Alex Getmanearly AI signals
EN

MiniMax M3.1 Flash

MiniMax

Released Updated
Context window
1M
1,000,000 tokens
Input / Output
image, text, video → text

API pricing

USD / 1M tokens

InputOutputCached input
  • $0.075
openrouter
  • $0.30
openrouter
  • $0.0075
openrouter
Calculate your workload

Timeline

  1. · Weights version · evidence link
Input / output price · USD / 1M tokens
ModelEvidence linksInput / output price
minimax-m3.1-flash
standard · text
opencode-go$0.15 / $0.60
minimax/minimax-m3.1-flash
standard
openrouter$0.075 / $0.30
minimax/minimax-m3.1-flash
standard
vercel-gateway$0.15 / $0.60
  1. · Catalogue listing · GitHub · MiniMax-AI/minimax-code · code
    Excerpt
    { mode: "switchable", default_value: "true" }, variants: { "none-thinking": { thinking: { type: "disabled" } }, thinking: { thinking: { type: "adaptive" } }, }, capabilities: MINIMAX_M3_FILE_API_CAPABILITIES, }, "MiniMax-M3.1-Flash": { name: "M3.1-Flash", attachment: true, reasoning: true, tool_call: true, temperature: true, modalities: { input: ["text", "image", "video"], output: ["text"] }, limit: { context: 512000, output: 128000 }, contextWindowOptions: [512000, 1000000], contextWindowOptionHints: { "1000000": "higher_usage" }, options: { reasoningSummary: "auto" }, thinking: { effortOptions: ["default", "low", "medium", "high", "xhigh", "max"], defaultEffort: "default", }, thinking_config: { mode: "forced_on" }, variants: { "none-thinking": { thinking: { type: "disabled" } },
  2. · Catalogue listing · GitHub · MiniMax-AI/minimax-code · code
    Excerpt
    options: { authMode: "managed-login", apiKey: "sk-xxx", baseURL: PRESET_BASE_URLS[key], }, models: MINIMAX_MODELS, }; return { provider: { minimax: provider } as ModelsConfig, defaultModel: "minimax/MiniMax-M3.1-Flash", }; } export const DEFAULT_MODEL_PRESETS: Record< PresetKey, { provider: ModelsConfig; defaultModel: string } > = { "cn-test": buildPresetEntry("cn-test"), "cn-dev": buildPresetEntry("cn-dev"), "cn-staging": buildPresetEntry("cn-staging"), "cn-prod": buildPresetEntry("cn-prod"), "en-test": buildPresetEntry("en-test"), "en-dev": buildPresetEntry("en-dev"), "en-staging": buildPresetEntry("en-staging"), "en-prod": buildPresetEntry("en-prod"), } as const; const DEFAULTS: Omit< Config, | "dataDir" | "agentsDir" | "sessionsDir" | "memoryDir" | "skillsDir" | "builtinSkillsDir" | "logsDir" | "plug

    This code reference does not establish a working model identifier.

Evidence links

  • · Catalogue listing · MiniMax API · MiniMax-M3.1-Flash

Signals 3

Specifications

MiniMax M3.1 Flash is a model from MiniMax with open weights, released on 19 Oct 2026. The context window is 1,000,000 tokens. Pricing is $0.075 per million input tokens and $0.30 per million output tokens.

Context window
1,000,000
Input
image · text · video
Output
text
Weights
Open
Input · USD / 1M tokens
$0.075
Output · USD / 1M tokens
$0.30
Cached input · USD / 1M tokens
$0.0075

Questions

What is the context window of MiniMax M3.1 Flash?

The context window is 1,000,000 tokens.

How much does MiniMax M3.1 Flash cost?

Pricing is $0.075 per million input tokens and $0.30 per million output tokens. Cached input is $0.0075 per million.

Are the weights of MiniMax M3.1 Flash publicly available?

Yes. MiniMax publishes the weights.

When was MiniMax M3.1 Flash released?

On 19 Oct 2026.