aiticker

Xiaomi · Released Sep 21, 2026

MiMo-V2.6-Flash

MiMo-V2.6-Flash is an open-source foundation model developed by Xiaomi. Built on a Mixture-of-Experts architecture with 309B total parameters and 15B activated per token, it employs a hybrid attention mechanism for...

ReasoningOpen weightsVision
  • Top 28%ProofBench
  • Top 42%SciCode
  • Top 42%CritPt
Compare in showdown → OpenRouter ↗ All Xiaomi models
Released
Sep 21 2026
Context window
1.05M 131K out
Input / 1M tokens
$0.14 from Free
Output / 1M tokens
$0.28 from Free

Where to run it

33 providers compared

Free to try on OpenCode, AMD, NaN — free endpoints are often limited-time and rate-limited. Included in Xiaomi Token Plan (China), Xiaomi Token Plan (Singapore), Xiaomi Token Plan (Europe), OpenCode Go. Cheapest: Vultr at $0.10 / $0.25 per 1M input / output tokens — 37% less than the priciest option.

ProviderInputOutputCache readContextMax outputUptimevs. best
OpenCodefree · may be limited-time Free Free Free200K32K— Free
AMDfree · may be limited-time Free Free Free1M131K— Free
NaNfree · may be limited-time Free Free —1M131K— Free
Xiaomi Token Plan (China)subscription plan Plan Plan Plan1M131K— Plan
Xiaomi Token Plan (Singapore)subscription plan Plan Plan Plan1M131K— Plan
Xiaomi Token Plan (Europe)subscription plan Plan Plan Plan1M131K— Plan
OpenCode Gosubscription plan Plan Plan Plan1M131K— Plan
Vultr $0.10 $0.25 —1M131K— Cheapest
DarkbloomFP4 $0.10 $0.28 $0.051M131K99.4%24h +5%
Kilo Gateway $0.10 $0.28 $0.051M131K— +5%
DevPass (LLM Gateway) $0.12 $0.25 $0.0031M131K— +11%
DeepInfraFP8 $0.13 $0.27 $0.0031M944K99.8%24h +21%
Relacemxfp4 · MXFP4 $0.13 $0.28 $0.0031M131K99.9%24h +22%
MakoraFP8 $0.13 $0.28 $0.0021M131K96.7%24h +22%
XiaomiFP8 $0.14 $0.28 $0.0031M131K100%24h +27%
NovitaFP8 $0.14 $0.28 $0.0031M131K99.6%24h +27%
GMICloudBF16 $0.14 $0.28 $0.0031.05M945K93.4%24h +27%
LLM Gateway $0.14 $0.28 $0.0031M66K— +27%
Tempr Gateway $0.14 $0.28 $0.0031M131K— +27%
NanoGPT $0.14 $0.28 $0.0031M131K— +27%
Boundless $0.14 $0.28 $0.0031M131K— +27%
EmpirioLabs AI $0.14 $0.28 $0.141M131K— +27%
Requesty $0.14 $0.28 $0.0031M131K— +27%
Vercel AI Gateway $0.14 $0.28 $0.0031M131K— +27%
Novita AI $0.14 $0.28 $0.0031M131K— +27%
ClinePass $0.14 $0.28 $0.0031M131K— +27%
Standard Compute $0.14 $0.28 $0.0031M50K— +27%
Io NetFP8 $0.15 $0.29 $0.0251.05M131K99.7%24h +35%
AIHubMix $0.15 $0.31 $0.0031M131K— +41%
CrossModel $0.16 $0.32 $0.0041M131K— +45%
above.dev $0.17 $0.34 $0.0031M131K— +54%
VeniceFP8 $0.17 $0.35 $0.0041M131K99.8%24h +59%
Venice AI $0.17 $0.35 $0.0041M131K— +59%

Value

Price vs. performance

4 models score higher for the same price or lesson SciCode, e.g. GLM 5.3.
13.2%31.1%49.0%66.9% $0.001$0.01$0.10$1.00$10.00 DeepSeek V4.1 Flash 1017 (DeepSeek) — 51.8% · $0.15/1M in Gemini 4 Argon (Google) — 61.8% · $2.00/1M in Step 5 Preview (StepFun) — 58.9% · $1.00/1M in Claude Haiku 5.5 (Anthropic) — 55.0% · $0.10/1M in Mistral Large 4 (Mistral) — 54.2% · $1.36/1M in GPT-6.1 Sol (OpenAI) — 55.8% · $2.00/1M in Claude Sonnet 5.5 (Anthropic) — 61.0% · $2.00/1M in GPT-6 Luna (OpenAI) — 54.6% · $0.10/1M in GPT-6 Sol (OpenAI) — 57.6% · $2.00/1M in Claude Opus 5.5 (Anthropic) — 66.9% · $4.00/1M in Grok 4.7 (xAI) — 57.8% · $2.00/1M in DeepSeek V4.1 Flash (DeepSeek) — 51.8% · $0.30/1M in GPT-6 Astra (OpenAI) — 56.5% · $10.00/1M in Qwen3.8 Max (0902) (Qwen) — 53.2% · $2.00/1M in Muse Spark 1.3 (Meta) — 59.7% · $1.25/1M in Gemini 3.8 Flash (Google) — 56.6% · $0.82/1M in Claude Fable 5.1 (Anthropic) — 63.1% · $10.00/1M in GLM 5.3 Flash (Z.ai) — 51.6% · $0.005/1M in GLM 5.3 (Z.ai) — 59.0% · $0.079/1M in Qwen3.8 27B (Qwen) — 46.6% · $0.04/1M in Gemini 3.7 Flash (Google) — 59.8% · $0.75/1M in DeepSeek V4 Pro 0813 (DeepSeek) — 51.0% · $0.66/1M in Grok 4.6 (xAI) — 56.5% · $2.00/1M in Muse Spark 1.2 (Meta) — 57.4% · $1.25/1M in DeepSeek V4 Flash 0731 (DeepSeek) — 49.9% · $0.44/1M in Claude Opus 5 (Anthropic) — 56.4% · $5.00/1M in Gemini 3.6 Flash (Google) — 53.4% · $0.75/1M in Gemini 3.5 Flash Lite (Google) — 41.3% · $0.30/1M in Kimi K3 (Moonshot AI) — 59.5% · $0.24/1M in Muse Spark 1.1 (Meta) — 58.8% · $1.25/1M in GPT-5.6 Luna (OpenAI) — 53.6% · $0.20/1M in GPT-5.6 Terra (OpenAI) — 55.0% · $2.00/1M in GPT-5.6 Sol (OpenAI) — 57.8% · $4.00/1M in Grok 4.5 (xAI) — 55.0% · $2.00/1M in Claude Sonnet 5 (Anthropic) — 54.3% · $2.00/1M in GLM 5.2 (Z.ai) — 51.2% · $0.034/1M in Kimi K2.7 Code (Moonshot AI) — 47.8% · $0.67/1M in Claude Fable 5 (Anthropic) — 61.0% · $10.00/1M in Qwen3.7 Plus (Qwen) — 46.1% · $0.32/1M in MiniMax M3 (MiniMax) — 47.1% · $0.30/1M in Step 3.7 Flash (StepFun) — 40.1% · $0.20/1M in Claude Opus 4.8 (Anthropic) — 53.5% · $5.00/1M in Qwen3.7 Max (Qwen) — 49.5% · $1.48/1M in Grok Build 0.1 (xAI) — 50.2% · $1.00/1M in Gemini 3.5 Flash (Google) — 53.9% · $1.50/1M in Gemini 3.1 Flash Lite (Google) — 43.4% · $0.25/1M in Grok 4.3 (xAI) — 48.3% · $1.25/1M in Qwen3.6 35B A3B (Qwen) — 36.6% · $0.10/1M in Qwen3.6 27B (Qwen) — 37.3% · $0.25/1M in GPT-5.5 (OpenAI) — 56.1% · $5.00/1M in DeepSeek V4 Pro 0423 (DeepSeek) — 51.0% · $0.95/1M in DeepSeek V4 Flash 0423 (DeepSeek) — 49.9% · $0.091/1M in Kimi K2.6 (Moonshot AI) — 53.5% · $0.65/1M in Claude Opus 4.7 (Anthropic) — 54.5% · $5.00/1M in GLM 5.1 (Z.ai) — 44.8% · $1.40/1M in Gemma 4 31B (Google) — 45.5% · $0.20/1M in Qwen3.6 Plus (Qwen) — 40.7% · $0.33/1M in MiniMax M2.7 (MiniMax) — 50.1% · $0.30/1M in GPT-5.4 Nano (OpenAI) — 47.2% · $0.20/1M in GPT-5.4 Mini (OpenAI) — 52.1% · $0.75/1M in Mistral Small 4 (Mistral) — 27.8% · $0.15/1M in Qwen3.5-9B (Qwen) — 29.5% · $0.08/1M in GPT-5.4 (OpenAI) — 56.6% · $2.50/1M in Gemini 3.1 Flash Lite Preview (Google) — 43.4% · $0.25/1M in Qwen3.5-35B-A3B (Qwen) — 29.3% · $0.14/1M in Qwen3.5-122B-A10B (Qwen) — 35.6% · $0.40/1M in Gemini 3.1 Pro Preview (Google) — 58.7% · $2.00/1M in Claude Sonnet 4.6 (Anthropic) — 46.8% · $3.00/1M in Qwen3 Coder Next (Qwen) — 36.2% · $0.12/1M in Kimi K2.5 (Moonshot AI) — 49.0% · $0.50/1M in GLM 4.7 (Z.ai) — 45.1% · $0.54/1M in Mistral Large 3 2512 (Mistral) — 36.6% · $0.50/1M in DeepSeek V3.2 (DeepSeek) — 38.9% · $0.28/1M in GPT-5.1 (OpenAI) — 43.3% · $1.25/1M in Claude Haiku 4.5 (Anthropic) — 42.3% · $1.00/1M in GLM 4.6 (Z.ai) — 38.4% · $0.55/1M in Claude Sonnet 4.5 (Anthropic) — 45.7% · $3.00/1M in DeepSeek V3.2 Exp (DeepSeek) — 38.9% · $0.27/1M in DeepSeek V3.1 Terminus (DeepSeek) — 38.0% · $0.27/1M in GPT-5 (OpenAI) — 42.9% · $1.25/1M in GPT-5 Mini (OpenAI) — 39.2% · $0.25/1M in gpt-oss-120b (OpenAI) — 36.0% · $0.15/1M in gpt-oss-20b (OpenAI) — 38.9% · $0.018/1M in Qwen3 235B A22B Thinking 2507 (Qwen) — 41.4% · $0.45/1M in Gemini 2.5 Pro (Google) — 46.3% · $1.25/1M in Gemini 2.5 Pro Preview 06-05 (Google) — 46.3% · $1.25/1M in R1 0528 (DeepSeek) — 38.3% · $0.50/1M in Qwen3 14B (Qwen) — 31.6% · $0.12/1M in Qwen3 32B (Qwen) — 35.4% · $0.08/1M in GPT-4.1 Mini (OpenAI) — 40.4% · $0.40/1M in GPT-4.1 Nano (OpenAI) — 25.9% · $0.10/1M in Gemma 3 12B (Google) — 16.4% · $0.05/1M in Gemma 3 27B (Google) — 23.3% · $0.08/1M in o3 Mini (OpenAI) — 42.8% · $1.10/1M in Llama 3.3 70B Instruct (Meta) — 26.0% · $0.10/1M in Mistral Large 2407 (Mistral) — 36.6% · $2.00/1M in Llama 3.1 8B Instruct (Meta) — 13.2% · $0.05/1M in Mistral Large (Mistral) — 36.6% · $2.00/1M in MiMo-V2.6-Pro (Xiaomi) — 60.9% · $0.43/1M in MiMo-V2.5-Pro (Xiaomi) — 50.2% · $0.30/1M in MiMo-V2.5 (Xiaomi) — 43.1% · $0.12/1M in MiMo-V2.6-Flash (Xiaomi) — 51.3% · $0.14/1M in MiMo-V2.6-Flash

MiMo-V2.6-Flash Other Xiaomi Other labs Value frontier · SciCode vs. input price per 1M tokens (log scale) · Drag to pan, pinch or Ctrl + scroll to zoom, double-click to zoom in.

Benchmarks

3 benchmark scores

BenchmarkScoreRankLeader
SciCodeSoftware engineering · Research-coding problems from the natural sciences 51.3% #42of 102 Claude Opus 5.566.9%
CritPtReasoning & knowledge · Open-ended, research-level physics problems 12.0% #46of 111 GPT-5.6 Sol32.3%
ProofBenchMaths · Graduate maths proofs verified in Lean 4 63.0% #19of 70 Claude Sonnet 5.5100.0%

Specs

Details

Model ID
xiaomi/mimo-v2.6-flash
Developer
Xiaomi
Release date
Sep 21, 2026 ·
Context window
1,050,000 tokens
Max output
131,072 tokens
API price
$0.14 / $0.28 per 1M input / output tokens
Providers
33
Input types
text, image, video, audio
Reasoning
Yes
Tool calling
Yes
Open weights
Yes
Free tier
No

Release date and prices from OpenRouter's catalog; providers from OpenRouter and models.dev. Buying directly from a provider can cost a little differently. Speed, latency and uptime are measured on OpenRouter only; uptime is the share of OpenRouter requests each provider served over the last day. Benchmark scores are the best result per benchmark from Epoch AI, licensed CC BY 4.0. Rank counts every model tracked here with a score.