Models/MiMo-V2.6-Pro

MiMo-V2.6-ProReady

mimo-v2-6-pro

Serverless APILLMReasoningVisionPrompt cachingOpen weights

Strong reasoning packed into an efficient, cost-effective package. It ranks #10 of the top 20 frontier models on the Artificial Analysis Intelligence Index with a score of 46.3. Released September 21, 2026.

Context

1.0T

Parameters

#10

Intelligence rank · 46.3

Open

Weights · MIT

View full spec

ReleasedSep 21, 2026

Knowledge cutoff—

Size classlarge

Input modalitiestext, image, speech, video

Output modalitiestext

Median output speed48 tok/s

Median time to first token4.3s

LicenseMIT

Usage guide

1. Choose how you'd like to use MiMo-V2.6-Pro

☁️ Serverless

Use with pay-per-token pricing. Zero setup, no cold starts, automatic failover between upstream routes.

Usage tiers · Standard • Priority

Try it — sign in

curl https://tokenhub.coality.io/v1/chat/completions \
  -H "Authorization: Bearer $TOKEN_HUB_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "mimo-v2-6-pro",
    "messages": [{"role": "user", "content": "Explain vector databases in one paragraph"}]
  }'

Pricing

Bucket	Price	Notes
Input tokens	$0.5437	per 1M tokens
Output tokens	$1.09	per 1M tokens
Cache read	$0.0045	cached input · 99% off
Cache write	—	per 1M tokens

Billed per token with micro-dollar precision · effective Oct 27, 2026 · default key limits 600 req/min · 200K tokens/min

Benchmarks

Humanity's Last Exam

49.4

SciCode

60.9

Terminal-Bench 4.0

34.8

Long Context Reasoning

86.3

Frontier Code

45.4

Scores from the Artificial Analysis evaluation suite (0–100 scale).

About this model

1.0T-parameter open-weight model, with a 1M context window, native image input, visible reasoning traces, prompt caching at a 99% discount on cached input, 48 output tokens/s median serving speed and 4.3s to first token.