The Known Good Updated 4 Sep 2026 Subscribe
Anthropic ·Proprietary ·Released November 2025·Tracked since 25 Jul 2026

Anthropic: Claude Opus 4.5 — quality, speed & price analysis

Compare with another model Provider benchmarks Data sources
Quality
#27 of 65
72based on 5 of 7 evaluations
Known Good Index
Speed
#170 of 338
47.8
Output tokens per second
Price
#412 of 442
$10.00
Blended per 1M tokens
In $5.00 · Out $25.00
Cache hit price
#299 of 324
$0.50
per 1M tokens (−90%)
Context
#314 of 476
200k
tokens (~300 pages)
Summary

Anthropic: Claude Opus 4.5 is above the median of the models we track for quality, but expensive for its standing, with mid-range throughput. It accepts file, image, text input, outputs text, and supports a 200k-token context window.

It scores 72 on the Known Good Index, above the tracked average of 65, from 5 of the seven component evaluations. Measured against the tracked average, its strongest result is Mock AIME 2024–25 (86 against 54) and its weakest is Humanity's Last Exam (14 against 17).

Pricing is $5.00 per 1M input tokens (above the $2.07 average) and $25.00 per 1M output (above the $9.51 average). Cached input reads at $0.50 per 1M, a 90% discount on its input price. At 48 tokens per second it sits in the lower middle of the tracked range.

Generated from tracked data on 4 Sep 2026 · how these comparisons are computed →

Technical specifications
ReasoningYes
Input modalityfile, image, text
Output modalitytext
Context window200,000 tokens
Max output64,000 tokens
WeightsProprietary
Knowledge cutoffMay 2025
Tool callingYes
Providers5 hosts · compare →
Highlights — where Anthropic: Claude Opus 4.5 sits
Jump to section
Models shown

Quality

How Anthropic: Claude Opus 4.5 compares against every tracked model

Known Good IndexCodingMathematicsReasoning
Known Good Index

Composite of GPQA Diamond, Mock AIME 2024–25, MATH Level 5, SWE-bench Verified, LiveBench, Humanity's Last Exam and Terminal-Bench, normalised 0–100. Scores are ingested from Epoch AI; we do not run these evaluations.

💡 A lightbulb marks a model its provider publishes as a reasoning model
The Known Good

Quality Breakdown

Anthropic: Claude Opus 4.5 on each evaluation feeding the index, against the tracked average

Evaluation scores

Bar = Anthropic: Claude Opus 4.5 · grey marker = average across tracked models · scores ingested from Epoch AI

GPQA Diamond86 / 64
Mock AIME 2024–2586 / 54
SWE-bench Verified77 / 71
Humanity's Last Exam14 / 17
Terminal-Bench63 / 45
The Known Good

Arena Elo

Human preference rating from blind pairwise votes

Text Arena

Elo from blind pairwise votes, ingested from Arena

1450
Elo · 95% CI ±3
#42
of 406 ranked models
70k
votes counted
1469
style-controlled (#38)

Ingested 4 Sep 2026.

The Known Good

Price & Cost

Published API pricing by token type

BlendedInput vs outputQuality per dollar
Blended Price

USD per 1M tokens at a 3:1 input:output blend. Live from OpenRouter, cross-checked against models.dev. Lower is better. Ranked against the 442 models priced above zero, which is the population the chart draws; excludes 29 published at no cost (free and promotional tiers).

The Known Good
We publish blended price rather than cost-per-task. Cost-per-task requires token counts from an evaluation suite we do not run. Blended price is computed from published rates and is fully reproducible — see the pricing methodology.

Context Window

Maximum input tokens accepted

Context windowMax output tokens
Context Window

Maximum input context from provider metadata via models.dev and OpenRouter. Higher is better.

The Known Good

Speed

Mean output throughput across hosting providers, over successful measurements from the last 48 hours

Output speedBy provider

Latency

Time to first token, mean across providers over successful measurements from the last 48 hours

Latency (TTFT)

Seconds to first streamed chunk, mean across tracked providers over successful measurements from the last 48 hours. Derived from OpenRouter endpoint telemetry. Lower is better.

The Known Good

Providers

Hosts serving Anthropic: Claude Opus 4.5, with their own price and speed

5 providers
Full provider benchmarks →
ProviderInput $/MOutput $/M BlendedSpeedTTFTContext
Amazon Bedrock · first party $5.00 $25.00 $10.00 75 1.4s 200k
Claude Platform on AWS $5.00 $25.00 $10.00 64 1.5s 200k
Anthropic · first party $5.00 $25.00 $10.00 37 1.4s 200k
Google · first party $5.00 $25.00 $10.00 4 1.1s 200k
Azure · first party $5.00 $25.00 $10.00 200k

Per-host pricing and telemetry from OpenRouter. Speed is output tokens per second; TTFT is time to first token.

The Known Good

History

How price and quality have moved since we began tracking this model

Quality & price over time

Since 25 Jul 2026

Known Good Index 72 · based on 5 of 7 evaluations
Blended price $10.00 per 1M · observed 4 Sep 2026
Output speed 48 tok/s · observed 4 Sep 2026
Time to first token 1.4s

No recorded changes for this model since tracking began.

The Known Good

Comparisons

Head-to-head pages pairing Anthropic: Claude Opus 4.5 with other tracked models

Sources for this page
Pricing & providers — OpenRouter Metadata — models.dev Benchmarks — Epoch AI (CC-BY 4.0)Elo — Arena Full attribution →