Microsoft AIImageReleased 4 September 2026
MAI-Image-2.6 Flash pricing, context and benchmark
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 latency-sensitive, high-throughput production image generation and editing at comparable quality to the precision tier....
4K
Input context
n/a
Output context
$1.75
Per 1M input
1
Providers
n/a
AA index
01 · Model Overview
Everything that matters, in one table
Context, pricing, cache, modalities and tooling, from the model registry and Artificial Analysis.
| Model | MAI-Image-2.6 Flash |
| Model ID | microsoft/mai-image-2.6-flash |
| Provider | Microsoft AI |
| Release date | 4 September 2026 |
| Status | Generally available |
| Input context | 4,096 tokens |
| Output context | Provider default |
| Official input pricing | $1.75 per 1M tokens |
| Official output pricing | $19 per 1M tokens |
| Cache read pricing | Not published |
| Market input pricing | $1.75 per 1M (cheapest route) |
| Market output pricing | Free per 1M (cheapest route) |
| Input modalities | text · image |
| Output modalities | image |
| Reasoning control | Not exposed |
| Tool support | Text generation only |
| Tokenizer | Other |
| Provider routes | 1 endpoint |
| Artificial Analysis index | Not published |
| Speed | Not published |
| Knowledge cutoff | Not publicly stated |
Input and output support
| Modality | Input | Output | Billed at |
|---|---|---|---|
| Text | ✓ yes | no | $1.75 in |
| Image | ✓ yes | ✓ yes | $1.75 in |
| Audio | no | no | not supported |
| Video | no | no | not supported |
| File (PDF) | no | no | not supported |
02 · Overview
What is MAI-Image-2.6 Flash?
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 latency-sensitive, high-throughput production image generation and editing at comparable quality to the precision tier....
MAI-Image-2.6 Flash carries a 4K token window, uses the Other tokenizer and is served by Microsoft AI. On Hoodgen it sits in the Image tier of the model menu next to its siblings, so you can switch mid conversation without losing the thread.
03 · Release
Release and what changed from the previous version
Released4 September 2026
| Property | Muse Image | MAI-Image-2.6 Flash | Change |
|---|---|---|---|
| Released | Aug 2026 | Sept 2026 | Newer release |
| Context | 66K | 4K | Changed |
| Max output | n/a | n/a | Unchanged |
| Input price | Free | $1.75 | Higher |
| Output price | Free | $19 | Higher |
| Input modalities | text, image | text, image | Unchanged |
| AA index | n/a | n/a | Newer benchmark run |
04 · Capabilities
Features and capabilities
◉
Vision
Screenshots, charts and photographed documents are read at the text token rate.
07 · Use cases
What can you do with MAI-Image-2.6 Flash?
Everyday writing
Drafts, rewrites, summaries and replies.
Research
Source material condensed with the key numbers kept.
Chat
General questions where latency and cost both matter.
Tooling inside Hoodgen
Writer, Humanizer, Coding and the rest of the tool suite.
09 · Pricing
MAI-Image-2.6 Flash pricing
Official pricing
Provider pricing
$1.75 / 1M in
$1.75 / 1M in
- image output, billed per generation
- image output from text, image input
Token price
$1.75 / 1M in
$19 / 1M out
- 4K context
- text, image input
Cheapest route
$1.75 / 1M in
Free / 1M out
- 1 route on OpenRouter
- What Hoodgen routes to first
- Same model, lower bill
Market pricing, every route
| Provider | Tier | Input | Output | Cache read | Uptime 24h |
|---|---|---|---|---|---|
| Azure | standard | $1.75 | n/a | n/a | 100.0% |
API pricing and cost calculator
| Rate | Per call | Total | Credits |
|---|---|---|---|
| Cheapest route | $0.0350 | $17.50 | 16625 |
| List price | $0.0635 | $31.75 | 30163 |
10 · Developers
API and developer information
| Model ID | microsoft/mai-image-2.6-flash |
| Endpoint | https://openrouter.ai/api/v1/chat/completions |
| Parameters | prompt and max_tokens |
| Streaming | Yes, server sent events |
| Modality string | text+image->image |
| Max prompt tokens | 4,096 |
| Max completion tokens | provider default |
curl https://openrouter.ai/api/v1/chat/completions \
-H "Authorization: Bearer $OPENROUTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "microsoft/mai-image-2.6-flash",
"messages": [{ "role": "user", "content": "Summarise this document." }],
"max_tokens": 1024
}'11 · Limitations
Model limitations
| Output cap | Provider default tokens per request. Long deliverables have to be chunked. |
| Benchmarks not published | Artificial Analysis does not publish an Intelligence Index for this release, so no benchmark score is claimed here. |
| Knowledge cutoff | The provider does not state a fixed cutoff for every release. Verify very recent events against search. |
12 · Comparison
MAI-Image-2.6 Flash vs other Microsoft AI models
| Model | Context | Input /1M | Output /1M | AA index | Released |
|---|---|---|---|---|---|
| MAI-Image-2.6 Flash | 4K | $1.75 | $19 | n/a | Sept 2026 |
| GPT Image 1 | 400K | $10 | $10 | n/a | Jun 2026 |
| GPT Image 2.6 Sunburst | 400K | $8 | $8 | n/a | Nov 2026 |
| GPT Image 2.6 Flare | 400K | $8 | $8 | n/a | Nov 2026 |
| GPT Image 2 | 400K | $8 | $8 | n/a | Jun 2026 |
| GPT Image 2.5 Flare | 400K | $8 | $8 | n/a | Sept 2026 |
13 · Privacy
Privacy and data policy
- On Hoodgen, prompts and attachments answer that request and stay in your conversation history so you can reopen it. They are not used to train models.
- Requests route through OpenRouter to Microsoft AI and are covered by that provider's API terms.
- Do not paste secrets or personal data you would not send to any hosted model.
14 · FAQ
MAI-Image-2.6 Flash questions, answered
MAI-Image-2.6 Flash is a image model from Microsoft AI, released 4 September 2026. 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 latency-sensitive, high-throughput production image generation and editing at comparable quality to the precision tier....
✦
Start chatting with MAI-Image-2.6 Flash
Free to try on Hoodgen AI, with a live credit estimate before every send. No API key, no setup.