Mai Thinking 1
MAI-Thinking-1Pricing
List prices at Azure AI Foundry, in US dollars per million tokens.
| Tier | Input / 1M | Output / 1M | |
|---|---|---|---|
| Standard | $2.00 | $8.00 | |
| Cached input 90% off input | $0.20 | 90% off input |
What it costs a month
At Azure AI Foundry list prices, 30 days.
- Chat assistant5,000 requests a day, 2K in / 0.5K out, cached$1,038
- RAG over documents2,000 requests a day, 8K in / 0.6K out, cached$816
- Coding agent1,000 requests a day, 40K in / 2K out, cached$1,368
- Overnight batch20,000 requests a day, 4K in / 0.4K out$6,720
Where to run it
2 hosts serve Mai Thinking 1. The comparison is on blended price, 3 parts input to 1 part output.
| Host | In / out per 1M | Model id | |
|---|---|---|---|
Azure AI FoundryCloud MAI-Thinking-1 | $2.00 / $8.00 | MAI-Thinking-1 | |
AIHubMixGateway mai-thinking-1 | $2.00 / $8.00 | mai-thinking-1 |
Capabilities
Core
- Streaming
- Function calling
- JSON mode
- Structured outputs
Multimodal
- Vision
- Image input
- Audio
- Image generation
- Video
Advanced
- Reasoning
- Tool calling
- MCP
- Prompt caching
- Batch API
- Embeddings
- Takes in
- Text
- Produces
- Text
- Features
- Prompt caching
Cheaper alternatives
Current models that cost less and keep most of what this one can do: tools, vision, reasoning, structured output, caching and enough context.
Same model, cheaper host
No host sells it for less than Azure AI Foundry.
Smaller Microsoft models
No cheaper Microsoft model keeps its key capabilities.
Other frontier labs
- 14% less
- 14% less
- 43% less
- 94% less
Open-weight picks
- 14% less
- 43% less
- 51% less
- 75% less
Call it
Using Azure AI Foundry's API.
from litellm import completion
response = completion(
model="azure_ai/MAI-Thinking-1",
messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)Quick answers
How much does Mai Thinking 1 cost?
On Azure AI Foundry, Mai Thinking 1 costs $2.00 per million input tokens and $8.00 per million output tokens. Cached input costs $0.20 per million tokens.
Which APIs offer Mai Thinking 1?
Mai Thinking 1 runs on 2 APIs: Azure AI Foundry and AIHubMix.
What is Mai Thinking 1's context window?
256K tokens, with up to 64K tokens in one reply.
Is Mai Thinking 1 being retired?
No retirement date is scheduled for it on any API we track.
What are cheaper alternatives to Mai Thinking 1?
Models that cost less and keep most of what it can do: Gemini 4 Hydrogen on Google AI Studio (14% less), Grok 4.7 on xAI (14% less) and Qwen3.8.2 4T A95B on DeepInfra (14% less). Savings are on a mix of 3 input tokens to 1 output token.
What is Mai Thinking 1's API model id?
Use MAI-Thinking-1 with Azure AI Foundry. Other hosts use their own ids: mai-thinking-1 on AIHubMix.
Sources
Raw catalog entry for MAI-Thinking-1 on Azure AI Foundry
{
"cache_read_input_token_cost": 2e-7,
"input_cost_per_token": 0.000002,
"litellm_provider": "azure_ai",
"max_input_tokens": 256000,
"max_output_tokens": 64000,
"mode": "chat",
"output_cost_per_token": 0.000008,
"source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'",
"supported_endpoints": [
"/v1/chat/completions"
],
"supported_modalities": [
"text"
],
"supported_output_modalities": [
"text"
],
"supports_function_calling": true,
"supports_pdf_input": false,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_tool_choice": true
}