Muse Wonder (Max)Ready
muse-wonder
Serverless APILLMReasoningVisionPrompt cachingClosed
The standard Muse Wonder build — open-weight multimodal reasoning balancing cost and capability. It ranks #7 of the top 20 frontier models on the Artificial Analysis Intelligence Index with a score of 52.4. Released October 12, 2026.
1.0M
Context
—
Parameters
#7
Intelligence rank · 52.4
Closed
Weights
View full spec
ReleasedOct 12, 2026
Knowledge cutoff—
Size classlarge
Input modalitiestext, image, speech, video
Output modalitiestext
Median output speed181 tok/s
Median time to first token40.6s
Usage guide
1. Choose how you'd like to use Muse Wonder (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",
"messages": [{"role": "user", "content": "Explain vector databases in one paragraph"}]
}'Pricing
| Bucket | Price | Notes |
|---|---|---|
| Input tokens | $5.00 | per 1M tokens |
| Output tokens | $25.00 | per 1M tokens |
| Cache read | $0.2500 | cached input · 95% off |
| 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
50.1
SciCode
60.3
Terminal-Bench 4.0
52.0
Long Context Reasoning
80.7
Scores from the Artificial Analysis evaluation suite (0–100 scale).
About this model
Closed model, with a 1M context window, native image input, visible reasoning traces, prompt caching at a 95% discount on cached input, 181 output tokens/s median serving speed and 40.6s to first token.