Microsoft AI: MAI-Image-2.6 Flash

microsoft/mai-image-2.6-flash

MAI-Image-2.6 Flash is the lower-latency, lower-cost member of the MAI-Image-2.6 family from Microsoft AI, built for latency-sensitive, high-throughput production image generation and editing at comparable quality to the precision tier....

Modalities: text+image->image
In / out price: $1.75 / $0per 1M
Context: 4K
Released: Sep 4, 2026
Knowledge cutoff: —

Providers

Every request enters through InfAPI. One key calls every model in the catalog. Upstream groups, ratios, and tiers are not shown.

Endpoint	Input	Output	Context	Status
InfAPI	$1.75	$0	4K	Available

Input: Text, Image
Output: Image
Tokenizer: Other
Max output: 1,024
Endpoint: Image

Pricing

Listed price for this model on this gateway. Token prices are per 1M tokens.

Item	Price	Unit
Inputprompt	$1.75	per 1M tokens
Outputcompletion	$0	per 1M tokens
Image tokensimage_token	$19	per 1M tokens
Image outputimage_output	$19	per 1M tokens

API

Send a prompt to the image endpoint. The response includes the generated image as base64.

Get your API key

Create a key on the keys page and set it as an environment variable: Keys

shell

export INFAPI_API_KEY=sk-...

Make your first request

Use microsoft/mai-image-2.6-flash

Python

import base64
import requests

response = requests.post(
    "https://infapi.cc/v1/images",
    headers={
        "Authorization": "Bearer $INFAPI_API_KEY",
        "Content-Type": "application/json",
    },
    json={
        "model": "microsoft/mai-image-2.6-flash",
        "prompt": "A serene mountain landscape at sunset with dramatic clouds",
    },
)
response.raise_for_status()
for index, image in enumerate(response.json().get("data", [])):
    raw = base64.b64decode(image["b64_json"])
    with open(f"output_{index}.png", "wb") as handle:
        handle.write(raw)
    print(f"Saved image {index + 1}")

Endpoint

POST https://infapi.cc/v1/images

Authorization: Bearer $INFAPI_API_KEY

Using third-party SDKs

Point the OpenAI SDK at https://infapi.cc/v1 with $INFAPI_API_KEY. The HTTP samples above are the request shape this gateway accepts.

Python (OpenAI)

import base64
from openai import OpenAI

client = OpenAI(
    base_url="https://infapi.cc/v1",
    api_key="$INFAPI_API_KEY",
)

result = client.images.generate(
    model="microsoft/mai-image-2.6-flash",
    prompt="A serene mountain landscape at sunset with dramatic clouds",
)
for index, image in enumerate(result.data):
    raw = base64.b64decode(image.b64_json)
    open(f"output_{index}.png", "wb").write(raw)

Supported parameters

max_completion_tokens
Max completion tokens
Same idea as max_tokens. Some newer models use this field instead.
max_tokens
Max tokens
Upper bound on generated tokens. Output stops at the limit.
temperature
Temperature
Sampling temperature. Lower is steadier, higher is more varied. Often 0 to 2.

FAQ

What is this model?

MAI-Image-2.6 Flash is the lower-latency, lower-cost member of the MAI-Image-2.6 (/microsoft/mai-image-2.6) family from Microsoft AI, built for latenc…

How much does it cost?

$1.75 / $0

What inputs and outputs does it support?

text+image->image

When was it released?

Sep 4, 2026

Endpoint

Input

Output

Context

Status

InfAPI

$1.75

Available

Item

Price

Unit

Inputprompt

$1.75

per 1M tokens

Outputcompletion

per 1M tokens

Image tokensimage_token

$19

per 1M tokens

Image outputimage_output

$19

per 1M tokens

API

Send a prompt to the image endpoint. The response includes the generated image as base64.

Get your API key

Create a key on the keys page and set it as an environment variable: Keys

shell

export INFAPI_API_KEY=sk-...

Make your first request

Use microsoft/mai-image-2.6-flash

Python

import base64
import requests

response = requests.post(
    "https://infapi.cc/v1/images",
    headers={
        "Authorization": "Bearer $INFAPI_API_KEY",
        "Content-Type": "application/json",
    },
    json={
        "model": "microsoft/mai-image-2.6-flash",
        "prompt": "A serene mountain landscape at sunset with dramatic clouds",
    },
)
response.raise_for_status()
for index, image in enumerate(response.json().get("data", [])):
    raw = base64.b64decode(image["b64_json"])
    with open(f"output_{index}.png", "wb") as handle:
        handle.write(raw)
    print(f"Saved image {index + 1}")

Endpoint

POST https://infapi.cc/v1/images

Authorization: Bearer $INFAPI_API_KEY

Using third-party SDKs

Point the OpenAI SDK at https://infapi.cc/v1 with $INFAPI_API_KEY. The HTTP samples above are the request shape this gateway accepts.

Python (OpenAI)

import base64
from openai import OpenAI

client = OpenAI(
    base_url="https://infapi.cc/v1",
    api_key="$INFAPI_API_KEY",
)

result = client.images.generate(
    model="microsoft/mai-image-2.6-flash",
    prompt="A serene mountain landscape at sunset with dramatic clouds",
)
for index, image in enumerate(result.data):
    raw = base64.b64decode(image.b64_json)
    open(f"output_{index}.png", "wb").write(raw)

Supported parameters

max_completion_tokens
Max completion tokens
Same idea as max_tokens. Some newer models use this field instead.
max_tokens
Max tokens
Upper bound on generated tokens. Output stops at the limit.
temperature
Temperature
Sampling temperature. Lower is steadier, higher is more varied. Often 0 to 2.