# MiMo V2.6 Pro MiMo-V2.6-Pro is Xiaomi's most capable reasoning model, built for complex engineering, long-horizon agent tasks and research work, with a one-million-token context window. It reasons by default with an off switch, supports tool calling, and accepts image as well as text input. Its published context window is 1,048,576 tokens. The advertised input rate is $0.435 per million input tokens. The advertised output rate is $0.87 per million output tokens. - Model identifier: ` xiaomi/mimo-v2.6-pro ` - Creator: Xiaomi - Providers: Tencent - Model type: Text generation - Canonical model page: [MiMo V2.6 Pro]() - API availability: Listed as serving through Impossibl. ## Providers Tencent hosts MiMo V2.6 Pro. Impossibl routes your request intelligently and handles failover automatically when a provider is down. | Provider | Endpoint location | Routes | Verified context window | Tool calling | | --- | --- | --- | --- | --- | | Tencent | Not specified | 1 | Not verified | Not verified | The model price applies whichever provider serves the request. Endpoint locations do not guarantee inference residency. ## Specs and Capabilities - Context window: 1,048,576 tokens - Maximum output tokens: Not published in the public catalog; this is separate from the context window. - Inputs: text, image - Outputs: text - Tool calling: Not published ## API access Use ` xiaomi/mimo-v2.6-pro ` as the model identifier through the Impossibl API. Published API endpoints: - ` /v1/chat/completions ` [API quickstart]() · [Models and billing documentation]() ## Published API prices All rates are in USD. An unpublished rate is unknown, not zero. Workspace-specific pricing, taxes, balance-purchase fees, billing adjustments, and tool charges can affect the amount paid. | Usage | Published base rate | Billing unit | | --- | --- | --- | | Input | $0.435 | per million input tokens | | Output | $0.87 | per million output tokens | | Cache read | $0.0036 | per million cached input tokens | | Cache write (default retention) | Not published | per million tokens | | Cache write (one-hour retention) | Not published | per million tokens | | Audio input | Not published | per million audio input tokens | ## Benchmarks Last checked: 2026-10-14T17:26:48.816Z. Configurations are evaluated separately. API scores retain their original units. Unmeasured scores are omitted. ### MiMo-V2.6-Pro Source: [Evaluation source]() | Benchmark | Score | | --- | --- | | Intelligence Index | 46.32 | | Omniscience Index | 8.38 | | Humanity’s Last Exam | 49.35% | | SciCode | 60.88% | | CritPt | 26.57% | | AA-LCR | 86.33% | | Multilingual LCR | 18.33% | | GDPval Elo | 1684.34 | | GDP.pdf All-pass | 19.20% | | AutomationBench Partial | 58.62% | | AnalystAgent | 37.50% | | legal index (API) | 44.8 | | economics index (API) | 53.2 | | engineering index (API) | 46.9 | | intelligence index (API) | 46.3 | | strategy and ops index (API) | 47.8 | | finance and accounting index (API) | 46.1 | | healthcare and medical index (API) | 41.8 | Full benchmark data and breakdowns: [Complete benchmark snapshot](). ## Availability and retirement The model is listed as serving. No retirement is announced in the current public catalog. ## Frequently asked questions ### What is MiMo V2.6 Pro? MiMo-V2.6-Pro is Xiaomi's most capable reasoning model, built for complex engineering, long-horizon agent tasks and research work, with a one-million-token context window. It reasons by default with an off switch, supports tool calling, and accepts image as well as text input. Sources: [Tencent Cloud TokenHub pricing](); [OpenRouter model listing]() ### How much does MiMo V2.6 Pro cost? MiMo V2.6 Pro costs $0.435 per million input tokens and $0.87 per million output tokens through the Impossibl API. Cache reads cost $0.0036 per million tokens. All rates are in USD. ### What is the context length of MiMo V2.6 Pro? MiMo V2.6 Pro has a 1,048,576-token context window through the Impossibl API. ### What inputs and outputs does MiMo V2.6 Pro support? MiMo V2.6 Pro accepts text and image as input. MiMo V2.6 Pro returns text. ### How do I use MiMo V2.6 Pro through an API? MiMo V2.6 Pro is available through the Impossibl API. Use xiaomi/mimo-v2.6-pro as the model identifier with /v1/chat/completions. The quickstart explains how to create an API key and send your first request. ## Sources and related links Prices, limits, capabilities, endpoints, and availability come from the public Impossibl catalog. Creator documentation supplies descriptions and release dates where available; it does not override the published API offering. - [Public Impossibl model catalog]() - [Full model directory as JSON]() - [MiMo V2.6 Pro: model details and pricing]() - [Model directory]() - [Tencent Cloud TokenHub pricing]() - [OpenRouter model listing]()