# Azure

Azure serves 39 models on LLM API: 31 text models, 3 image models, 3 audio models and 2 embedding models from OpenAI, DeepSeek, Moonshot AI and 1 other lab.

Model ID prefix: `azure/` (for text and image requests) · 39 models · 4 labs · [Azure privacy policy](https://www.microsoft.com/en-us/privacy/privacystatement)
Updated: 2026-11-13
Canonical: https://llmapi.ai/providers/microsoft-azure/

## Models and prices

Prices when Azure serves the request.

### Text (31)

Prices per 1M tokens.

| Model | Model ID | Input | Output | Cache read | Context |
| --- | --- | --- | --- | --- | --- |
| [GPT-6 Astra](https://llmapi.ai/models/openai-gpt-6-astra/) | `azure/gpt-6-astra` | $10 | $50 | $1 | 1.05M |
| [GPT-6.1 Sol](https://llmapi.ai/models/gpt-6-1-sol/) | `azure/gpt-6.1-sol` | $2 | $10 | $0.1 | 1.05M |
| [GPT-6.1 Terra](https://llmapi.ai/models/gpt-6-1-terra/) | `azure/gpt-6.1-terra` | $1 | $5 | $0.05 | 1.05M |
| [GPT-6 Luna](https://llmapi.ai/models/openai-gpt-6-luna/) | `azure/gpt-6-luna` | $0.1 | $0.5 | $0.01 | 1.05M |
| [DeepSeek V4 Pro](https://llmapi.ai/models/deepseek-deepseek-v4-pro/) | `azure/deepseek-v4-pro` | $1.74 | $3.48 | $0.145 | 1.05M |
| [Kimi K3.1 Pro](https://llmapi.ai/models/kimi-k3-1-pro/) | `azure/kimi-k3.1-pro` | $2 | $10 | $0.2 | 1.05M |
| [GPT-6 Sol](https://llmapi.ai/models/openai-gpt-6-sol/) | `azure/gpt-6-sol` | $2 | $10 | $0.2 | 1.05M |
| [Grok 4.7](https://llmapi.ai/models/xai-grok-4-7/) | `azure/grok-4.7` | $6 | $18 | $1.5 | 500K |
| [GPT-5.6 Luna](https://llmapi.ai/models/openai-gpt-5-6-luna/) | `azure/gpt-5.6-luna` | $0.2 | $1.2 | $0.02 | 1.05M |
| [GPT-5.6 Sol](https://llmapi.ai/models/openai-gpt-5-6-sol/) | `azure/gpt-5.6-sol` | $4 | $20 | $0.4 | 1.05M |
| [GPT-5.6 Terra](https://llmapi.ai/models/openai-gpt-5-6-terra/) | `azure/gpt-5.6-terra` | $2 | $12 | $0.2 | 1.05M |
| [Grok 4.3](https://llmapi.ai/models/x-ai-grok-4-3/) | `azure/grok-4.3` | $1.25 | $2.5 | $0.2 | 1M |
| [DeepSeek V4 Flash (Apr 23)](https://llmapi.ai/models/deepseek-deepseek-v4-flash/) | `azure/deepseek-v4-flash` | $0.19 | $0.51 | $0.028 | 1.05M |
| [GPT-5.5](https://llmapi.ai/models/openai-gpt-5-5/) | `azure/gpt-5.5` | $5 | $30 | $0.5 | 1.05M |
| [Kimi K2.6](https://llmapi.ai/models/moonshotai-kimi-k2-6/) | `azure/kimi-k2.6` | $0.95 | $4 | $0.16 | 262K |
| [GPT-5.4 Mini](https://llmapi.ai/models/openai-gpt-5-4-mini/) | `azure/gpt-5.4-mini` | $0.75 | $4.5 | $0.07 | 400K |
| [GPT-5.4](https://llmapi.ai/models/openai-gpt-5-4/) | `azure/gpt-5.4` | $2.5 | $15 | $0.25 | 1.05M |
| [GPT-5.4 Pro](https://llmapi.ai/models/openai-gpt-5-4-pro/) | `azure/gpt-5.4-pro` | $30 | $180 | $3 | 1.05M |
| [GPT-5.2](https://llmapi.ai/models/openai-gpt-5-2/) | `azure/gpt-5.2` | $1.75 | $14 | $0.175 | 400K |
| [GPT-6 Luna Decisions](https://llmapi.ai/models/gpt-6-luna-decisions/) | `azure/gpt-6-luna-decisions` | $0.1 | — | $0.01 | 1.05M |
| [GPT-5.4 Nano](https://llmapi.ai/models/openai-gpt-5-4-nano/) (deprecated) | `azure/gpt-5.4-nano` | $0.2 | $1.25 | $0.02 | 400K |
| [GPT-5.3 Codex](https://llmapi.ai/models/openai-gpt-5-3-codex/) (deprecated) | `azure/gpt-5.3-codex` | $1.75 | $14 | $0.175 | 400K |
| [GPT-5.2 Codex](https://llmapi.ai/models/openai-gpt-5-2-codex/) (deprecated) | `azure/gpt-5.2-codex` | $1.75 | $14 | $0.175 | 400K |
| [GPT-5.1](https://llmapi.ai/models/openai-gpt-5-1/) (deprecated) | `azure/gpt-5.1` | $1.25 | $10 | $0.125 | 400K |
| [GPT-5.1 Codex Mini](https://llmapi.ai/models/openai-gpt-5-1-codex-mini/) (deprecated) | `azure/gpt-5.1-codex-mini` | $0.25 | $2 | $0.025 | 400K |
| [GPT-5.1 Codex](https://llmapi.ai/models/openai-gpt-5-1-codex/) (deprecated) | `azure/gpt-5.1-codex` | $1.25 | $10 | $0.125 | 400K |
| [GPT-5 Codex](https://llmapi.ai/models/openai-gpt-5-codex/) (deprecated) | `azure/gpt-5-codex` | $1.25 | $10 | $0.125 | 400K |
| [GPT-5 Nano](https://llmapi.ai/models/openai-gpt-5-nano/) (deprecated) | `azure/gpt-5-nano` | $0.05 | $0.4 | $0.005 | 400K |
| [GPT-5 Mini](https://llmapi.ai/models/openai-gpt-5-mini/) (deprecated) | `azure/gpt-5-mini` | $0.25 | $2 | $0.025 | 400K |
| [GPT-5](https://llmapi.ai/models/openai-gpt-5/) (deprecated) | `azure/gpt-5` | $1.25 | $10 | $0.125 | 400K |
| [GPT-5 Pro](https://llmapi.ai/models/openai-gpt-5-pro/) (deprecated) | `azure/gpt-5-pro` | $15 | $120 | — | 400K |

### Image (3)

Price per image.

| Model | Model ID | Price | Modes |
| --- | --- | --- | --- |
| [GPT Image 2.5 Sunburst](https://llmapi.ai/models/openai-gpt-image-2-5-sunburst/) | `azure/gpt-image-2.5-sunburst` | $0.22 / image | Generate, Edit |
| [GPT Image 2](https://llmapi.ai/models/openai-gpt-image-2/) | `azure/gpt-image-2` | $0.22 / image | Generate, Edit |
| [GPT Image 2.5 Flare](https://llmapi.ai/models/openai-gpt-image-2-5-flare/) | `azure/gpt-image-2.5-flare` | $0.22 / image | Generate, Edit |

### Audio (3)

Price per minute of audio or per 1K characters.

| Model | Model ID | Task | Price |
| --- | --- | --- | --- |
| [GPT Live 1](https://llmapi.ai/models/gpt-live-1/) | `gpt-live-1` | Realtime voice | $0.05 / minute |
| [Azure Whisper](https://llmapi.ai/models/openai-whisper/) | `whisper` | Transcription | $0.006 / minute |
| [GPT Transcribe](https://llmapi.ai/models/openai-gpt-transcribe/) | `gpt-transcribe` | Transcription | $0.0045 / minute |

### Embeddings (2)

Price per 1M input tokens.

| Model | Model ID | Input | Dimensions | Context |
| --- | --- | --- | --- | --- |
| [Azure OpenAI Text Embedding 3 Large](https://llmapi.ai/models/azure-text-embedding-3-large/) | `azure/text-embedding-3-large` | $0.13 | 3072 | 8K |
| [Azure OpenAI Text Embedding 3 Small](https://llmapi.ai/models/azure-text-embedding-3-small/) | `azure/text-embedding-3-small` | $0.02 | 1536 | 8K |

**Volume pricing.** At higher monthly volume, models on Azure may cost less. Book a call and sales will quote a price for your usage. [Book a call with sales](https://meetings.hubspot.com/julia-andriienko/llmapi) or [Create an account first](https://app.llmapi.ai/signup).

## Send requests to Azure

Put `azure/` before a model ID and the request goes to Azure. If Azure’s uptime over the last 5 minutes is below 90%, it goes to another provider of the model, unless it sends `X-No-Fallback: true`. [Routing docs](https://docs.llmapi.ai/features/routing)

Example: GPT-6 Astra, Responses (`POST /v1/responses`). Set LLMAPI_KEY to your LLM API key.

```python
import os

from openai import OpenAI

client = OpenAI(
    base_url="https://api.llmapi.ai/v1",
    api_key=os.environ["LLMAPI_KEY"],
)

response = client.responses.create(
    model="azure/gpt-6-astra",
    input="Hello",
)
print(response.output_text)
```

Prices synced 2026-11-13.

Next step: [Get API key](https://app.llmapi.ai/signup)