VENICE ATLAS · MODEL DOSSIER · MIMO-V2.6-FLASH

Model overview

MiMo-V2.6-Flash

Name: MiMo-V2.6-Flash
Brand: venice.ai
Price: 0.1750 USD
Availability: InStock

MiMo-V2.6-Flash is Xiaomi's efficiency-balanced omnimodal model: a sparse Mixture-of-Experts with 309B total and 15B activated parameters, natively understanding text, image, video, and audio with a 1M-token context window. Trained with mixed reinforcement learning across coding, general agents, visual, and cybersecurity tasks, it is built for long-horizon coding, tool use, and computer use.

xiaomi-mimo-v2-6-flash · venice.ai

Text · Venice catalog$0.17 per 1M tokensPrice on Venice AI

ModalityTextOn Venice AI

Primary price$0.17 per 1M tokensper 1M tokens

Context window1MMax tokens

Benchmarks16Benchmark results

Benchmark results

See the tests behind each score. They use the benchmark’s original scoring scale.

Agents#2731.85 rating Coding#2733.75 rating General intelligence#3444.68 rating Knowledge#12-1.97 rating Productivity#14-1.97 rating Reasoning#4043.26 rating Safety#915.02 rating Tool Calling#2525.99 rating

Agents7 results

Agents' Last Examagents-last-exam · agents

27.6%

ReportedOct 2026

AutomationBench v1.0.6automationbench-1.0.6 · agents

52.3%

ReportedOct 2026

ExploitGymexploitgym · agents

6.00%

ReportedOct 2026

JobBenchjobbench · agents

61.2%

ReportedOct 2026

Program Benchprogram-bench · agents

26.0%

ReportedOct 2026

SEC-bench Prosec-bench-pro · agents

47.5%

ReportedOct 2026

Toolathlon-Verifiedtoolathlon-verified · agents

73.6%

ReportedOct 2026

Coding6 results

CyberGymcybergym · code

95.1%

ReportedOct 2026

DeepSWE 1.1deepswe-1.1 · code

67.9%

ReportedOct 2026

ExploitBenchexploitbench · code

25.3%

ReportedOct 2026

MiMo Coding Benchmimo-coding-bench · code

61.2%

ReportedOct 2026

MiMo Cyber Benchmimo-cyber-bench · code

77.2%

ReportedOct 2026

MiMo Visual Codingmimo-visual-coding · code

71.5%

ReportedOct 2026

Multimodal1 result

OSWorld-Verifiedosworld-verified · multimodal

80.8%

ReportedOct 2026

Reasoning2 results

Terminal-Bench 2.1terminal-bench-2.1 · reasoning

87.6%

ReportedOct 2026

Terminal-Bench 4.0terminal-bench-4.0 · reasoning

28.8%

ReportedOct 2026

Learn what each benchmark measures ↗

Pricing detail

Input price per 1M tokens: $0.17
Output price per 1M tokens: $0.35
Cache read price per 1M tokens: $0.0037
Blended price per 1M tokens (50/50): $0.26

Prices are published by Venice AI. Venice model page ↗

Capabilities

ReasoningFunction callingVisionAudio inputVideo inputWeb search

Endpoint metadata

Privacy: private
Quantization: fp8
Maximum completion tokens: 131K
Uncensored: No
Beta: No
Mapping confidence: 100.0%

View model source ↗

All capabilities

Max Images: 10
Quantization: fp8
Supports E2 E E: No
Supports Vision: Yes
Supports X Search: No
Optimized For Code: Yes
Supports Log Probs: No
Supports Reasoning: Yes
Supports Web Search: Yes
Supports Audio Input: Yes
Supports Video Input: Yes
Default Reasoning Effort: high
Reasoning Effort Options: none, low, medium, high
Supports Multiple Images: Yes
Supports Response Schema: Yes
Supports Tee Attestation: No
Supports Function Calling: Yes
Supports Reasoning Effort: Yes

Related models

More from xiaomi

xiaomi-mimo-v2-5MiMo-V2.5$0.40 input per 1M tokens ↗