Models/Muse Wonder Full (Max)

Muse Wonder Full (Max)Ready

muse-wonder-full

Serverless APILLMReasoningVisionClosed

The largest Muse Wonder release — open-weight multimodal reasoning at full parameter count. It ranks #3 of the top 20 frontier models on the Artificial Analysis Intelligence Index with a score of 55.8. Released October 12, 2026.

Context

—

Parameters

Intelligence rank · 55.8

Closed

Weights

View full spec

ReleasedOct 12, 2026

Knowledge cutoff—

Size class—

Input modalitiestext, image, speech, video

Output modalitiestext

Usage guide

1. Choose how you'd like to use Muse Wonder Full (Max)

☁️ 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-staging.coality.io/v1/chat/completions \
  -H "Authorization: Bearer $TOKEN_HUB_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "muse-wonder-full",
    "messages": [{"role": "user", "content": "Explain vector databases in one paragraph"}]
  }'

Pricing

Bucket	Price	Notes
Input tokens	—	per 1M tokens
Output tokens	—	per 1M tokens
Cache read	—	per 1M tokens
Cache write	—	per 1M tokens

Billed per token with micro-dollar precision · effective Oct 26, 2026 · default key limits 600 req/min · 200K tokens/min

Benchmarks

Humanity's Last Exam

53.6

SciCode

62.6

Terminal-Bench 4.0

57.1

Long Context Reasoning

83.7

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

About this model

Closed model, with a 1M context window, native image input and visible reasoning traces.