# MiniMax M3.1 Flash

Canonical page: https://agentsky.dev/models/minimax/minimax-m3.1-flash
JSON record: https://gateway.agentsky.dev/v1/models/minimax/minimax-m3.1-flash

MiniMax M3.1 Flash is a text and image and video-input model by MiniMax, available through the AgentSky API as minimax/minimax-m3.1-flash at $0.165 per million input tokens and $0.66 per million output tokens, with a 1M context window.

A fast, always-thinking MiniMax model with image and video understanding, tool calling and adjustable reasoning effort.

## Facts

- **Model id:** `minimax/minimax-m3.1-flash`
- **Maker:** MiniMax
- **Input modalities:** Text, Image, Video
- **Context:** 1M
- **Max output tokens:** 524,288
- **Aliases:** `minimax/minimax-m3.1-flash`, `minimax/MiniMax-M3.1-Flash`, `minimax-m3.1-flash`

## Pricing

USD per million tokens on the default plan. Signed-in pages show your own plan's price; every response carries the cost of that call in `usage.cost`.

| Meter | Per 1M tokens |
|---|---|
| Input | $0.165 |
| Output | $0.66 |
| Cache read | $0.0165 |
| Cache write | $0.165 |

## Use it

Anthropic wire base URL: `https://gateway.agentsky.dev`. OpenAI wire base URL: `https://gateway.agentsky.dev/v1`. Authenticate with an AgentSky API key (`ast_…`) and pass the model id.

### OpenAI SDK

```js
import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://gateway.agentsky.dev/v1",
  apiKey: process.env.AGENTSKY_API_KEY, // ast_…
});

const completion = await client.chat.completions.create({
  model: "minimax/minimax-m3.1-flash",
  messages: [{ role: "user", content: "Summarise this ticket." }],
});
console.log(completion.usage.cost); // USD, in the response
```

### Codex

```bash
export OPENAI_BASE_URL="https://gateway.agentsky.dev/v1"
export OPENAI_API_KEY="$AGENTSKY_API_KEY"

codex --model minimax/minimax-m3.1-flash
```

### OpenCode

```js
// opencode.json — then switch models any time with /models
{
  "$schema": "https://opencode.ai/config.json",
  "provider": {
    "agentsky": {
      "npm": "@ai-sdk/openai-compatible",
      "name": "AgentSky",
      "options": {
        "baseURL": "https://gateway.agentsky.dev/v1",
        "apiKey": "{env:AGENTSKY_API_KEY}"
      },
      "models": { "minimax/minimax-m3.1-flash": {} }
    }
  }
}
```

## Run it with an agent

- [Hermes + MiniMax M3.1 Flash](https://agentsky.dev/agents/hermes/with/minimax-m3.1-flash)
- [Claude Code + MiniMax M3.1 Flash](https://agentsky.dev/agents/claude-code/with/minimax-m3.1-flash)
- [Codex + MiniMax M3.1 Flash](https://agentsky.dev/agents/codex/with/minimax-m3.1-flash)
- [OpenClaw + MiniMax M3.1 Flash](https://agentsky.dev/agents/openclaw/with/minimax-m3.1-flash)
- [pi + MiniMax M3.1 Flash](https://agentsky.dev/agents/pi/with/minimax-m3.1-flash)
- [DeepSeek Harness + MiniMax M3.1 Flash](https://agentsky.dev/agents/dsh/with/minimax-m3.1-flash)
- [Kimi Code + MiniMax M3.1 Flash](https://agentsky.dev/agents/kimi-code/with/minimax-m3.1-flash)
- [OpenCode + MiniMax M3.1 Flash](https://agentsky.dev/agents/opencode/with/minimax-m3.1-flash)
- [MiniMax Code + MiniMax M3.1 Flash](https://agentsky.dev/agents/minimax-code/with/minimax-m3.1-flash)

## Questions

### What is MiniMax M3.1 Flash?

MiniMax M3.1 Flash is a model from MiniMax. A fast, always-thinking MiniMax model with image and video understanding, tool calling and adjustable reasoning effort.

### How much does MiniMax M3.1 Flash cost?

$0.165 / $0.66 per million tokens at the prices shown, for input and output respectively. The exact price of every call comes back in the response as usage.cost, so you never have to compute it.

### What is the context length of MiniMax M3.1 Flash?

1M tokens, and it writes up to 524K tokens in one reply. These are the limits listed for this model in the current AgentSky catalog.

### Which clients can call MiniMax M3.1 Flash?

Anything that speaks the OpenAI-compatible request format. Point the client's base URL at the gateway, use an AgentSky key, and pass minimax/minimax-m3.1-flash as the model.

### How do I name MiniMax M3.1 Flash in a request?

The gateway accepts minimax/minimax-m3.1-flash, minimax/MiniMax-M3.1-Flash, minimax-m3.1-flash. Any of them resolves to the same model, so an existing integration usually needs no change to its model string.

### Can MiniMax M3.1 Flash read images?

Yes. Its listed input types are text, image, video. Include the image with your request; image input does not imply image generation.

### What output can MiniMax M3.1 Flash produce?

The listed output types are text. This model returns text. Producing image, video or audio files requires a suitable tool or another model; it is not included in text generation.

### How should I plan a long prompt for MiniMax M3.1 Flash?

Plan your instructions, conversation history and source material around the 1M-token context limit, leaving room for the response. The listed response ceiling is 524K tokens. A larger window lets you supply more relevant material; it does not make unrelated content useful.

### What would 10,000 input tokens and 2,000 output tokens cost with MiniMax M3.1 Flash?

At the displayed input and output rates, the model-token subtotal is $0.00297. This example assumes uncached input and excludes additional pricing categories, tool calls and agent runtime. Actual usage determines the final charge.

### How is cached input priced for MiniMax M3.1 Flash?

The catalog lists $0.0165 per million cache-read tokens. Cache writes are listed at $0.165 per million tokens. Repeating a prompt does not by itself guarantee a cache hit; only usage reported as cached receives that rate.

### Does the MiniMax M3.1 Flash token price cover an entire agent task?

No. The model price covers the model usage described above. A task can also incur tool and runtime charges, and several model calls may be needed to complete it. Compare total task usage when evaluating cost.

### How do I use MiniMax M3.1 Flash on AgentSky?

The composer above preselects MiniMax M3.1 Flash for a compatible agent. Enter a concrete task, select any tools or connectors it needs, and send. Sign in if prompted; paid execution requires available credits.