct | Meta | 10.5M | $0.20 | $0.78 | azure_ai/Llama-4-Scout-17B-16E-Instruct |
| GPT 5 Mini (2025-08-07) | OpenAI | 272K | $0.25 | $2.00 | azure/gpt-5-mini-2025-08-07 |
| GPT-5 Mini | OpenAI | 1M | $0.25 | $2.00 | azure/gpt-5-mini |
| Grok 3 Mini | xAI | 131K | $0.25 | $1.27 | azure_ai/grok-3-mini |
| Llama 4 Maverick 17B 128e Instruct FP8 | Meta | 1M | $0.25 | $1.00 | azure_ai/Llama-4-Maverick-17B-128E-Instruct-FP8 |
| Codestral 2501 | Mistral | 256K | $0.30 | $0.90 | azure_ai/Codestral-2501 |
| DeepSeek V4.1 Flash | DeepSeek | 1M | $0.30 | $1.20 | azure_ai/deepseek-v4.1-flash |
| Llama 3.1 8B Instruct | Meta | 200K | $0.30 | $0.61 | azure_ai/Meta-Llama-3.1-8B-Instruct |
1–50 of 215
Page 1 of 5
Listed prices from LiteLLM, OpenRouter and Vercel · catalogue refreshed Oct 14, 2026 · 26 prices older, back to Jul 18, 2026
Every weekday
AI moves fast. Here's your debrief.
News, analysis, tools, and more.
For people who build with AI