- Providers
- Azure
Access
- SDK
- @ai-sdk/azure
- Environment variables
- AZURE_RESOURCE_NAME, AZURE_API_KEY
Models
50 of 50 model versions
| Model | Family | Provider model ID | Protocol | Streaming | Organization | Context | Max output | Input | Output | Reasoning | Tool call | Structured | Temperature | Weights | Price | Released | Updated | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Claude Opus 5 anthropic/claude-opus-5 | ANAnthropic | Claude | claude-opus-5 | Openai responses | Yes | 1M | 128K | Yes | Yes | -No | -No | Closed | input $5/M · output $25/M cache read $0.5/M · cache write $6.25/M | 2026-07-24 | 2026-07-24 | |||
| GPT-5.6 Luna openai/gpt-5.6-luna | OPOpenAI | GPT | gpt-5.6-luna | Openai responses | Yes | 1.1M | 128K | Yes | Yes | Yes | -No | Closed | input $1/M · output $6/M cache read $0.1/M · cache write $1.25/M | 2026-07-09 | 2026-08-06 | |||
| GPT-5.6 Sol openai/gpt-5.6-sol | OPOpenAI | GPT | gpt-5.6-sol | Openai responses | Yes | 1.1M | 128K | Yes | Yes | Yes | -No | Closed | input $5/M · output $30/M cache read $0.5/M | 2026-07-09 | 2026-08-06 | |||
| GPT-5.6 Terra openai/gpt-5.6-terra | OPOpenAI | GPT | gpt-5.6-terra | Openai responses | Yes | 1.1M | 128K | Yes | Yes | Yes | -No | Closed | input $2.5/M · output $15/M cache read $0.25/M · cache write $3.125/M | 2026-07-09 | 2026-08-06 | |||
| Claude Sonnet 5 anthropic/claude-sonnet-5 | ANAnthropic | Claude | claude-sonnet-5 | Openai responses | Yes | 1M | 128K | Yes | Yes | -No | -No | Closed | input $2/M · output $10/M cache read $0.2/M · cache write $2.5/M | 2026-06-30 | 2026-07-01 | |||
| Claude Fable 5 anthropic/claude-fable-5 | ANAnthropic | Claude | claude-fable-5 | Openai responses | Yes | 1M | 128K | Yes | Yes | -No | -No | Closed | input $10/M · output $50/M cache read $1/M · cache write $12.5/M | 2026-06-09 | 2026-06-11 | |||
| Claude Opus 4.8 anthropic/claude-opus-4-8 | ANAnthropic | Claude | claude-opus-4-8 | Openai responses | Yes | 1M | 128K | Yes | Yes | -No | -No | Closed | input $5/M · output $25/M cache read $0.5/M · cache write $6.25/M | 2026-05-28 | 2026-06-11 | |||
| DeepSeek V4 Flash deepseek/deepseek-v4-flash | DEDeepSeek | DeepSeek | deepseek-v4-flash | Openai responses | Yes | 1M | 384K | Yes | Yes | Yes | Yes | Open | input $0.19/M · output $0.51/M | 2026-04-24 | 2026-08-06 | |||
| DeepSeek V4 Pro deepseek/deepseek-v4-pro | DEDeepSeek | DeepSeek | deepseek-v4-pro | Openai responses | Yes | 1M | 384K | Yes | Yes | Yes | Yes | Open | input $1.74/M · output $3.48/M | 2026-04-24 | 2026-08-06 | |||
| GPT-5.5 openai/gpt-5.5 | OPOpenAI | GPT | gpt-5.5 | Openai responses | Yes | 1.1M | 128K | Yes | Yes | Yes | -No | Closed | input $5/M · output $30/M cache read $0.5/M | 2026-04-23 | 2026-08-06 | |||
| GPT Image 2 openai/gpt-image-2 | OPOpenAI | GPT | gpt-image-2 | Openai responses | Yes | - | - | -No | -No | -No | -No | Closed | input $5/M · output $30/M cache read $1.25/M | 2026-04-21 | 2026-08-06 | |||
| Kimi K2.6 moonshotai/kimi-k2.6 | MAMoonshot AI | Kimi | kimi-k2.6 | Openai responses | Yes | 262K | 262K | Yes | Yes | Yes | Yes | Open | input $0.95/M · output $4/M | 2026-04-21 | 2026-08-06 | |||
| GPT-5.4 mini openai/gpt-5.4-mini | OPOpenAI | GPT | gpt-5.4-mini | Openai responses | Yes | 400K | 128K | Yes | Yes | Yes | -No | Closed | input $0.75/M · output $4.5/M cache read $0.075/M | 2026-03-17 | 2026-03-20 | |||
| GPT-5.4 nano openai/gpt-5.4-nano | OPOpenAI | GPT | gpt-5.4-nano | Openai responses | Yes | 400K | 128K | Yes | Yes | Yes | -No | Closed | input $0.2/M · output $1.25/M cache read $0.02/M | 2026-03-17 | 2026-03-20 | |||
| GPT-5.4 openai/gpt-5.4 | OPOpenAI | GPT | gpt-5.4 | Openai responses | Yes | 1.1M | 128K | Yes | Yes | Yes | -No | Closed | input $2.5/M · output $15/M cache read $0.25/M | 2026-03-05 | 2026-08-06 | |||
| GPT-5.4 Pro openai/gpt-5.4-pro | OPOpenAI | GPT | gpt-5.4-pro | Openai responses | Yes | 1.1M | 128K | Yes | Yes | -No | -No | Closed | input $30/M · output $180/M | 2026-03-05 | 2026-03-20 | |||
| Claude Sonnet 4.6 anthropic/claude-sonnet-4-6 | ANAnthropic | Claude | claude-sonnet-4-6 | Openai responses | Yes | 1M | 64K | Yes | Yes | -No | Yes | Closed | input $3/M · output $15/M cache read $0.3/M · cache write $3.75/M | 2026-02-17 | 2026-06-11 | |||
| Claude Opus 4.6 anthropic/claude-opus-4-6 | ANAnthropic | Claude | claude-opus-4-6 | Openai responses | Yes | 1M | 128K | Yes | Yes | -No | Yes | Closed | input $5/M · output $25/M cache read $0.5/M · cache write $6.25/M | 2026-02-05 | 2026-07-17 | |||
| GPT-5.3-Codex openai/gpt-5.3-codex | OPOpenAI | GPT | gpt-5.3-codex | Openai responses | Yes | 400K | 128K | Yes | Yes | Yes | -No | Closed | input $1.75/M · output $14/M cache read $0.175/M | 2026-02-05 | 2026-08-06 | |||
| Kimi K2.5 moonshotai/kimi-k2.5 | MAMoonshot AI | Kimi | kimi-k2.5 | Openai responses | Yes | 262K | 262K | Yes | Yes | Yes | -No | Open | input $0.6/M · output $3/M | 2026-01 | 2026-08-06 | |||
| GPT-5.2 openai/gpt-5.2 | OPOpenAI | GPT | gpt-5.2 | Openai responses | Yes | 400K | 128K | Yes | Yes | Yes | -No | Closed | input $1.75/M · output $14/M cache read $0.125/M | 2025-12-11 | 2026-01-01 | |||
| GPT-5.2-Codex openai/gpt-5.2-codex | OPOpenAI | GPT | gpt-5.2-codex | Openai responses | Yes | 400K | 128K | Yes | Yes | Yes | -No | Closed | input $1.75/M · output $14/M cache read $0.175/M | 2025-12-11 | 2026-08-06 | |||
| GPT Image 1.5 openai/gpt-image-1.5 | OPOpenAI | GPT | gpt-image-1.5 | Openai responses | Yes | - | - | -No | -No | -No | -No | Closed | input $5/M · output $32/M cache read $1.25/M | 2025-11-25 | 2026-08-06 | |||
| GPT-5.1 openai/gpt-5.1 | OPOpenAI | GPT | gpt-5.1 | Openai responses | Yes | 400K | 128K | Yes | Yes | Yes | -No | Closed | input $1.25/M · output $10/M cache read $0.125/M | 2025-11-13 | 2026-02-01 | |||
| GPT-5.1-Codex openai/gpt-5.1-codex | OPOpenAI | GPT | gpt-5.1-codex | Openai responses | Yes | 400K | 128K | Yes | Yes | Yes | -No | Closed | input $1.25/M · output $10/M cache read $0.125/M | 2025-11-13 | 2026-08-06 | |||
| GPT-5.1-Codex mini openai/gpt-5.1-codex-mini | OPOpenAI | GPT | gpt-5.1-codex-mini | Openai responses | Yes | 400K | 128K | Yes | Yes | Yes | -No | Closed | input $0.25/M · output $2/M cache read $0.025/M | 2025-11-13 | 2026-08-06 | |||
| GPT-5.1-Codex-Max openai/gpt-5.1-codex-max | OPOpenAI | GPT | gpt-5.1-codex-max | Openai responses | Yes | 400K | 128K | Yes | Yes | Yes | -No | Closed | input $1.25/M · output $10/M cache read $0.125/M | 2025-11-13 | 2026-08-06 | |||
| Claude Opus 4.5 anthropic/claude-opus-4-5-20251101 | ANAnthropic | Claude | claude-opus-4-5 | Openai responses | Yes | 200K | 64K | Yes | Yes | -No | Yes | Closed | input $5/M · output $25/M cache read $0.5/M · cache write $6.25/M | 2025-11-01 | 2026-06-11 | |||
| Claude Haiku 4.5 anthropic/claude-haiku-4-5-20251001 | ANAnthropic | Claude | claude-haiku-4-5 | Openai responses | Yes | 200K | 64K | Yes | Yes | -No | Yes | Closed | input $1/M · output $5/M cache read $0.1/M · cache write $1.25/M | 2025-10-15 | 2026-01-01 | |||
| GPT-5 Pro openai/gpt-5-pro | OPOpenAI | GPT | gpt-5-pro | Openai responses | Yes | 400K | 272K | Yes | Yes | Yes | -No | Closed | input $15/M · output $120/M | 2025-10-06 | 2026-01-01 | |||
| Claude Sonnet 4.5 anthropic/claude-sonnet-4-5-20250929 | ANAnthropic | Claude | claude-sonnet-4-5 | Openai responses | Yes | 200K | 64K | Yes | Yes | -No | Yes | Closed | input $3/M · output $15/M cache read $0.3/M · cache write $3.75/M | 2025-09-29 | 2026-06-11 | |||
| GPT-5-Codex openai/gpt-5-codex | OPOpenAI | GPT | gpt-5-codex | Openai responses | Yes | 400K | 128K | Yes | Yes | Yes | -No | Closed | input $1.25/M · output $10/M cache read $0.13/M | 2025-09-15 | 2026-08-06 | |||
| GPT-5 openai/gpt-5 | OPOpenAI | GPT | gpt-5 | Openai responses | Yes | 400K | 128K | Yes | Yes | Yes | -No | Closed | input $1.25/M · output $10/M cache read $0.13/M | 2025-08-07 | 2025-09-19 | |||
| GPT-5 mini openai/gpt-5-mini | OPOpenAI | GPT | gpt-5-mini | Openai responses | Yes | 400K | 128K | Yes | Yes | Yes | -No | Closed | input $0.25/M · output $2/M cache read $0.03/M | 2025-08-07 | 2026-08-06 | |||
| GPT-5 nano openai/gpt-5-nano | OPOpenAI | GPT | gpt-5-nano | Openai responses | Yes | 400K | 128K | Yes | Yes | Yes | -No | Closed | input $0.05/M · output $0.4/M cache read $0.01/M | 2025-08-07 | 2026-08-06 | |||
| Claude Opus 4.1 anthropic/claude-opus-4-1-20250805 | ANAnthropic | Claude | claude-opus-4-1 | Openai responses | Yes | 200K | 32K | Yes | Yes | -No | Yes | Closed | input $15/M · output $75/M cache read $1.5/M · cache write $18.75/M | 2025-08-05 | 2026-08-06 | |||
| Mistral Medium 3 mistral/mistral-medium-2505 | MAMistral AI | Mistral | mistral-medium-2505 | Openai responses | Yes | 128K | 131K | -No | Yes | -No | Yes | Closed | input $0.4/M · output $2/M | 2025-05-07 | 2026-08-06 | |||
| GPT Image 1 openai/gpt-image-1 | OPOpenAI | GPT | gpt-image-1 | Openai responses | Yes | - | - | -No | -No | -No | -No | Closed | input $5/M · output $40/M cache read $1.25/M | 2025-04-24 | 2026-08-06 | |||
| o3 openai/o3 | OPOpenAI | o-series | o3 | Openai responses | Yes | 200K | 100K | Yes | Yes | Yes | -No | Closed | input $2/M · output $8/M cache read $0.5/M | 2025-04-16 | 2026-08-06 | |||
| o4-mini openai/o4-mini | OPOpenAI | o-series | o4-mini | Openai responses | Yes | 200K | 100K | Yes | Yes | Yes | -No | Closed | input $1.1/M · output $4.4/M cache read $0.275/M | 2025-04-16 | 2026-08-06 | |||
| GPT-4.1 openai/gpt-4.1 | OPOpenAI | GPT | gpt-4.1 | Openai responses | Yes | 1M | 33K | -No | Yes | Yes | Yes | Closed | input $2/M · output $8/M cache read $0.5/M | 2025-04-14 | 2026-08-06 | |||
| GPT-4.1 mini openai/gpt-4.1-mini | OPOpenAI | GPT | gpt-4.1-mini | Openai responses | Yes | 1M | 33K | -No | Yes | Yes | Yes | Closed | input $0.4/M · output $1.6/M cache read $0.1/M | 2025-04-14 | 2026-08-06 | |||
| GPT-4.1 nano openai/gpt-4.1-nano | OPOpenAI | GPT | gpt-4.1-nano | Openai responses | Yes | 1M | 33K | -No | Yes | Yes | Yes | Closed | input $0.1/M · output $0.4/M cache read $0.025/M | 2025-04-14 | 2026-08-06 | |||
| DeepSeek-R1 deepseek/deepseek-r1 | DEDeepSeek | DeepSeek | deepseek-r1 | Openai responses | Yes | 128K | 33K | Yes | Yes | -No | Yes | Open | input $1.35/M · output $5.4/M | 2025-01-20 | 2026-08-06 | |||
| o3-mini openai/o3-mini | OPOpenAI | o-series | o3-mini | Openai responses | Yes | 200K | 100K | Yes | Yes | Yes | -No | Closed | input $1.1/M · output $4.4/M cache read $0.55/M | 2024-12-20 | 2026-08-06 | |||
| Llama-3.3-70B-Instruct meta/llama-3.3-70b-instruct | MEMeta | Llama | llama-3.3-70b-instruct | Openai responses | Yes | 128K | 4.1K | -No | Yes | Yes | Yes | Open | input $0.71/M · output $0.71/M | 2024-12-06 | 2026-08-06 | |||
| o1 openai/o1 | OPOpenAI | o-series | o1 | Openai responses | Yes | 200K | 100K | Yes | Yes | Yes | -No | Closed | input $15/M · output $60/M cache read $7.5/M | 2024-12-05 | 2026-08-06 | |||
| GPT-4o mini openai/gpt-4o-mini | OPOpenAI | GPT | gpt-4o-mini | Openai responses | Yes | 128K | 16K | -No | Yes | Yes | Yes | Closed | input $0.15/M · output $0.6/M cache read $0.075/M | 2024-07-18 | 2026-08-06 | |||
| GPT-4o openai/gpt-4o | OPOpenAI | GPT | gpt-4o | Openai responses | Yes | 128K | 16K | -No | Yes | Yes | Yes | Closed | input $2.5/M · output $10/M cache read $1.25/M | 2024-05-13 | 2026-08-06 | |||
| GPT-4 Turbo openai/gpt-4-turbo | OPOpenAI | GPT | gpt-4-turbo | Openai responses | Yes | 128K | 4.1K | -No | Yes | -No | Yes | Closed | input $10/M · output $30/M | 2023-11-06 | 2026-08-06 |