Skip to content
Tier A — Frontier
Runs in:GlobalMade in:United States
Anthropic

Claude Opus 5.5

Tier A — Frontier · 1M tokens

Tokonomix Editorial Team·Reviewed by Mes Kalkan··
Section 01

Speed analysis

Latency measured across all benchmark runs. P50 (median) and P95 (95th percentile) give a realistic picture of response speed under normal and peak load.

P50 latency (median)P95 latency119 runs
578132320682813355810-2311-22ms
Section 02

Pricing

What you pay per million tokens when you use this model on Tokonomix, plus an estimate for a typical conversation.

💰
API rates — Claude Opus 5.5
$5.20 per 1M input tokens
$26.00 per 1M output tokens
≈ $0.0083 per typical conversation (800 tokens)
Input vs output price (per 1M tokens)
per 1M input tokens$5.20
per 1M output tokens$26.00
Section 03

Tokens per second

Throughput in tokens per second, derived from measured P50 latency. Higher is better; fluctuations track provider-side load.

Throughput (tokens / s)171 / avg 203
34388

Estimated from P50 latency × 200 output tokens — the absolute number depends on this assumption; the trend is what matters.

Section 04

Capabilities

toolssource: seed-newest-generation-2026-09-30visionjson modepdf inputreasoningjson schemaprompt cachingmax output tokens: 128000
Section 05

Availability

Availability

How often this model answers when we call it — measured across real API requests and live tests over the last 30 days. This is separate from quality: these numbers only tell you whether the model responds, not how good the answer is.

Last 7 days

100.0%

n=5

Last 30 days

100.0%

n=194

Median response time

9,651ms

n=194

Based on 551 measurements over the last 30 days.

Technical details

Only live API calls and live-test requests count — internal probes and benchmark runs are excluded.

Calls with a custom API key (BYOK) are excluded: those failures are key-specific, not a sign of model downtime.

Failed calls are NOT included in quality scores — quality is measured on successful responses only. Availability and quality are independent signals.

Median response time (p50) across successful calls with a recorded duration. Outliers (very slow or very fast calls) pull the median less than the average.

Total calls (30d)

194

OK responses (30d)

194

Total calls (7d)

5

OK responses (7d)

5

Section 06

Tokonomix benchmark verdicts

● 2026-11-22

Claude Opus 5.5 still lacks benchmark data despite expanded capabilities

Claude Opus 5.5 continues to show no performance data across standard benchmarks, despite now offering a significantly expanded feature set. The model has added seven major capabilities since the last evaluation period: tools, vision, JSON mode, PDF input, reasoning, JSON schema, and prompt caching. These additions suggest Anthropic is positioning this model as a comprehensive multimodal solution with advanced structured output and optimization features. However, the complete absence of benchmark scores across coding, mathematics, reasoning, and general knowledge tasks makes it impossible to assess actual performance or compare it meaningfully to competing models. The gap between capability expansion and performance transparency is notable. Users considering Claude Opus 5.5 should be aware they are evaluating based on feature checklist rather than measured performance. The lack of benchmark participation may indicate the model is in early release, undergoing significant development, or that Anthropic is prioritizing different evaluation methodologies. Until performance data becomes available, adoption decisions must rely entirely on direct testing and qualitative assessment rather than quantitative comparison.

Quality

—

Latency p50

—

Test runs

0

✓ Added seven major capabilities✓ Vision and PDF support enabled✗ No benchmark data available✗ Performance remains unmeasured
Last automated test
Nov 22, 2026 · 14:02 UTC · Speed benchmark
P50 latency
1173 ms
P95 latency
1221 ms
Errors
0 / 6 runs
Last reviewed by Tokonomix Team·November 22, 2026