Azure OpenAI models & pricing
Azure OpenAI hosts 201 models (167 with public pricing) covering 8 modalities. OpenAI models on Azure with regional endpoints, RBAC, and content-filtering policies. Cheapest input starts at $0.0200/M tokens; the most premium goes up to $75.00/M. Use Future AGI's Agent Command Center to route any Azure OpenAI model with cost-optimized fallback and unified observability.
201
chat 126
| Model ↕ | Input / 1M ↕ | Output / 1M ↕ | Context ↕ | Caps |
|---|---|---|---|---|
| GPT-5 nano | $0.0500/M | $0.400/M | 272,000 | tools · vision · reasoning · cache |
| GPT-5 nano (2025-08-07) | $0.0500/M | $0.400/M | 272,000 | tools · vision · reasoning · cache |
| GPT-5 nano (2025-08-07) | $0.0550/M | $0.440/M | 272,000 | tools · vision · reasoning · cache |
| GPT-5 nano (2025-08-07) | $0.0550/M | $0.440/M | 272,000 | tools · vision · reasoning · cache |
| GPT 4.1 nano | $0.1000/M | $0.400/M | 1,047,576 | tools · vision · cache |
| GPT 4.1 nano (2025-04-14) Deprecates in 175d | $0.1000/M | $0.400/M | 1,047,576 | tools · vision · cache |
| GPT 4.1 nano (2025-04-14) Deprecates in 175d | $0.110/M | $0.440/M | 1,047,576 | tools · vision · cache |
| GPT-4o mini | $0.150/M | $0.600/M | 128,000 | tools · vision |
| GPT-4o mini (2024-07-18) | $0.165/M | $0.660/M | 128,000 | tools · vision · cache |
| GPT-4o mini | $0.165/M | $0.660/M | 128,000 | tools · vision · cache |
| GPT-4o mini (2024-07-18) | $0.165/M | $0.660/M | 128,000 | tools · vision · cache |
| GPT-4o mini (2024-07-18) | $0.165/M | $0.660/M | 128,000 | tools · vision · cache |
| GPT 35 Turbo 0301 Deprecated | $0.200/M | $2.00/M | 4,097 | tools |
| GPT 5.4 nano | $0.200/M | $1.25/M | 1,050,000 | tools · vision · reasoning · cache |
| GPT 5.4 nano (2026-03-17) | $0.200/M | $1.25/M | 1,050,000 | tools · vision · reasoning · cache |
| GPT-5 mini | $0.250/M | $2.00/M | 272,000 | tools · vision · reasoning · cache |
| GPT-5 mini (2025-08-07) | $0.250/M | $2.00/M | 272,000 | tools · vision · reasoning · cache |
| GPT-5 mini (2025-08-07) | $0.275/M | $2.20/M | 272,000 | tools · vision · reasoning · cache |
| GPT-5 mini (2025-08-07) | $0.275/M | $2.20/M | 272,000 | tools · vision · reasoning · cache |
| GPT 4.1 mini | $0.400/M | $1.60/M | 1,047,576 | tools · vision · cache |
| GPT 4.1 mini (2025-04-14) Deprecates in 175d | $0.400/M | $1.60/M | 1,047,576 | tools · vision · cache |
| GPT 4.1 mini (2025-04-14) Deprecates in 175d | $0.440/M | $1.76/M | 1,047,576 | tools · vision · cache |
| GPT-3.5 Turbo | $0.500/M | $1.50/M | 4,097 | tools |
| GPT 3.5 Turbo 0125 Deprecated | $0.500/M | $1.50/M | 16,384 | tools |
| GPT 35 Turbo | $0.500/M | $1.50/M | 4,097 | tools |
| GPT 35 Turbo 0125 Deprecated | $0.500/M | $1.50/M | 16,384 | tools |
| GPT 4o mini Realtime preview (2024-12-17) | $0.600/M | $2.40/M | 128,000 | tools · audio |
| GPT Audio mini (2025-10-06) | $0.600/M | $2.40/M | 128,000 | tools |
| GPT Realtime mini (2025-10-06) | $0.600/M | $2.40/M | 32,000 | tools · audio |
| GPT 4o mini Realtime preview (2024-12-17) | $0.660/M | $2.64/M | 128,000 | tools · audio |
| GPT 4o mini Realtime preview (2024-12-17) | $0.660/M | $2.64/M | 128,000 | tools · audio |
| GPT 5.4 mini | $0.750/M | $4.50/M | 1,050,000 | tools · vision · reasoning · cache |
| GPT 5.4 mini (2026-03-17) | $0.750/M | $4.50/M | 1,050,000 | tools · vision · reasoning · cache |
| GPT 35 Turbo 1106 Deprecated | $1.00/M | $2.00/M | 16,384 | tools |
| o1-mini (2024-09-12) | $1.10/M | $4.40/M | 128,000 | tools · reasoning · cache |
| o3-mini | $1.10/M | $4.40/M | 200,000 | reasoning · cache |
| o3-mini (2025-01-31) | $1.10/M | $4.40/M | 200,000 | reasoning · cache |
| o4-mini | $1.10/M | $4.40/M | 200,000 | tools · vision · reasoning · cache |
| o4-mini (2025-04-16) | $1.10/M | $4.40/M | 200,000 | tools · vision · reasoning · cache |
| o1-mini (2024-09-12) | $1.21/M | $4.84/M | 128,000 | tools · cache |
| o3-mini (2025-01-31) | $1.21/M | $4.84/M | 200,000 | reasoning · cache |
| o1-mini | $1.21/M | $4.84/M | 128,000 | tools · reasoning · cache |
| o1-mini (2024-09-12) | $1.21/M | $4.84/M | 128,000 | tools · cache |
| o3-mini (2025-01-31) | $1.21/M | $4.84/M | 200,000 | reasoning · cache |
| o4-mini (2025-04-16) | $1.21/M | $4.84/M | 200,000 | tools · vision · reasoning · cache |
| GPT 5.1 | $1.25/M | $10.00/M | 272,000 | tools · vision · reasoning · cache |
| GPT 5.1 Chat | $1.25/M | $10.00/M | 128,000 | tools · vision · reasoning · cache |
| GPT-5 | $1.25/M | $10.00/M | 272,000 | tools · vision · reasoning · cache |
| GPT 5.1 | $1.25/M | $10.00/M | 272,000 | tools · vision · reasoning · cache |
| GPT 5.1 (2025-11-13) | $1.25/M | $10.00/M | 272,000 | tools · vision · reasoning · cache |
| GPT 5.1 Chat | $1.25/M | $10.00/M | 128,000 | tools · vision · reasoning · cache |
| GPT 5.1 Chat (2025-11-13) | $1.25/M | $10.00/M | 128,000 | vision · reasoning · cache |
| GPT-5 (2025-08-07) | $1.25/M | $10.00/M | 272,000 | tools · vision · reasoning · cache |
| GPT 5 Chat | $1.25/M | $10.00/M | 128,000 | tools · vision · reasoning · cache |
| GPT 5 Chat latest | $1.25/M | $10.00/M | 128,000 | tools · vision · reasoning · cache |
| GPT-5 (2025-08-07) | $1.38/M | $11.00/M | 272,000 | tools · vision · reasoning · cache |
| GPT-5 (2025-08-07) | $1.38/M | $11.00/M | 272,000 | tools · vision · reasoning · cache |
| GPT 5.1 | $1.38/M | $11.00/M | 272,000 | tools · vision · reasoning · cache |
| GPT 5.1 Chat | $1.38/M | $11.00/M | 128,000 | tools · vision · reasoning · cache |
| GPT 5.1 | $1.38/M | $11.00/M | 272,000 | tools · vision · reasoning · cache |
| GPT 5.1 Chat | $1.38/M | $11.00/M | 128,000 | tools · vision · reasoning · cache |
| GPT 35 Turbo 0613 Deprecated | $1.50/M | $2.00/M | 4,097 | tools |
| GPT 5.2 | $1.75/M | $14.00/M | 272,000 | tools · vision · reasoning · cache |
| GPT 5.2 (2025-12-11) | $1.75/M | $14.00/M | 272,000 | tools · vision · reasoning · cache |
| GPT 5.2 Chat | $1.75/M | $14.00/M | 128,000 | tools · vision · reasoning · cache |
| GPT 5.2 Chat (2025-12-11) | $1.75/M | $14.00/M | 128,000 | tools · vision · reasoning · cache |
| GPT 5.3 Chat | $1.75/M | $14.00/M | 128,000 | tools · vision · reasoning · cache |
| GPT 4.1 | $2.00/M | $8.00/M | 1,047,576 | tools · vision · cache |
| GPT 4.1 (2025-04-14) Deprecates in 175d | $2.00/M | $8.00/M | 1,047,576 | tools · vision · cache |
| o3 | $2.00/M | $8.00/M | 200,000 | tools · vision · reasoning · cache |
| o3 (2025-04-16) Deprecated | $2.00/M | $8.00/M | 200,000 | tools · vision · reasoning · cache |
| GPT 4.1 (2025-04-14) Deprecates in 175d | $2.20/M | $8.80/M | 1,047,576 | tools · vision · cache |
| o3 (2025-04-16) Deprecated | $2.20/M | $8.80/M | 200,000 | tools · vision · reasoning · cache |
| GPT-4o (2024-08-06) Deprecated | $2.50/M | $10.00/M | 128,000 | tools · vision · cache |
| GPT-4o (2024-11-20) Deprecated | $2.50/M | $10.00/M | 128,000 | tools · vision · cache |
| GPT-4o (2024-08-06) Deprecated | $2.50/M | $10.00/M | 128,000 | tools · vision · cache |
| GPT-4o (2024-11-20) Deprecated | $2.50/M | $10.00/M | 128,000 | tools · vision |
| GPT-4o | $2.50/M | $10.00/M | 128,000 | tools · vision · cache |
| GPT-4o (2024-08-06) Deprecated | $2.50/M | $10.00/M | 128,000 | tools · vision · cache |
| GPT-4o Audio (2024-12-17) | $2.50/M | $10.00/M | 128,000 | tools |
| GPT 4o mini Audio preview (2024-12-17) | $2.50/M | $10.00/M | 128,000 | tools |
| GPT 5.4 | $2.50/M | $15.00/M | 1,050,000 | tools · vision · reasoning · cache |
| GPT 5.4 (2026-03-05) | $2.50/M | $15.00/M | 1,050,000 | tools · vision · reasoning · cache |
| GPT Audio 1.5 (2026-02-23) | $2.50/M | $10.00/M | 128,000 | tools |
| GPT Audio (2025-08-28) | $2.50/M | $10.00/M | 128,000 | tools |
| GPT-4o (2024-08-06) Deprecated | $2.75/M | $11.00/M | 128,000 | tools · vision · cache |
| GPT-4o (2024-11-20) Deprecated | $2.75/M | $11.00/M | 128,000 | tools · vision |
| GPT-4o (2024-11-20) Deprecated | $2.75/M | $11.00/M | 128,000 | tools · vision · cache |
| GPT-4o (2024-08-06) Deprecated | $2.75/M | $11.00/M | 128,000 | tools · vision · cache |
| GPT-4o (2024-11-20) Deprecated | $2.75/M | $11.00/M | 128,000 | tools · vision |
| Command R+ | $3.00/M | $15.00/M | 128,000 | tools |
| Computer Use preview | $3.00/M | $12.00/M | 8,192 | tools · vision · reasoning |
| GPT 35 Turbo 16k | $3.00/M | $4.00/M | 16,385 | |
| GPT 35 Turbo 16k 0613 | $3.00/M | $4.00/M | 16,385 | tools |
| GPT Realtime 1.5 (2026-02-23) | $4.00/M | $16.00/M | 32,000 | tools · audio |
| GPT Realtime (2025-08-28) | $4.00/M | $16.00/M | 32,000 | tools · audio |
| GPT-4o (2024-05-13) | $5.00/M | $15.00/M | 128,000 | tools · vision · cache |
| GPT-4o Realtime (2024-10-01) | $5.00/M | $20.00/M | 128,000 | tools · audio |
| GPT-4o Realtime (2024-12-17) | $5.00/M | $20.00/M | 128,000 | tools · audio |
| GPT 5.5 | $5.00/M | $30.00/M | 1,050,000 | tools · vision · reasoning · cache |
| GPT 5.5 (2026-04-23) | $5.00/M | $30.00/M | 1,050,000 | tools · vision · reasoning · cache |
| GPT-4o Realtime (2024-10-01) | $5.50/M | $22.00/M | 128,000 | tools · audio |
| GPT-4o Realtime (2024-12-17) | $5.50/M | $22.00/M | 128,000 | tools · audio |
| GPT-4o Realtime (2024-10-01) | $5.50/M | $22.00/M | 128,000 | tools · audio |
| GPT-4o Realtime (2024-12-17) | $5.50/M | $22.00/M | 128,000 | tools · audio |
| Mistral Large 2402 | $8.00/M | $24.00/M | 32,000 | tools |
| Mistral Large latest | $8.00/M | $24.00/M | 32,000 | tools |
| GPT 4.0125 preview | $10.00/M | $30.00/M | 128,000 | tools |
| GPT 4.1106 preview | $10.00/M | $30.00/M | 128,000 | tools |
| GPT-4 Turbo | $10.00/M | $30.00/M | 128,000 | tools |
| GPT-4 Turbo (2024-04-09) | $10.00/M | $30.00/M | 128,000 | tools · vision |
| GPT 4 Turbo Vision preview | $10.00/M | $30.00/M | 128,000 | vision |
| o1 | $15.00/M | $60.00/M | 200,000 | tools · vision · reasoning · cache |
| o1 (2024-12-17) | $15.00/M | $60.00/M | 200,000 | tools · vision · reasoning · cache |
| o1-preview | $15.00/M | $60.00/M | 128,000 | tools · reasoning · cache |
| o1-preview (2024-09-12) | $15.00/M | $60.00/M | 128,000 | tools · reasoning · cache |
| o1 (2024-12-17) | $16.50/M | $66.00/M | 200,000 | tools · vision · cache |
| o1-preview (2024-09-12) | $16.50/M | $66.00/M | 128,000 | tools · cache |
| o1 (2024-12-17) | $16.50/M | $66.00/M | 200,000 | tools · vision · cache |
| o1-preview (2024-09-12) | $16.50/M | $66.00/M | 128,000 | tools · cache |
| GPT-4 | $30.00/M | $60.00/M | 8,192 | tools |
| GPT 4.0613 | $30.00/M | $60.00/M | 8,192 | tools |
| GPT-4 32K | $60.00/M | $120/M | 32,768 | |
| GPT 4.32k 0613 | $60.00/M | $120/M | 32,768 | |
| GPT 4.5 preview | $75.00/M | $150/M | 128,000 | tools · vision · cache |
| Container | — | — | — |
image generation 31
responses 25
| Model ↕ | Input / 1M ↕ | Output / 1M ↕ | Context ↕ | Caps |
|---|---|---|---|---|
| GPT 5.1 Codex mini | $0.250/M | $2.00/M | 272,000 | tools · vision · reasoning · cache |
| GPT 5.1 Codex mini | $0.250/M | $2.00/M | 272,000 | tools · vision · reasoning · cache |
| GPT 5.1 Codex mini (2025-11-13) | $0.250/M | $2.00/M | 272,000 | tools · vision · reasoning · cache |
| GPT 5.1 Codex mini | $0.275/M | $2.20/M | 272,000 | tools · vision · reasoning · cache |
| GPT 5.1 Codex mini | $0.275/M | $2.20/M | 272,000 | tools · vision · reasoning · cache |
| GPT 5.1 Codex | $1.25/M | $10.00/M | 272,000 | tools · vision · reasoning · cache |
| GPT 5.1 Codex | $1.25/M | $10.00/M | 272,000 | tools · vision · reasoning · cache |
| GPT 5.1 Codex (2025-11-13) | $1.25/M | $10.00/M | 272,000 | tools · vision · reasoning · cache |
| GPT 5.1 Codex Max | $1.25/M | $10.00/M | 272,000 | tools · vision · reasoning · cache |
| GPT 5 Codex | $1.25/M | $10.00/M | 272,000 | tools · vision · reasoning · cache |
| GPT 5.1 Codex | $1.38/M | $11.00/M | 272,000 | tools · vision · reasoning · cache |
| GPT 5.1 Codex | $1.38/M | $11.00/M | 272,000 | tools · vision · reasoning · cache |
| Codex mini | $1.50/M | $6.00/M | 200,000 | tools · vision · reasoning · cache |
| GPT 5.2 Codex | $1.75/M | $14.00/M | 272,000 | tools · vision · reasoning · cache |
| GPT 5.3 Codex | $1.75/M | $14.00/M | 272,000 | tools · vision · reasoning · cache |
| o3 Deep Research | $10.00/M | $40.00/M | 200,000 | tools · vision · reasoning · cache |
| GPT-5 Pro | $15.00/M | $120/M | 272,000 | tools · vision · reasoning · cache |
| o3-pro | $20.00/M | $80.00/M | 200,000 | tools · vision · reasoning |
| o3-pro (2025-06-10) | $20.00/M | $80.00/M | 200,000 | tools · vision · reasoning |
| GPT 5.2 Pro | $21.00/M | $168/M | 272,000 | tools · vision · reasoning · cache |
| GPT 5.2 Pro (2025-12-11) | $21.00/M | $168/M | 272,000 | tools · vision · reasoning · cache |
| GPT 5.4 Pro | $30.00/M | $180/M | 1,050,000 | tools · vision · reasoning · cache |
| GPT 5.4 Pro (2026-03-05) | $30.00/M | $180/M | 1,050,000 | tools · vision · reasoning · cache |
| GPT 5.5 Pro | $30.00/M | $180/M | 1,050,000 | tools · vision · reasoning · cache |
| GPT 5.5 Pro (2026-04-23) | $30.00/M | $180/M | 1,050,000 | tools · vision · reasoning · cache |
audio speech 5
| Model ↕ | Input / 1M ↕ | Output / 1M ↕ | Context ↕ | Caps |
|---|---|---|---|---|
| GPT 4o mini TTS | $2.50/M | $10.00/M | — | |
| Speech Azure TTS | — | — | — | |
| Speech Azure TTS Hd | — | — | — | |
| TTS-1 | — | — | — | |
| TTS-1 HD | — | — | — |
embedding 4
| Model ↕ | Input / 1M ↕ | Output / 1M ↕ | Context ↕ | Caps |
|---|---|---|---|---|
| text-embedding-3-small Deprecated | $0.0200/M | — | 8,191 | |
| Ada | $0.1000/M | — | 8,191 | |
| text-embedding-ada-002 | $0.1000/M | — | 8,191 | |
| text-embedding-3-large | $0.130/M | — | 8,191 |
audio transcription 4
| Model ↕ | Input / 1M ↕ | Output / 1M ↕ | Context ↕ | Caps |
|---|---|---|---|---|
| GPT 4o mini Transcribe | $1.25/M | $5.00/M | 16,000 | |
| GPT 4o Transcribe | $2.50/M | $10.00/M | 16,000 | |
| GPT 4o Transcribe Diarize | $2.50/M | $10.00/M | 16,000 | |
| Whisper | — | — | — |
completion 3
| Model ↕ | Input / 1M ↕ | Output / 1M ↕ | Context ↕ | Caps |
|---|---|---|---|---|
| GPT 3.5 Turbo Instruct 0914 | $1.50/M | $2.00/M | 4,097 | |
| GPT 35 Turbo Instruct | $1.50/M | $2.00/M | 4,097 | |
| GPT 35 Turbo Instruct 0914 | $1.50/M | $2.00/M | 4,097 |
video generation 3
| Model ↕ | Input / 1M ↕ | Output / 1M ↕ | Context ↕ | Caps |
|---|---|---|---|---|
| Sora 2 | — | — | — | |
| Sora 2 Pro | — | — | — | |
| Sora 2 Pro High Res | — | — | — |
FAQ
How many Azure OpenAI models are there?
201 Azure OpenAI models are listed across 8 modalities on this page. 167 have public per-token pricing.
How is Azure OpenAI pricing verified?
Pricing is aggregated from BerriAI/litellm, models.dev, and OpenRouter and refreshed weekly. Each row shows a per-model "verified" date. If a price is wrong, click the row to open the model page and use the inline "suggest edit" link — submissions go into a public review queue.
Which Azure OpenAI model is cheapest?
Input pricing on Azure OpenAI starts at $0.0200 per 1M tokens. Sort the table by price (or use the in-page filter at the top) to find the cheapest model that matches your capability requirements.
Can I route to Azure OpenAI via an OpenAI-compatible API?
Yes — point your OpenAI client at Future AGI's Agent Command Center, configure a Azure OpenAI target, and call Azure OpenAI models with the standard /v1/chat/completions surface. The same gateway can route to other providers as fallback. Free for the first 100K requests/month.
Route any Azure OpenAI model via Agent Command Center →
OpenAI-compatible endpoint. Caching, fallback, guardrails, observability. Free for 100K requests/month.