Claude Opus 5.5 (Max, Default Fallback)Ready
claude-opus-5-5
Serverless APILLMReasoningVisionPrompt cachingClosed
The frontier reasoning flagship of the Claude 5.5 family, built for long-horizon agentic work and large-document analysis. It ranks #1 of the top 20 frontier models on the Artificial Analysis Intelligence Index with a score of 57.6. Released September 22, 2026.
1M
Context
—
Parameters
#1
Intelligence rank · 57.6
Closed
Weights
View full spec
ReleasedSep 22, 2026
Knowledge cutoff—
Size classlarge
Input modalitiestext, image
Output modalitiestext
Median output speed97 tok/s
Median time to first token728.3s
Usage guide
1. Choose how you'd like to use Claude Opus 5.5 (Max, Default Fallback)
☁️ 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": "claude-opus-5-5",
"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 | $6.25 | 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
61.4
MMMU-Pro
87.7
SciCode
66.9
Terminal-Bench 4.0
59.6
Long Context Reasoning
84.7
Frontier Code
52.2
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, 97 output tokens/s median serving speed and 728.3s to first token.