Claude Opus 4.5
by Anthropic
Prices last updated November 17, 2026
Previous Opus generation with strong reasoning and coding.
Price Comparison
Compare pricing across 8 providers serving Claude Opus 4.5
| Provider | Input $/1M | Output $/1M | Context | Speed | TTFT | Status |
|---|---|---|---|---|---|---|
KIE AI | $1.43 ● | $7.15 | — | — | — | Live |
Muapi | $3.00 | $15.00 | — | — | — | Live |
PoYo | $4.00 | $20.00 | — | — | — | Live |
OpenRouter | $5.00 | $25.00 | — | — | — | Live |
Anthropic | $5.00 | $25.00 | — | — | — | Live |
Venice AI | $5.00 | $25.00 | 198k | — | — | Live |
WaveSpeed AI | $5.00 | $25.00 | 200k | — | — | Live |
Infron | $5.00 | $25.00 | 200k | — | — | Live |
Benchmarks
Independent results for Claude Opus 4.5, as each source publishes them. Where a source tested several versions (effort levels, thinking modes, dated snapshots), the best one is shown and named under "As tested". Scores from different sources use different scales and aren't comparable with each other.
| Benchmark | Score | Rank | As tested |
|---|---|---|---|
| Overall | |||
Epoch Capabilities IndexEpoch AI One score combining a model's results across many benchmarks, on a common scale. | 151.9±1.5 | #63 of 258 | Claude Opus 4.5 |
| Reasoning | |||
GPQA DiamondEpoch AI Graduate-level multiple-choice questions in biology, physics and chemistry, written to be hard to look up. | 86.0%±4.1 | #80 of 232 | claude-opus-4-5-20251101_32K Nov 2025 |
| Math | |||
FrontierMath Tiers 1-3Epoch AI Unpublished research-level maths problems with automatically checkable answers. | 34.4%±5.5 | #71 of 95 | claude-opus-4-5-20251101_32K Jun 2026 |
FrontierMath Tier 4Epoch AI FrontierMath's hardest tier: problems that take specialist mathematicians days. | 4.9%±5.8 | #67 of 77 | claude-opus-4-5-20251101_32K Jun 2026 |
OTIS Mock AIMEEpoch AI Competition maths problems from the OTIS mock AIME exams (2024-2025). | 86.1%±8.4 | #88 of 215 | claude-opus-4-5-20251101_32K Nov 2025 |
| Coding | |||
SWE-bench VerifiedEpoch AI Real GitHub issues from Python projects; the model must write a patch that passes the project's tests. Epoch's own runs. | 76.7%±3.8 | #9 of 32 | claude-opus-4-5-20251101 Feb 2026 |
Text Arena: CodingLMArena Text Arena votes on coding prompts only. | 1,530±7 7,742 votes | #24 of 421 | Claude Opus 4.5 (High, 32K, 20251101) Nov 2026 |
Code Arena (WebDev)LMArena Human votes on web apps the models build from a prompt. | 1,494±8 10,961 votes | #76 of 161 | Claude Opus 4.5 (High, 32K, 20251101) Nov 2026 |
| Knowledge | |||
SimpleQA VerifiedEpoch AI Short factual questions answered without search, measuring what the model knows and whether it makes things up. | 45.7%±3.1 | #46 of 97 | claude-opus-4-5-20251101_32K Aug 2026 |
| Chat | |||
Text ArenaLMArena Human votes on chat answers across all kinds of prompts (style-controlled). | 1,473±4 37,227 votes | #48 of 426 | Claude Opus 4.5 (High, 32K, 20251101) Nov 2026 |
Epoch AI: Epoch runs each benchmark itself on the models it evaluates, with the same harness for every model. The Epoch Capabilities Index combines many benchmarks into one score. Data: Epoch AI, 'Capabilities & benchmarking', epoch.ai/benchmarks (CC BY 4.0).
LMArena: People compare two anonymous models side by side and vote for the better answer; ratings come from those votes (Bradley-Terry, style-controlled for text and vision). Data: LMArena (arena.ai) leaderboard dataset (CC BY 4.0).
Rank is among all models the source ranks, including ones we don't list.
Claude Opus 4.5 guides
How AI API Prices Changed, 2023–2026: Token Prices in Charts
Charts of official AI API token prices by generation for GPT, Claude and Gemini, 2023–2026: which got cheaper, which got pricier, and what changes next.
Nov 2026Claude API Pricing 2026: Every Model, Batch and Caching Discounts, and the Cheapest Provider
Claude API cost per 1M tokens for Opus 5.5, Sonnet 5.5, Haiku 5.5 and Fable 5.2, plus 50% Batch and prompt caching discounts and the cheapest provider.