Azure AI Pricing
Azure AI 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 Jais 30B Chat costs $9710.00/1M output. The largest context window is 10.0M tokens (Llama 4 Scout 17B 16e Instruct). Prices are USD, current as of October 12, 2026.
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
10.0M
Llama 4 Scout 17B 16e Instruct
Models priced
109
Avg $92.07/1M output
Pricing by model
All prices in USD per 1 million tokens. Showing 80 of 109 priced models, cheapest first.
| Model | Input / 1M | Output / 1M | Context |
|---|---|---|---|
| Model Router | $0.140 | — | 200K |
| Ministral 3B | $0.040 | $0.040 | 128K |
| Mistral Nemo | $0.150 | $0.150 | 131K |
| Fw Nemotron Lightning 3.5 30B A3b | $0.060 | $0.220 | 262K |
| Mistral Small 2503 | $0.100 | $0.300 | 128K |
| Phi 4 Mini Instruct | $0.075 | $0.300 | 131K |
| Phi 4 Mini Reasoning | $0.075 | $0.300 | 131K |
| Fw DeepSeek V4 Flash | $0.150 | $0.310 | 1.0M |
| Phi 4 Multimodal Instruct | $0.080 | $0.320 | 131K |
| Meta Llama 3 70B Instruct | $1.10 | $0.370 | 8K |
| Claude Haiku 5.5 | $0.100 | $0.500 | 1.0M |
| GPT 6 Luna | $0.100 | $0.500 | 922K |
| Grok 4 Fast Non Reasoning | $0.200 | $0.500 | 0 |
| Grok 4 Fast Reasoning | $0.200 | $0.500 | 0 |
| Grok 4.1 Fast Non Reasoning | $0.200 | $0.500 | 128K |
| Grok 4.1 Fast Reasoning | $0.200 | $0.500 | 128K |
| Phi 4 | $0.125 | $0.500 | 16K |
| Phi 4 Reasoning | $0.125 | $0.500 | 33K |
| DeepSeek V4 Flash | $0.190 | $0.510 | 1.0M |
| Phi 3 Mini 128K Instruct | $0.130 | $0.520 | 128K |
| Phi 3 Mini 4K Instruct | $0.130 | $0.520 | 4K |
| Phi 3.5 Mini Instruct | $0.130 | $0.520 | 128K |
| Phi 3.5 Vision Instruct | $0.130 | $0.520 | 128K |
| GPT Oss 120B | $0.150 | $0.600 | 131K |
| Phi 3 Small 128K Instruct | $0.150 | $0.600 | 128K |
| Phi 3 Small 8K Instruct | $0.150 | $0.600 | 8K |
| Fw Glm 5.3 Flash | $0.188 | $0.625 | 1.0M |
| Phi 3.5 Moe Instruct | $0.160 | $0.640 | 128K |
| Fw GPT Oss 120B | $0.165 | $0.660 | 131K |
| Phi 3 Medium 128K Instruct | $0.170 | $0.680 | 128K |
| Phi 3 Medium 4K Instruct | $0.170 | $0.680 | 4K |
| Jamba Instruct | $0.500 | $0.700 | 70K |
| Llama 3.3 70B Instruct | $0.710 | $0.710 | 128K |
| Llama 4 Scout 17B 16e Instruct | $0.200 | $0.780 | 10.0M |
| Codestral 2501 | $0.300 | $0.900 | 256K |
| Llama 4 Maverick 17B 128e Instruct Fp8 | $0.250 | $1.00 | 1.0M |
| DeepSeek V4.1 Flash | $0.300 | $1.20 | 1.0M |
| GPT 5.4 Nano | $0.200 | $1.25 | 272K |
| Grok 3 Mini | $0.250 | $1.27 | 0 |
| DeepSeek V4 Flash 0731 | $0.440 | $1.32 | 1.0M |
| Fw Minimax M2.5 | $0.330 | $1.32 | 1.0M |
| Fw Minimax M3 | $0.330 | $1.32 | 512K |
| Fw DeepSeek V4.1 Flash | $0.375 | $1.50 | 1.0M |
| Grok Code Fast 1 | $0.200 | $1.50 | 256K |
| Mistral Large 3 | $0.500 | $1.50 | 256K |
| DeepSeek V3.2 | $0.580 | $1.68 | 128K |
| DeepSeek V3.2 Speciale | $0.580 | $1.68 | 128K |
| Fw DeepSeek V3.2 | $0.620 | $1.85 | 164K |
| Mistral Medium 2505 | $0.400 | $2.00 | 131K |
| Grok 4.20 Non Reasoning | $1.25 | $2.50 | 262K |
| Grok 4.20 Reasoning | $1.25 | $2.50 | 262K |
| Grok 4.3 | $1.25 | $2.50 | 200K |
| Kimi K2 Thinking | $0.600 | $2.50 | 262K |
| Fw Nemotron 3 Ultra Nvfp4 | $0.660 | $2.64 | 262K |
| Kimi K2.5 | $0.600 | $3.00 | 262K |
| Mistral Small | $1.00 | $3.00 | 32K |
| Cohere Command A Plus 05 2026 | $0.800 | $3.20 | 128K |
| Fw Kimi K2.5 | $0.660 | $3.30 | 262K |
| DeepSeek V4 Pro | $1.74 | $3.48 | 1.0M |
| Mai Cyber 1 Flash | $0.600 | $3.50 | 256K |
| Fw Glm 5 | $1.10 | $3.52 | 200K |
| Meta Llama 3.1 70B Instruct | $2.68 | $3.54 | 128K |
| Fw DeepSeek V4 Pro | $1.93 | $3.83 | 1.0M |
| Kimi K2.6 | $0.950 | $4.00 | 262K |
| Kimi K2.7 Code | $0.950 | $4.00 | 262K |
| Fw Kimi K2.6 | $1.04 | $4.40 | 262K |
| Fw Kimi K2.7 Code | $1.05 | $4.40 | 262K |
| Fw Inkling | $1.10 | $4.46 | 1.0M |
| GPT 5.4 Mini | $0.750 | $4.50 | 272K |
| DeepSeek | $1.14 | $4.56 | 128K |
| DeepSeek V3 0324 | $1.14 | $4.56 | 0 |
| Fw Glm 5.1 | $1.54 | $4.84 | 203K |
| Fw Glm 5.2 | $1.54 | $4.84 | 1.0M |
| DeepSeek V3.1 | $1.23 | $4.94 | 0 |
| Claude Haiku 4.5 | $1.00 | $5.00 | 200K |
| DeepSeek R1 | $1.35 | $5.40 | 0 |
| Mai Ds R1 | $1.35 | $5.40 | 128K |
| Fw Glm 5.3 | $1.75 | $5.50 | 1.0M |
| Grok 4.6 | $2.00 | $6.00 | 200K |
| Jais 30B Chat | $3200.00 | $9710.00 | 8K |
Frequently asked questions
How much does Azure AI cost per 1M tokens?
Azure AI pricing starts at $0.040 per 1 million output tokens (Ministral 3B) across 109 models, with its current flagship Jais 30B Chat at $9710.00. Older premium models in the catalog list higher. Rates current as of October 12, 2026.
What is the cheapest Azure AI model?
Ministral 3B is the cheapest Azure AI 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 AI context window?
Llama 4 Scout 17B 16e Instruct has the largest context window in the Azure AI catalog at 10.0M input tokens, with up to 16K output tokens per response.
How do I calculate my actual Azure AI 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