Azure OpenAI models & pricing

Azure OpenAI hosts 338 models (297 with public pricing) covering 9 modalities. OpenAI models on Azure with regional endpoints, RBAC, and content-filtering policies. Cheapest input starts at $0.0220/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.

Homepage ↗ Docs ↗
338

chat 212

Model ↕ Input / 1M ↕ Output / 1M ↕ Blended ↕ Context ↕ Caps
GPT-5 nano Deprecates in 97d $0.0500/M $0.400/M $0.137/M 272,000 tools · vision · reasoning · cache
GPT-5 nano (2025-08-07) Deprecates in 97d $0.0500/M $0.400/M $0.137/M 272,000 tools · vision · reasoning · cache
GPT-5 nano (EU) Deprecates in 97d $0.0550/M $0.440/M $0.151/M —
GPT-5 nano (2025-08-07 · EU) Deprecates in 97d $0.0550/M $0.440/M $0.151/M 272,000 tools · vision · reasoning · cache
GPT-5 nano (US) Deprecates in 97d $0.0550/M $0.440/M $0.151/M —
GPT-5 nano (2025-08-07 · US) Deprecates in 97d $0.0550/M $0.440/M $0.151/M 272,000 tools · vision · reasoning · cache
GPT-4.1 nano Deprecates in 161d $0.1000/M $0.400/M $0.175/M 1,047,576 tools · vision · cache
GPT-4.1 nano (2025-04-14) Deprecates in 161d $0.1000/M $0.400/M $0.175/M 1,047,576 tools · vision · cache
GPT-6 Luna $0.1000/M $0.500/M $0.200/M 922,000 tools · vision · reasoning · cache
GPT-6 Luna (2026-09-22) $0.1000/M $0.500/M $0.200/M 922,000 tools · vision · reasoning · cache
GPT-4.1 nano (EU) Deprecates in 161d $0.110/M $0.440/M $0.193/M —
GPT-4.1 nano (US) Deprecates in 161d $0.110/M $0.440/M $0.193/M —
GPT-4.1 nano (2025-04-14 · US) Deprecates in 161d $0.110/M $0.440/M $0.193/M 1,047,576 tools · vision · cache
GPT-6 Luna (US) $0.110/M $0.550/M $0.220/M 922,000 tools · vision · reasoning · cache
GPT-6 Luna (EU) $0.120/M $0.600/M $0.240/M 922,000 tools · vision · reasoning · cache
Model Router $0.140/M — — 200,000 vision
GPT-4o mini (Global · Standard) Deprecates in 161d $0.150/M $0.600/M $0.262/M 128,000 tools · vision
GPT-4o mini Deprecates in 161d $0.150/M $0.600/M $0.262/M 128,000 tools · vision · cache
GPT-4o mini (2024-07-18) Deprecates in 161d $0.150/M $0.600/M $0.262/M 128,000 tools · vision · cache
GPT-4o mini Audio preview (2024-12-17) $0.150/M $0.600/M $0.262/M 128,000 tools
GPT-4o mini (EU) Deprecates in 161d $0.165/M $0.660/M $0.289/M 128,000 tools · vision · cache
GPT-4o mini (2024-07-18 · EU) Deprecates in 161d $0.165/M $0.660/M $0.289/M 128,000 tools · vision · cache
GPT-4o mini (US) Deprecates in 161d $0.165/M $0.660/M $0.289/M 128,000 tools · vision · cache
GPT-4o mini (2024-07-18 · US) Deprecates in 161d $0.165/M $0.660/M $0.289/M 128,000 tools · vision · cache
GPT-3.5 Turbo 0301 Deprecated $0.200/M $2.00/M $0.650/M 4,097 tools
GPT-5.4 nano $0.200/M $1.25/M $0.463/M 272,000 tools · vision · reasoning · cache
GPT-5.4 nano (2026-03-17) $0.200/M $1.25/M $0.463/M 272,000 tools · vision · reasoning · cache
GPT-5.6 Luna $0.200/M $1.20/M $0.450/M 922,000 tools · vision · reasoning · cache
GPT-5.6 Luna (2026-07-09) $0.200/M $1.20/M $0.450/M 922,000 tools · vision · reasoning · cache
GPT-5.4 nano (EU) $0.220/M $1.38/M $0.509/M —
GPT-5.6 Luna (EU) $0.220/M $1.32/M $0.495/M 922,000 tools · vision · reasoning · cache
GPT-5.4 nano (US) $0.220/M $1.38/M $0.509/M —
GPT-5.6 Luna (US) $0.220/M $1.32/M $0.495/M 922,000 tools · vision · reasoning · cache
GPT-5 mini Deprecates in 97d $0.250/M $2.00/M $0.688/M 272,000 tools · vision · reasoning · cache
GPT-5 mini (2025-08-07) Deprecates in 97d $0.250/M $2.00/M $0.688/M 272,000 tools · vision · reasoning · cache
GPT-5 mini (EU) Deprecates in 97d $0.275/M $2.20/M $0.756/M —
GPT-5 mini (2025-08-07 · EU) Deprecates in 97d $0.275/M $2.20/M $0.756/M 272,000 tools · vision · reasoning · cache
GPT-5 mini (US) Deprecates in 97d $0.275/M $2.20/M $0.756/M —
GPT-5 mini (2025-08-07 · US) Deprecates in 97d $0.275/M $2.20/M $0.756/M 272,000 tools · vision · reasoning · cache
GPT-4.1 mini Deprecates in 161d $0.400/M $1.60/M $0.700/M 1,047,576 tools · vision · cache
GPT-4.1 mini (2025-04-14) Deprecates in 161d $0.400/M $1.60/M $0.700/M 1,047,576 tools · vision · cache
GPT-4.1 mini (EU) Deprecates in 161d $0.440/M $1.76/M $0.770/M —
GPT-4.1 mini (US) Deprecates in 161d $0.440/M $1.76/M $0.770/M —
GPT-4.1 mini (2025-04-14 · US) Deprecates in 161d $0.440/M $1.76/M $0.770/M 1,047,576 tools · vision · cache
GPT-3.5 Turbo $0.500/M $1.50/M $0.750/M 4,097 tools
GPT-3.5 Turbo 0125 Deprecated $0.500/M $1.50/M $0.750/M 16,384 tools
GPT-3.5 Turbo $0.500/M $1.50/M $0.750/M 4,097 tools
GPT-3.5 Turbo 0125 Deprecated $0.500/M $1.50/M $0.750/M 16,384 tools
GPT Audio mini $0.600/M $2.40/M $1.05/M 128,000 tools
GPT Audio mini (2025-10-06) Deprecates in 153d $0.600/M $2.40/M $1.05/M 128,000 tools
GPT-5.4 mini $0.750/M $4.50/M $1.69/M 272,000 tools · vision · reasoning · cache
GPT-5.4 mini (2026-03-17) $0.750/M $4.50/M $1.69/M 272,000 tools · vision · reasoning · cache
GPT-5.4 mini (EU) $0.825/M $4.95/M $1.86/M —
GPT-5.4 mini (US) $0.825/M $4.95/M $1.86/M —
GPT-3.5 Turbo 1106 Deprecated $1.00/M $2.00/M $1.25/M 16,384 tools
o1-mini $1.10/M $4.40/M $1.93/M 128,000 tools · reasoning · cache
o1-mini (2024-09-12) $1.10/M $4.40/M $1.93/M 128,000 tools · reasoning · cache
o3-mini Deprecates in 15d $1.10/M $4.40/M $1.93/M 200,000 reasoning · cache
o3-mini (2025-01-31) Deprecates in 15d $1.10/M $4.40/M $1.93/M 200,000 reasoning · cache
o4-mini Deprecates in 15d $1.10/M $4.40/M $1.93/M 200,000 tools · vision · reasoning · cache
o4-mini (2025-04-16) Deprecates in 15d $1.10/M $4.40/M $1.93/M 200,000 tools · vision · reasoning · cache
o1-mini (EU) $1.21/M $4.84/M $2.12/M —
o1-mini (2024-09-12 · EU) $1.21/M $4.84/M $2.12/M 128,000 tools · cache
o3-mini (EU) Deprecates in 15d $1.21/M $4.84/M $2.12/M 200,000 reasoning · cache
o3-mini (2025-01-31 · EU) Deprecates in 15d $1.21/M $4.84/M $2.12/M 200,000 reasoning · cache
o4-mini (EU) Deprecates in 15d $1.21/M $4.84/M $2.12/M 200,000
o4-mini (2025-04-16 · EU) Deprecates in 15d $1.21/M $4.84/M $2.12/M 200,000
o1-mini (US) $1.21/M $4.84/M $2.12/M —
o1-mini (2024-09-12 · US) $1.21/M $4.84/M $2.12/M 128,000 tools · cache
o3-mini (US) Deprecates in 15d $1.21/M $4.84/M $2.12/M 200,000 reasoning · cache
o3-mini (2025-01-31 · US) Deprecates in 15d $1.21/M $4.84/M $2.12/M 200,000 reasoning · cache
o4-mini (US) Deprecates in 15d $1.21/M $4.84/M $2.12/M 200,000 tools · vision · reasoning · cache
o4-mini (2025-04-16 · US) Deprecates in 15d $1.21/M $4.84/M $2.12/M 200,000 tools · vision · reasoning · cache
GPT-5.1 (Global) $1.25/M $10.00/M $3.44/M 272,000 tools · vision · reasoning · cache
GPT-5.1 Chat (Global) $1.25/M $10.00/M $3.44/M 128,000 tools · vision · reasoning · cache
GPT-5 Deprecates in 97d $1.25/M $10.00/M $3.44/M 272,000 tools · vision · reasoning · cache
GPT-5.1 $1.25/M $10.00/M $3.44/M 272,000 tools · vision · reasoning · cache
GPT-5.1 (2025-11-13) $1.25/M $10.00/M $3.44/M 272,000 tools · vision · reasoning · cache
GPT-5.1 Chat Deprecated $1.25/M $10.00/M $3.44/M 111,616 tools · reasoning · cache
GPT-5.1 Chat (2025-11-13) $1.25/M $10.00/M $3.44/M 128,000 vision · reasoning · cache
GPT-5 (2025-08-07) Deprecates in 97d $1.25/M $10.00/M $3.44/M 272,000 tools · vision · reasoning · cache
GPT-5 Chat Deprecated $1.25/M $10.00/M $3.44/M 128,000 vision · cache
GPT-5 Chat latest $1.25/M $10.00/M $3.44/M 128,000 tools · vision · reasoning · cache
GPT-5 (EU) Deprecates in 97d $1.38/M $11.00/M $3.78/M —
GPT-5.1 (EU) $1.38/M $11.00/M $3.78/M 272,000 tools · vision · reasoning · cache
GPT-5.1 Chat (EU) Deprecated $1.38/M $11.00/M $3.78/M 111,616 tools · reasoning · cache
GPT-5 (2025-08-07 · EU) Deprecates in 97d $1.38/M $11.00/M $3.78/M 272,000 tools · vision · reasoning · cache
GPT-5 (US) Deprecates in 97d $1.38/M $11.00/M $3.78/M —
GPT-5.1 (US) $1.38/M $11.00/M $3.78/M 272,000 tools · vision · reasoning · cache
GPT-5.1 Chat (US) Deprecated $1.38/M $11.00/M $3.78/M 111,616 tools · reasoning · cache
GPT-5 (2025-08-07 · US) Deprecates in 97d $1.38/M $11.00/M $3.78/M 272,000 tools · vision · reasoning · cache
GPT-3.5 Turbo 0613 Deprecated $1.50/M $2.00/M $1.63/M 4,097 tools
o3-mini (US GovCloud) $1.51/M $6.05/M $2.65/M 200,000 reasoning · cache
GPT-5.1 (US GovCloud) $1.72/M $13.75/M $4.73/M 272,000 tools · vision · reasoning · cache
GPT-5.2 $1.75/M $14.00/M $4.81/M 272,000 tools · vision · reasoning · cache
GPT-5.2 (2025-12-11) $1.75/M $14.00/M $4.81/M 272,000 tools · vision · reasoning · cache
GPT-5.2 Chat Deprecated $1.75/M $14.00/M $4.81/M 111,616 tools · cache
GPT-5.2 Chat (2025-12-11) $1.75/M $14.00/M $4.81/M 128,000 tools · vision · reasoning · cache
GPT-5.3 Chat Deprecated $1.75/M $14.00/M $4.81/M 111,616 tools · cache
GPT-5.2 (EU) $1.93/M $15.40/M $5.29/M —
GPT-5.2 Chat (EU) Deprecated $1.93/M $15.40/M $5.29/M 111,616 tools · cache
GPT-5.3 Chat (EU) Deprecated $1.93/M $15.40/M $5.29/M 111,616 tools · cache
GPT-5.2 (US) $1.93/M $15.40/M $5.29/M —
GPT-5.2 Chat (US) Deprecated $1.93/M $15.40/M $5.29/M 111,616 tools · cache
GPT-5.3 Chat (US) Deprecated $1.93/M $15.40/M $5.29/M 111,616 tools · cache
GPT-4.1 Deprecates in 161d $2.00/M $8.00/M $3.50/M 1,047,576 tools · vision · cache
GPT-4.1 (2025-04-14) Deprecates in 161d $2.00/M $8.00/M $3.50/M 1,047,576 tools · vision · cache
GPT-5.6 Terra $2.00/M $12.00/M $4.50/M 922,000 tools · vision · reasoning · cache
GPT-5.6 Terra (2026-07-09) $2.00/M $12.00/M $4.50/M 922,000 tools · vision · reasoning · cache
GPT-6.1 Sol $2.00/M $10.00/M $4.00/M 922,000 tools · vision · reasoning · cache
GPT-6.1 Sol (2026-09-29) $2.00/M $10.00/M $4.00/M 922,000 tools · vision · reasoning · cache
GPT-6 Sol $2.00/M $10.00/M $4.00/M 922,000 tools · vision · reasoning · cache
GPT-6 Sol (2026-09-22) $2.00/M $10.00/M $4.00/M 922,000 tools · vision · reasoning · cache
o3 Deprecates in 15d $2.00/M $8.00/M $3.50/M 200,000 tools · vision · reasoning · cache
o3 (2025-04-16) Deprecates in 15d $2.00/M $8.00/M $3.50/M 200,000 tools · vision · reasoning · cache
GPT-4.1 (EU) Deprecates in 161d $2.20/M $8.80/M $3.85/M —
GPT-5.6 Terra (EU) $2.20/M $13.20/M $4.95/M 922,000 tools · vision · reasoning · cache
o3 (EU) Deprecates in 15d $2.20/M $8.80/M $3.85/M 200,000
o3 (2025-04-16 · EU) Deprecates in 15d $2.20/M $8.80/M $3.85/M 200,000
GPT-4.1 (US) Deprecates in 161d $2.20/M $8.80/M $3.85/M —
GPT-4.1 (2025-04-14 · US) Deprecates in 161d $2.20/M $8.80/M $3.85/M 1,047,576 tools · vision · cache
GPT-5.6 Terra (US) $2.20/M $13.20/M $4.95/M 922,000 tools · vision · reasoning · cache
GPT-6.1 Sol (US) $2.20/M $11.00/M $4.40/M 922,000 tools · vision · reasoning · cache
GPT-6 Sol (US) $2.20/M $11.00/M $4.40/M 922,000 tools · vision · reasoning · cache
o3 (US) Deprecates in 15d $2.20/M $8.80/M $3.85/M 200,000 tools · vision · reasoning · cache
o3 (2025-04-16 · US) Deprecates in 15d $2.20/M $8.80/M $3.85/M 200,000 tools · vision · reasoning · cache
GPT-6.1 Sol (APAC) $2.40/M $12.00/M $4.80/M 922,000 tools · vision · reasoning · cache
GPT-6.1 Sol (EU) $2.40/M $12.00/M $4.80/M 922,000 tools · vision · reasoning · cache
GPT-6 Sol (EU) $2.40/M $12.00/M $4.80/M 922,000 tools · vision · reasoning · cache
GPT-4o (2024-08-06 · Global) Deprecates in 161d $2.50/M $10.00/M $4.38/M 128,000 tools · vision · cache
GPT-4o (2024-11-20 · Global) Deprecates in 161d $2.50/M $10.00/M $4.38/M 128,000 tools · vision · cache
GPT-4o (2024-08-06 · Global · Standard) Deprecates in 161d $2.50/M $10.00/M $4.38/M 128,000 tools · vision · cache
GPT-4o (2024-11-20 · Global · Standard) Deprecates in 161d $2.50/M $10.00/M $4.38/M 128,000 tools · vision
GPT-4o Deprecates in 161d $2.50/M $10.00/M $4.38/M 128,000 tools · vision · cache
GPT-4o (2024-08-06) Deprecates in 161d $2.50/M $10.00/M $4.38/M 128,000 tools · vision · cache
GPT-4o (2024-11-20) Deprecates in 161d $2.50/M $10.00/M $4.38/M 128,000 tools · vision · cache
GPT-4o Audio (2024-12-17) $2.50/M $10.00/M $4.38/M 128,000 tools
GPT-5.4 $2.50/M $15.00/M $5.63/M 922,000 tools · vision · reasoning · cache
GPT-5.4 (2026-03-05) $2.50/M $15.00/M $5.63/M 922,000 tools · vision · reasoning · cache
GPT Audio Deprecates in 118d $2.50/M $10.00/M $4.38/M 128,000 tools
GPT Audio 1.5 $2.50/M $10.00/M $4.38/M 128,000 tools
GPT Audio 1.5 (2026-02-23) $2.50/M $10.00/M $4.38/M 128,000 tools
GPT Audio (2025-08-28) Deprecates in 118d $2.50/M $10.00/M $4.38/M 128,000 tools
GPT-4o (EU) Deprecates in 161d $2.75/M $11.00/M $4.81/M 128,000 tools · vision
GPT-4o (2024-08-06 · EU) Deprecates in 161d $2.75/M $11.00/M $4.81/M 128,000 tools · vision · cache
GPT-4o (2024-11-20 · EU) Deprecates in 161d $2.75/M $11.00/M $4.81/M 128,000 tools · vision
GPT-5.4 (EU) $2.75/M $16.50/M $6.19/M 922,000 tools · vision · reasoning · cache
GPT-5.4 (2026-03-05 · EU) $2.75/M $16.50/M $6.19/M 922,000 tools · vision · reasoning · cache
GPT-4o (US) Deprecates in 161d $2.75/M $11.00/M $4.81/M 128,000 tools · vision
GPT-4o (2024-08-06 · US) Deprecates in 161d $2.75/M $11.00/M $4.81/M 128,000 tools · vision · cache
GPT-4o (2024-11-20 · US) Deprecates in 161d $2.75/M $11.00/M $4.81/M 128,000 tools · vision
GPT-5.4 (US) $2.75/M $16.50/M $6.19/M 922,000 tools · vision · reasoning · cache
GPT-5.4 (2026-03-05 · US) $2.75/M $16.50/M $6.19/M 922,000 tools · vision · reasoning · cache
Command R+ Deprecated $3.00/M $15.00/M $6.00/M 128,000 tools
Computer Use preview $3.00/M $12.00/M $5.25/M 8,192 tools · vision · reasoning
GPT-3.5 Turbo 16K Deprecated $3.00/M $4.00/M $3.25/M 16,385
GPT-3.5 Turbo 16K 0613 Deprecated $3.00/M $4.00/M $3.25/M 16,385 tools
Computer Use preview (EU) $3.30/M $13.20/M $5.78/M —
Computer Use preview (US) $3.30/M $13.20/M $5.78/M —
GPT-5.6 $4.00/M $20.00/M $8.00/M 922,000 tools · vision · reasoning · cache
GPT-5.6 Sol $4.00/M $20.00/M $8.00/M 922,000 tools · vision · reasoning · cache
GPT-5.6 Sol (2026-07-09) $4.00/M $20.00/M $8.00/M 922,000 tools · vision · reasoning · cache
GPT-5.6 (EU) $4.40/M $22.00/M $8.80/M 922,000 tools · vision · reasoning · cache
GPT-5.6 Sol (EU) $4.40/M $22.00/M $8.80/M 922,000 tools · vision · reasoning · cache
GPT-5.6 (US) $4.40/M $22.00/M $8.80/M 922,000 tools · vision · reasoning · cache
GPT-5.6 Sol (US) $4.40/M $22.00/M $8.80/M 922,000 tools · vision · reasoning · cache
Chat latest Deprecates in 28d $5.00/M $30.00/M $11.25/M 272,000 tools · vision · reasoning · cache
GPT-4o (2024-05-13) Deprecates in 35d $5.00/M $15.00/M $7.50/M 128,000 tools · vision · cache
GPT-5.5 $5.00/M $30.00/M $11.25/M 922,000 tools · vision · reasoning · cache
GPT-5.5 (2026-04-23) $5.00/M $30.00/M $11.25/M 922,000 tools · vision · reasoning · cache
GPT-5.5 (2026-04-24) $5.00/M $30.00/M $11.25/M 922,000 tools · vision · reasoning · cache
GPT (chat latest) $5.00/M $30.00/M $11.25/M 272,000 tools · vision · reasoning · cache
GPT-4o (2024-05-13 · EU) Deprecates in 35d $5.50/M $16.50/M $8.25/M 128,000
GPT-5.5 (EU) $5.50/M $33.00/M $12.38/M 922,000 tools · vision · reasoning · cache
GPT-5.5 (2026-04-23 · EU) $5.50/M $33.00/M $12.38/M 922,000 tools · vision · reasoning · cache
GPT-5.5 (2026-04-24 · EU) $5.50/M $33.00/M $12.38/M 922,000 tools · vision · reasoning · cache
GPT-4o (2024-05-13 · US) Deprecates in 35d $5.50/M $16.50/M $8.25/M 128,000
GPT-5.5 (US) $5.50/M $33.00/M $12.38/M 922,000 tools · vision · reasoning · cache
GPT-5.5 (2026-04-23 · US) $5.50/M $33.00/M $12.38/M 922,000 tools · vision · reasoning · cache
GPT-5.5 (2026-04-24 · US) $5.50/M $33.00/M $12.38/M 922,000 tools · vision · reasoning · cache
GPT (chat latest) (US) $5.50/M $33.00/M $12.38/M 272,000 tools · vision · reasoning · cache
Mistral Large 2402 $8.00/M $24.00/M $12.00/M 32,000 tools
Mistral Large latest $8.00/M $24.00/M $12.00/M 32,000 tools
GPT-4 0125 preview $10.00/M $30.00/M $15.00/M 128,000 tools
GPT-4 1106 preview $10.00/M $30.00/M $15.00/M 128,000 tools
GPT-6 Astra $10.00/M $50.00/M $20.00/M 922,000 tools · vision · reasoning · cache
GPT-6 Astra (2026-09-03) $10.00/M $50.00/M $20.00/M 922,000 tools · vision · reasoning · cache
o3 Deep Research (EU) Deprecates in 15d $11.00/M $44.00/M $19.25/M —
GPT-4 Turbo $11.00/M $33.00/M $16.50/M 128,000 tools
GPT-4 Turbo (2024-04-09) $11.00/M $33.00/M $16.50/M 128,000 tools · vision
GPT-4 Turbo Vision preview $11.00/M $33.00/M $16.50/M 128,000 vision
GPT-6 Astra (US) $11.00/M $55.00/M $22.00/M 922,000 tools · vision · reasoning · cache
o3 Deep Research (US) Deprecates in 15d $11.00/M $44.00/M $19.25/M —
GPT-6 Astra (EU) $12.00/M $60.00/M $24.00/M 922,000 tools · vision · reasoning · cache
o1 Deprecates in 15d $15.00/M $60.00/M $26.25/M 200,000 tools · vision · reasoning · cache
o1 (2024-12-17) Deprecates in 15d $15.00/M $60.00/M $26.25/M 200,000 tools · vision · reasoning · cache
o1-preview $15.00/M $60.00/M $26.25/M 128,000 tools · reasoning · cache
o1-preview (2024-09-12) $15.00/M $60.00/M $26.25/M 128,000 tools · reasoning · cache
o1 (EU) Deprecates in 15d $16.50/M $66.00/M $28.88/M 200,000 tools · vision · cache
o1 (2024-12-17 · EU) Deprecates in 15d $16.50/M $66.00/M $28.88/M 200,000 tools · vision · cache
o1-preview (EU) Deprecated $16.50/M $66.00/M $28.88/M 128,000 cache
o1-preview (2024-09-12 · EU) $16.50/M $66.00/M $28.88/M 128,000 tools · cache
o1 (US) Deprecates in 15d $16.50/M $66.00/M $28.88/M 200,000 tools · vision · cache
o1 (2024-12-17 · US) Deprecates in 15d $16.50/M $66.00/M $28.88/M 200,000 tools · vision · cache
o1-preview (US) Deprecated $16.50/M $66.00/M $28.88/M 128,000 cache
o1-preview (2024-09-12 · US) $16.50/M $66.00/M $28.88/M 128,000 tools · cache
GPT-4 Deprecated $30.00/M $60.00/M $37.50/M 8,192 tools
GPT-4 0613 Deprecated $30.00/M $60.00/M $37.50/M 8,192 tools
GPT-4 32K Deprecated $60.00/M $120/M $75.00/M 32,768
GPT-4 32K 0613 Deprecated $60.00/M $120/M $75.00/M 32,768
GPT-4.5 preview Deprecated $75.00/M $150/M $93.75/M 128,000 tools · vision · cache
Container — — — —

responses 41

Model ↕ Input / 1M ↕ Output / 1M ↕ Blended ↕ Context ↕ Caps
GPT-5.1 Codex mini (Global) $0.250/M $2.00/M $0.688/M 272,000 tools · vision · reasoning · cache
GPT-5.1 Codex mini $0.250/M $2.00/M $0.688/M 272,000 tools · vision · reasoning · cache
GPT-5.1 Codex mini (2025-11-13) $0.250/M $2.00/M $0.688/M 272,000 tools · vision · reasoning · cache
GPT-5.1 Codex mini (EU) $0.275/M $2.20/M $0.756/M 272,000 tools · vision · reasoning · cache
GPT-5.1 Codex mini (US) $0.275/M $2.20/M $0.756/M 272,000 tools · vision · reasoning · cache
GPT-5.1 Codex (Global) $1.25/M $10.00/M $3.44/M 272,000 tools · vision · reasoning · cache
GPT-5.1 Codex $1.25/M $10.00/M $3.44/M 272,000 tools · vision · reasoning · cache
GPT-5.1 Codex (2025-11-13) $1.25/M $10.00/M $3.44/M 272,000 tools · vision · reasoning · cache
GPT-5.1 Codex Max $1.25/M $10.00/M $3.44/M 272,000 tools · vision · reasoning · cache
GPT-5 Codex Deprecates in 133d $1.25/M $10.00/M $3.44/M 272,000 tools · vision · reasoning · cache
GPT-5.1 Codex (EU) $1.38/M $11.00/M $3.78/M 272,000 tools · vision · reasoning · cache
GPT-5.1 Codex Max (EU) $1.38/M $11.00/M $3.78/M —
GPT-5 Codex (EU) Deprecates in 133d $1.38/M $11.00/M $3.78/M —
GPT-5.1 Codex (US) $1.38/M $11.00/M $3.78/M 272,000 tools · vision · reasoning · cache
GPT-5.1 Codex Max (US) $1.38/M $11.00/M $3.78/M —
GPT-5 Codex (US) Deprecates in 133d $1.38/M $11.00/M $3.78/M —
Codex mini Deprecates in 11d $1.50/M $6.00/M $2.63/M 200,000 tools · vision · reasoning · cache
Codex mini (EU) Deprecates in 11d $1.65/M $6.60/M $2.89/M —
Codex mini (US) Deprecates in 11d $1.65/M $6.60/M $2.89/M —
GPT-5.2 Codex $1.75/M $14.00/M $4.81/M 272,000 tools · vision · reasoning · cache
GPT-5.3 Codex $1.75/M $14.00/M $4.81/M 272,000 tools · vision · reasoning · cache
GPT-5.2 Codex (EU) $1.93/M $15.40/M $5.29/M —
GPT-5.3 Codex (EU) $1.93/M $15.40/M $5.29/M —
GPT-5.2 Codex (US) $1.93/M $15.40/M $5.29/M —
GPT-5.3 Codex (US) $1.93/M $15.40/M $5.29/M —
o3 Deep Research Deprecates in 15d $10.00/M $40.00/M $17.50/M 200,000 tools · vision · reasoning · cache
GPT-5 Pro Deprecates in 154d $15.00/M $120/M $41.25/M 272,000 tools · vision · reasoning · cache
GPT-5 Pro (EU) Deprecates in 154d $16.50/M $132/M $45.38/M —
GPT-5 Pro (US) Deprecates in 154d $16.50/M $132/M $45.38/M —
o3-pro Deprecates in 15d $20.00/M $80.00/M $35.00/M 200,000 tools · vision · reasoning
o3-pro (2025-06-10) Deprecates in 15d $20.00/M $80.00/M $35.00/M 200,000 tools · vision · reasoning
GPT-5.2 Pro $21.00/M $168/M $57.75/M 272,000 tools · vision · reasoning · cache
GPT-5.2 Pro (2025-12-11) $21.00/M $168/M $57.75/M 272,000 tools · vision · reasoning · cache
GPT-5.2 Pro (EU) $23.10/M $185/M $63.52/M —
GPT-5.2 Pro (US) $23.10/M $185/M $63.52/M —
GPT-5.4 Pro $30.00/M $180/M $67.50/M 922,000 tools · vision · reasoning · cache
GPT-5.4 Pro (2026-03-05) $30.00/M $180/M $67.50/M 922,000 tools · vision · reasoning · cache
GPT-5.5 Pro $30.00/M $180/M $67.50/M 1,050,000 tools · vision · reasoning · cache
GPT-5.5 Pro (2026-04-23) $30.00/M $180/M $67.50/M 1,050,000 tools · vision · reasoning · cache
GPT-5.4 Pro (EU) $33.00/M $198/M $74.25/M —
GPT-5.4 Pro (US) $33.00/M $198/M $74.25/M —

image generation 33

Model ↕ Input / 1M ↕ Output / 1M ↕ Blended ↕ Context ↕ Caps
GPT Image 1 mini Deprecates in 154d $2.00/M $8.00/M $3.50/M —
GPT Image 1 Deprecated $5.00/M $40.00/M $13.75/M —
GPT Image 1.5 Deprecates in 42d $5.00/M $10.00/M $6.25/M —
GPT Image 1.5 (2025-12-16) Deprecates in 42d $5.00/M $10.00/M $6.25/M —
GPT Image 2 $5.00/M $30.00/M $11.25/M — vision
GPT Image 2 (2026-04-21) $5.00/M $30.00/M $11.25/M — vision
GPT Image 2.5 Flare $5.00/M $30.00/M $11.25/M — vision
GPT Image 2.5 Sunburst $5.00/M $30.00/M $11.25/M — vision
DALL·E 2 (Standard 1024×1024) — — — —
DALL·E 3 (HD 1024×1024) — — — —
DALL·E 3 (HD 1024×1792) — — — —
DALL·E 3 (HD 1792×1024) — — — —
DALL·E 3 (Standard 1024×1024) — — — —
DALL·E 3 (Standard 1024×1792) — — — —
DALL·E 3 (Standard 1792×1024) — — — —
GPT Image 1 (High 1024×1024) Deprecated — — — —
GPT Image 1 (High 1024×1536) Deprecated — — — —
GPT Image 1 (High 1536×1024) Deprecated — — — —
GPT Image 1 (Low 1024×1024) Deprecated — — — —
GPT Image 1 (Low 1024×1536) Deprecated — — — —
GPT Image 1 (Low 1536×1024) Deprecated — — — —
GPT Image 1 (Medium 1024×1024) Deprecated — — — —
GPT Image 1 (Medium 1024×1536) Deprecated — — — —
GPT Image 1 (Medium 1536×1024) Deprecated — — — —
GPT Image 1 mini (High 1024×1024) Deprecates in 154d — — — —
GPT Image 1 mini (High 1024×1536) Deprecates in 154d — — — —
GPT Image 1 mini (High 1536×1024) Deprecates in 154d — — — —
GPT Image 1 mini (Low 1024×1024) Deprecates in 154d — — — —
GPT Image 1 mini (Low 1024×1536) Deprecates in 154d — — — —
GPT Image 1 mini (Low 1536×1024) Deprecates in 154d — — — —
GPT Image 1 mini (Medium 1024×1024) Deprecates in 154d — — — —
GPT Image 1 mini (Medium 1024×1536) Deprecates in 154d — — — —
GPT Image 1 mini (Medium 1536×1024) Deprecates in 154d — — — —

realtime 20

Model ↕ Input / 1M ↕ Output / 1M ↕ Blended ↕ Context ↕ Caps
GPT-4o mini Realtime preview (2024-12-17) $0.600/M $2.40/M $1.05/M 128,000 tools · audio
GPT Realtime 2.1 mini $0.600/M $2.40/M $1.05/M 32,000 tools · audio
GPT Realtime mini $0.600/M $2.40/M $1.05/M 32,000 tools · audio
GPT Realtime mini (2025-10-06) Deprecates in 153d $0.600/M $2.40/M $1.05/M 32,000 tools · audio
GPT-4o mini Realtime preview (2024-12-17 · EU) $0.660/M $2.64/M $1.16/M 128,000 tools · audio
GPT-4o mini Realtime preview (2024-12-17 · US) $0.660/M $2.64/M $1.16/M 128,000 tools · audio
GPT Realtime Deprecates in 118d $4.00/M $16.00/M $7.00/M 32,000 tools · audio
GPT Realtime 1.5 $4.00/M $16.00/M $7.00/M 32,000 tools · audio
GPT Realtime 1.5 (2026-02-23) $4.00/M $16.00/M $7.00/M 32,000 tools · audio
GPT Realtime 2 Deprecated $4.00/M $24.00/M $9.00/M 32,000 tools · audio
GPT Realtime 2.1 $4.00/M $24.00/M $9.00/M 32,000 tools · audio
GPT Realtime (2025-08-28) Deprecates in 118d $4.00/M $16.00/M $7.00/M 32,000 tools · audio
GPT-4o Realtime (2024-10-01) Deprecated $5.00/M $20.00/M $8.75/M 128,000 tools · audio
GPT-4o Realtime (2024-12-17) $5.00/M $20.00/M $8.75/M 16,000 tools · audio
GPT-4o Realtime (2024-10-01 · EU) Deprecated $5.50/M $22.00/M $9.63/M 128,000 tools · audio
GPT-4o Realtime (2024-12-17 · EU) $5.50/M $22.00/M $9.63/M 16,000 tools · audio
GPT-4o Realtime (2024-10-01 · US) Deprecated $5.50/M $22.00/M $9.63/M 128,000 tools · audio
GPT-4o Realtime (2024-12-17 · US) $5.50/M $22.00/M $9.63/M 16,000 tools · audio
GPT Live 1 — — — — tools · audio
GPT Realtime Translate — — — 32,000 audio

embedding 12

Model ↕ Input / 1M ↕ Output / 1M ↕ Blended ↕ Context ↕ Caps
text-embedding-3-small (EU) $0.0220/M — — —
text-embedding-3-small $0.0220/M — — 8,192
text-embedding-3-small (US) $0.0220/M — — —
text-embedding-3-small (US GovCloud) $0.0250/M — — 8,191
Ada $0.110/M — — 8,191
text-embedding-ada-002 (EU) $0.110/M — — —
text-embedding-ada-002 $0.110/M — — 8,192
text-embedding-ada-002 (US) $0.110/M — — —
text-embedding-3-large (EU) $0.143/M — — —
text-embedding-3-large $0.143/M — — 8,192
text-embedding-3-large (US) $0.143/M — — —
text-embedding-3-large (US GovCloud) $0.163/M — — 8,191

audio transcription 9

Model ↕ Input / 1M ↕ Output / 1M ↕ Blended ↕ Context ↕ Caps
GPT-4o mini Transcribe $1.25/M $5.00/M $2.19/M 16,000
GPT-4o Transcribe Deprecated $2.50/M $10.00/M $4.38/M 16,000
GPT-4o Transcribe Diarize Deprecates in 162d $2.50/M $10.00/M $4.38/M 16,000
GPT Live Transcribe — — — 32,000 audio
GPT Realtime Whisper — — — 32,000 audio
GPT Transcribe — — — — audio
Speech Azure STT — — — —
Whisper Deprecates in 41d — — — —
Whisper Deprecates in 41d — — — —

audio speech 5

Model ↕ Input / 1M ↕ Output / 1M ↕ Blended ↕ Context ↕ Caps
GPT-4o mini TTS $0.600/M $10.00/M $2.95/M —
Speech Azure TTS — — — —
Speech Azure TTS HD — — — —
TTS-1 Deprecates in 41d — — — —
TTS-1 HD Deprecates in 41d — — — —

completion 3

Model ↕ Input / 1M ↕ Output / 1M ↕ Blended ↕ Context ↕ Caps
GPT-3.5 Turbo Instruct 0914 $1.65/M $2.20/M $1.79/M 4,097
GPT-3.5 Turbo Instruct $1.65/M $2.20/M $1.79/M 4,097
GPT-3.5 Turbo Instruct 0914 $1.65/M $2.20/M $1.79/M 4,097

video generation 3

Model ↕ Input / 1M ↕ Output / 1M ↕ Blended ↕ Context ↕ Caps
Sora 2 Deprecated — — — —
Sora 2 Pro — — — —
Sora 2 Pro High Res — — — —

FAQ

How many Azure OpenAI models are there?

338 Azure OpenAI models are listed across 9 modalities on this page. 297 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 $0.0220 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.