Skip to main content

MiMo V2.6 Flash

MiMo-V2.6-Flash is an open-source foundation model developed by Xiaomi.

Model card on Hugging Face
Input / output price
$0.126 / $0.252 per 1M
Context
1.1M tokens
Released
Sep 22, 2026
Agent setup

Paste into Claude Code, Cursor, or Codex

Help me set up the Respan gateway: fetch and follow https://www.respan.ai/docs/agent-setup.md. Use model "mimo-v2.6-flash".

Read docs

Providers

8 providers, cheapest first, OpenRouter last, priced per 1M tokens after gateway discounts.

ProviderInputOutput
Pareto Inferenceparetoinference/mimo-v2.6-flash
$0.126/M$0.252/M
Concentrateconcentrate/mimo-v2.6-flash
$0.14/M$0.28/M
DeepInfradeepinfra/mimo-v2.6-flash
$0.14/M$0.28/M
EmpirioLabsempiriolabs/mimo-v2.6-flash
$0.14/M$0.28/M
Novitanovita/mimo-v2.6-flash
$0.14/M$0.28/M

Is a provider down? OpenRouter status

Pricing

Averaged across 8 providers, in USD per 1M tokens after gateway discounts.

Average input
$0.15 per 1M
Average output
$0.30 per 1M
Average cache read
$0.03 per 1M

Cost by volume

Total cost from 0 to 1T tokens on the cheapest and most expensive provider.

Highest$0.20/MMakoraLowest$0.126/MPareto Inference

Throughput and latency

30-day averages from requests through the Respan gateway. Under each figure, every model on the gateway by its average, this one in blue.

Output speed

Higher is better

65tokens/sacross providers

Faster than 71% of the other 596 models on the gateway

Time to first token

Lower is better

1.6sacross providers

Faster than 53% of the other 153 models on the gateway

Response latency

Lower is better

7.9sacross providers

Faster than 22% of the other 776 models on the gateway

Benchmarks

The Respan Index plus 14 published scores from 3 sources, each linked to where it was published.

51.8/ 100

Respan Index#41 of 176

176 ranked models. The shaded band is this model's 95% interval, 37.0 to 70.3. Gemini 3.7 Flash and GPT-5.4 Pro fall inside it, so the gap is within the margin of error.
MiMo V2.6 Flash by category: Coding 40.2, Agents 61.4, Reasoning 49.2, Knowledge & language 55.2 (estimated), Human preference 56.9
  1. 41MiMo-V2.6-Flash51.8
  2. 40Gemini 3.7 Flash52.0
  3. 42GPT-5.4 Pro51.0

Published scores

BenchmarkScore
Terminal-Bench 2.1huggingface.co87.6%
DeepSWE v1.1huggingface.co67.9%
Terminal-Bench 4.0huggingface.co28.8%
Terminal-Bench 4.0Vals AI24.2%

Compare MiMo V2.6 Flash: MiMo-V2.6-Flash vs MiMo-V2-Flash, MiMo-V2.6-Flash vs Muse Spark 1.3, MiMo-V2.6-Flash vs MiMo-V2.6-Pro, MiMo-V2.6-Flash vs MiMo-V2.5-Pro

Apps

Use MiMo V2.6 Flash in the tools you already run. Each guide points the app at the Respan gateway.

Setup guides for more apps are in the integration docs.

MiMo V2.6 Flash FAQ

Short answers, built from the data on this page.

MiMo V2.6 Flash is a model from Xiaomi, released on Sep 22, 2026. MiMo-V2.6-Flash is an open-source foundation model developed by Xiaomi.

On the Respan gateway, MiMo V2.6 Flash costs from $0.126 per 1M input tokens and $0.252 per 1M output tokens on Pareto Inference, after gateway discounts. Averaged across its 8 providers, it costs $0.15 per 1M input tokens and $0.30 per 1M output tokens.

MiMo V2.6 Flash is available through 8 providers: Pareto Inference, Concentrate, DeepInfra, EmpirioLabs, Novita, IO.net, and 2 more.

MiMo V2.6 Flash accepts up to 1.1M tokens of context on its largest provider route.

Point any OpenAI-compatible SDK at https://gateway.respan.ai/v1 with your Respan API key and set the model to "mimo-v2.6-flash". To set it up with a coding agent, copy the agent setup prompt at the top of this page.

MiMo V2.6 Flash scores 51.8 out of 100 on the Respan Index v1.1, ranking #41 of 176 models. By category: Coding 40.2, Agents 61.4, Reasoning 49.2, Knowledge & language 55.2 (estimated), and Human preference 56.9. The Respan Index combines independent and lab-reported benchmark results into one score, using benchmark data collected by Respan.

MiMo V2.6 Flash has 14 published benchmark scores, including Terminal-Bench 2.1 87.6%, OSWorld-Verified 80.8%, and LMArena WebDev 1638. Each score links to where it was published; the data is collected by Respan.

Certified where it counts.

Built to meet the security and privacy standards that enterprise and healthcare teams require.

ISO 27001

The internationally recognized standard for information security management.

SOC 2

Secure, compliant management of your data across all of our systems.

GDPR

Operated under GDPR, the world's strictest standard for data privacy.

HIPAA

HIPAA compliant, with a BAA available for healthcare teams.

Works with your entire stack

Use Respan with your favorite frameworks and tools.

AnthropicAI21 LabsxAIVercel AI SDK
LangChainOpenRouterAssemblyAICursor
LiteLLMGroqBasetenMem0
CohereCogneeLlamaIndexFireworks
DeepSeekLinkupHaystackTogether AI
PerplexityInference.netPostHogRubyLLM
SlackMastraAzure OpenAIMistral
AWS BedrockMoonshotHyperspellBAML
ModaInstructorGoogle GeminiParasail
ReductoZapierAgnoNebius
OpenAINovita AIReplicateSuperagent

Built for AI agents.
Break less.
Ship more.