Azure AI Foundry API pricing
140 Azure AI Foundry models: text, embeddings, image, speech to text, rerank, document ocr, from price book 2026-10-22.
Billing rules Veqen applies
- Token models: cached input at the cache-read rate, cache writes at the write rate; batch and service tiers at their own rates where published; long-context rates once the full prompt passes the threshold.
- Image models: per image, with each size and quality priced separately. When the API reports image tokens, those are the bill.
- Audio models: per second of audio or per character of text, or per token where the model bills tokens.
- Rerank models: per query.
Also recognized as: az.ai.inference, azure_ai (framework, gateway and OpenTelemetry names).
Reconcile your bill
Azure AI Foundry doesn't offer a cost API, so Veqen's ledger is your running record of spend. Enter each month's bill to reconcile it and book it in the close. How reconciliation works.
Prices come from Azure AI Foundry's pricing page. Negotiated rates or committed-use discounts can be set as custom prices.
Text 113 models
| Model | Input | Output | Cached input | Batch input | Context | Status |
|---|---|---|---|---|---|---|
| FW-Nemotron-Lightning-3.5-30B-A3B | $0.06 | $0.22 | $0.01 | — | 262.1K | |
| Phi-4-mini-instruct | $0.075 | $0.30 | — | — | 131.1K | |
| Phi-4-mini-reasoning | $0.075 | $0.30 | — | — | 131.1K | |
| Phi-4-multimodal-instruct | $0.08 | $0.32 | — | — | 131.1K | |
| gpt-6-luna | $0.10 | $0.50 | $0.01 | — | 922K | |
| Phi-4 | $0.125 | $0.50 | — | — | 16.4K | |
| Phi-4-reasoning | $0.125 | $0.50 | — | — | 32.8K | |
| FW-DeepSeek-V4-Flash | $0.15 | $0.31 | $0.03 | — | 1M | |
| gpt-oss-120b | $0.15 | $0.60 | — | — | 131.1K | |
| FW-GLM-5.3-Flash | $0.188 | $0.625 | $0.038 | — | 1M | |
| Llama-4-Scout-17B-16E-Instruct | $0.20 | $0.78 | — | — | 10M | |
| grok-4-1-fast-non-reasoning | $0.20 | $0.50 | — | — | 128K | |
| grok-4-1-fast-reasoning | $0.20 | $0.50 | — | — | 128K | |
| grok-code-fast-1 | $0.20 | $1.50 | — | — | 256K | |
| Llama-4-Maverick-17B-128E-Instruct-FP8 | $0.25 | $1.00 | — | — | 1M | |
| Codestral-2501 | $0.30 | $0.90 | — | — | 256K | |
| FW-MiniMax-M3 | $0.33 | $1.32 | $0.066 | — | 512K | |
| FW-DeepSeek-V4.1-Flash | $0.375 | $1.50 | $0.008 | — | 1M | |
| mistral-large-3 | $0.50 | $1.50 | — | — | 256K | |
| deepseek-v3.2 | $0.58 | $1.68 | — | — | 128K | |
| deepseek-v3.2-speciale | $0.58 | $1.68 | — | — | 128K | |
| MAI-Cyber-1-Flash | $0.60 | $3.50 | $0.06 | — | 256K | |
| FW-Nemotron-3-Ultra-NVFP4 | $0.66 | $2.64 | $0.13 | — | 262.1K | |
| Llama-3.3-70B-Instruct | $0.71 | $0.71 | — | — | 128K | |
| FW-Kimi-K2.6 | $1.045 | $4.40 | $0.176 | — | 262.1K | |
| FW-Kimi-K2.7-Code | $1.05 | $4.40 | $0.21 | — | 262.1K | |
| FW-Inkling | $1.10 | $4.46 | $0.19 | — | 1M | |
| grok-4.3 | $1.25 | $2.50 | $0.20 | — | 200K | |
| mistral-medium-3-5 | $1.50 | $7.50 | — | — | 128K | |
| FW-GLM-5.2 | $1.54 | $4.84 | $0.15 | — | 1M | |
| FW-GLM-5.3 | $1.75 | $5.50 | $0.325 | — | 1M | |
| FW-DeepSeek-V4-Pro | $1.925 | $3.828 | $0.165 | — | 1M | |
| MAI-Thinking-1 | $2.00 | $8.00 | $0.20 | — | 256K | |
| gpt-6-sol | $2.00 | $10.00 | $0.20 | — | 922K | |
| gpt-6.1-sol | $2.00 | $10.00 | $0.10 | — | 922K | |
| grok-4.6 | $2.00 | $6.00 | $0.50 | — | 200K | |
| mistral-large-latest | $2.00 | $6.00 | — | — | 128K | |
| FW-GLM-5.2-Fast | $2.31 | $7.26 | $0.231 | — | 1M | |
| cohere-command-a | $2.50 | $10.00 | — | — | 131.1K | |
| FW-Kimi-K3 | $3.00 | $15.00 | $0.30 | — | 1M | |
| grok-4 | $3.00 | $15.00 | — | — | 262K | |
| gpt-6-astra | $10.00 | $50.00 | $1.00 | — | 922K | |
| ministral-3b | $0.04 | $0.04 | — | — | 128K | Retires 2026-12-09 |
| claude-haiku-5-5 | $0.10 | $0.50 | $0.01 | — | 1M | Retires 2027-09-29 |
| mistral-small-2503 | $0.10 | $0.30 | — | — | 128K | Retires 2026-12-09 |
| Phi-3-mini-128k-instruct | $0.13 | $0.52 | — | — | 128K | Retired 2025-08-30 |
| Phi-3-mini-4k-instruct | $0.13 | $0.52 | — | — | 4.1K | Retired 2025-08-30 |
| Phi-3.5-mini-instruct | $0.13 | $0.52 | — | — | 128K | Retired 2025-08-30 |
| Phi-3.5-vision-instruct | $0.13 | $0.52 | — | — | 128K | Retired 2025-08-30 |
| model-router | $0.14 | $0.00 | — | — | 200K | Retires 2027-05-20 |
| model_router | $0.14 | $0.00 | — | — | 200K | Retires 2027-05-20 |
| Phi-3-small-128k-instruct | $0.15 | $0.60 | — | — | 128K | Retired 2025-08-30 |
| Phi-3-small-8k-instruct | $0.15 | $0.60 | — | — | 8.2K | Retired 2025-08-30 |
| mistral-nemo | $0.15 | $0.15 | — | — | 131.1K | Retired 2026-01-30 |
| Phi-3.5-MoE-instruct | $0.16 | $0.64 | — | — | 128K | Retired 2025-08-30 |
| FW-GPT-OSS-120B | $0.165 | $0.66 | $0.082 | — | 131.1K | Retires 2027-07-01 |
| Phi-3-medium-128k-instruct | $0.17 | $0.68 | — | — | 128K | Retired 2025-08-30 |
| Phi-3-medium-4k-instruct | $0.17 | $0.68 | — | — | 4.1K | Retired 2025-08-30 |
| deepseek-v4-flash | $0.19 | $0.51 | $0.028 | — | 1M | Retires 2028-02-20 |
| MAI-Code-1.1-Flash | $0.20 | $1.20 | $0.02 | — | 256K | Retires 2026-12-09 |
| gpt-5.4-nano | $0.20 | $1.25 | $0.02 | — | 272K | Retires 2027-09-21 |
| grok-4-fast-non-reasoning | $0.20 | $0.50 | — | — | — | Retired 2026-05-01 |
| grok-4-fast-reasoning | $0.20 | $0.50 | — | — | — | Retired 2026-05-01 |
| grok-3-mini | $0.25 | $1.27 | — | — | — | Retired 2026-05-01 |
| deepseek-v4.1-flash | $0.30 | $1.20 | $0.006 | — | 1M | Retires 2026-12-15 |
| FW-MiniMax-M2.5 | $0.33 | $1.32 | $0.033 | — | 1M | Retires 2027-07-01 |
| mistral-medium-2505 | $0.40 | $2.00 | — | — | 131.1K | Retires 2026-12-09 |
| DeepSeek-V4-Flash-0731 | $0.44 | $1.32 | $0.014 | — | 1M | Retires 2026-12-03 |
| jamba-instruct | $0.50 | $0.70 | — | — | 70K | Retired 2025-03-01 |
| kimi-k2-thinking | $0.60 | $2.50 | — | — | 262.1K | Retired 2026-03-29 |
| kimi-k2.5 | $0.60 | $3.00 | $0.10 | — | 262.1K | Retires 2027-01-26 |
| FW-DeepSeek-V3.2 | $0.62 | $1.85 | $0.31 | — | 163.8K | Retires 2027-07-01 |
| FW-Kimi-K2.5 | $0.66 | $3.30 | $0.11 | — | 262.1K | Retires 2027-07-01 |
| gpt-5.4-mini | $0.75 | $4.50 | $0.075 | — | 272K | Retires 2027-09-21 |
| Cohere-command-a-plus-05-2026 | $0.80 | $3.20 | — | — | 128K | Retired 2026-10-16 |
| kimi-k2.6 | $0.95 | $4.00 | $0.16 | — | 262.1K | Retires 2027-04-16 |
| kimi-k2.7-code | $0.95 | $4.00 | $0.19 | — | 262.1K | Retires 2027-04-16 |
| claude-haiku-4-5 | $1.00 | $5.00 | $0.10 | — | 200K | Retires 2026-11-15 |
| mistral-small | $1.00 | $3.00 | — | — | 32K | Retired 2025-07-31 |
| FW-GLM-5 | $1.10 | $3.52 | $0.22 | — | 200K | Retires 2027-07-01 |
| Meta-Llama-3-70B-Instruct | $1.10 | $0.37 | — | — | 8.2K | Retired 2025-06-30 |
| deepseek-v3 | $1.14 | $4.56 | — | — | 128K | Retired 2025-08-31 |
| deepseek-v3-0324 | $1.14 | $4.56 | — | — | — | Retired 2026-07-13 |
| deepseek-v3.1 | $1.23 | $4.94 | — | — | — | Retired 2026-07-13 |
| grok-4-20-non-reasoning | $1.25 | $2.50 | $1.25 | — | 262K | Retires 2027-04-06 |
| grok-4-20-reasoning | $1.25 | $2.50 | $1.25 | — | 262K | Retires 2027-04-06 |
| MAI-DS-R1 | $1.35 | $5.40 | — | — | 128K | Retired 2026-02-27 |
| deepseek-r1 | $1.35 | $5.40 | — | — | — | Retired 2026-08-13 |
| codex-mini | $1.50 | $6.00 | $0.375 | — | 200K | Retires 2026-11-15 |
| FW-GLM-5.1 | $1.54 | $4.84 | $0.286 | — | 202.8K | Retires 2027-07-01 |
| deepseek-v4-pro | $1.74 | $3.48 | $0.145 | — | 1M | Retires 2028-02-20 |
| claude-sonnet-5 | $2.00 | $10.00 | $0.20 | — | 1M | Retires 2027-06-30 |
| claude-sonnet-5-5 | $2.00 | $10.00 | $0.20 | — | 1M | Retires 2027-09-29 |
| grok-4.7 | $2.00 | $6.00 | $0.50 | — | 500K | Retires 2027-10-05 |
| mistral-large-2407 | $2.00 | $6.00 | — | — | 128K | Retired 2025-05-13 |
| gpt-5.4 | $2.50 | $15.00 | $0.25 | — | 922K | Retires 2027-09-02 |
| Meta-Llama-3.1-70B-Instruct | $2.68 | $3.54 | — | — | 128K | Retired 2025-06-30 |
| claude-sonnet-4-5 | $3.00 | $15.00 | $0.30 | — | 200K | Retires 2026-11-30 |
| claude-sonnet-4-6 | $3.00 | $15.00 | $0.30 | — | 1M | Retires 2027-02-10 |
| grok-3 | $3.00 | $15.00 | — | — | — | Retired 2026-05-01 |
| claude-opus-5-5 | $4.00 | $20.00 | $0.20 | — | 1M | Retires 2027-09-18 |
| mistral-large | $4.00 | $12.00 | — | — | 32K | Retired 2025-04-15 |
| claude-opus-4-5 | $5.00 | $25.00 | $0.50 | — | 200K | Retires 2026-11-24 |
| claude-opus-4-6 | $5.00 | $25.00 | $0.50 | — | 1M | Retires 2027-02-02 |
| claude-opus-4-7 | $5.00 | $25.00 | $0.50 | — | 1M | Retires 2027-04-06 |
| claude-opus-4-8 | $5.00 | $25.00 | $0.50 | — | 1M | Retires 2027-09-01 |
| claude-opus-5 | $5.00 | $25.00 | $0.50 | — | 1M | Retires 2027-07-08 |
| gpt-5.5 | $5.00 | $30.00 | $0.50 | — | 922K | Retires 2027-10-26 |
| gpt-chat-latest | $5.00 | $30.00 | $0.50 | — | 272K | Retires 2027-05-18 |
| claude-opus-5-5-fast | $8.00 | $40.00 | $0.40 | — | 1M | Retires 2027-10-01 |
| claude-fable-5 | $10.00 | $50.00 | $1.00 | — | 1M | Retires 2027-12-05 |
| claude-fable-5-1 | $10.00 | $50.00 | $0.25 | — | 1M | Retires 2027-12-05 |
| gpt-5.4-pro | $30.00 | $180.00 | $3.00 | — | 922K | Retires 2027-09-07 |
Embeddings 5 models
| Model | Price | Status |
|---|---|---|
| Cohere-embed-v3-english | $0.10 per 1M tokens | |
| Cohere-embed-v3-multilingual | $0.10 per 1M tokens | |
| embed-v-4-0 | $0.12 per 1M tokens | |
| Cohere-Embed-V5-Fast | $0.08 per 1M tokens | Retires 2027-01-23 |
| Cohere-Embed-V5-Pro | $0.12 per 1M tokens | Retires 2027-01-23 |
Image 9 models
| Model | Price | Status |
|---|---|---|
| FLUX-1.1-pro | $0.04 per image | |
| FLUX.1-Kontext-pro | $0.04 per image | |
| flux.2-pro | $0.04 per image | |
| MAI-Image-2.6-Flash | $1.75 in · $19.00 out per 1M | |
| MAI-Image-2.6 | $5.00 in · $38.00 out per 1M | |
| MAI-Image-2.5-Flash | $0.02 per image | Retired 2026-10-01 |
| MAI-Image-2.5 | $0.048 per image | Retired 2026-10-01 |
| MAI-Image-2.5-Pro | $0.1085 per image | Retired 2026-10-01 |
| gpt-image-2 | $5.00 in · $30.00 out per 1M | Retires 2027-10-21 |
Speech to text 1 model
| Model | Price | Status |
|---|---|---|
| whisper | $0.006 per minute | Retires 2026-12-15 |
Rerank 4 models
| Model | Price | Status |
|---|---|---|
| cohere-rerank-v4.0-fast | $2.00 per 1K queries | |
| cohere-rerank-v4.0-pro | $2.50 per 1K queries | |
| cohere-rerank-v3-english | $2.00 per 1K queries | Retired 2025-06-30 |
| cohere-rerank-v3-multilingual | $2.00 per 1K queries | Retired 2025-06-30 |
Document OCR 8 models
| Model | Price | Status |
|---|---|---|
| doc-intelligence/prebuilt-document | $10.00 per 1K pages | |
| doc-intelligence/prebuilt-layout | $10.00 per 1K pages | |
| doc-intelligence/prebuilt-read | $1.50 per 1K pages | |
| mistral-document-ai-2512 | $3.00 per 1K pages | |
| mistral-ocr-2505 | $1.00 per 1K pages | |
| mistral-ocr-2512 | $2.00 per 1K pages | |
| mistral-ocr-4-0 | $4.00 per 1K pages | |
| Cohere-parse-v5 | $1.50 per 1K pages | Retires 2026-12-15 |