# MAI-Code-1-Flash Usage, Cost & Rank | OpenCode Data

Microsoft coding model built for fast, efficient assistance in everyday developer workflows

- Page: https://opencode.ai/data/microsoft/mai-code-1-flash
- JSON: https://opencode.ai/data/microsoft/mai-code-1-flash.json
- Model ID: microsoft/mai-code-1-flash
- Lab: Microsoft

## Model facts

| Fact | Value |
| --- | --- |
| Context window | 256K |
| Max output | 128K |
| Knowledge cutoff | 2025-12 |
| Release date | 2026-06-02 |
| Input modalities | text |
| Output modalities | text |
| Reasoning | Yes |
| Tool calling | Yes |
| Open weights | No |

## Benchmarks

| Benchmark | Score | Metric | Source |
| --- | --- | --- | --- |
| SWE-Bench Pro | 51.2 | resolve rate | https://microsoft.ai/news/introducingmai-code-1-flash/ |
| SWE-Bench Verified | 71.6 | resolved | https://llm-stats.com/benchmarks/swe-bench-verified |
| Terminal-Bench | 54.8 | success rate | https://llm-stats.com/benchmarks/terminal-bench-2 |
| GPQA Diamond | 84.6 | accuracy | https://llm-stats.com/benchmarks/gpqa |

## Methodology

- Updates: Aggregated every hour. Days and weeks use UTC.
- Tokens: Input, output, reasoning, and cached tokens for each request.
- Users and sessions: Approximate counts of distinct users and OpenCode sessions.
- Cost: Session cost is the average cost per OpenCode session. Token prices are list prices from the OpenCode model catalog.
- Retention: The share of a model's users in one week who use it again the next week.
- Citation: Cite OpenCode Data (opencode.ai/data) with the update time shown at the top of the page.