Claude 4.7 Opus Thinking

Claude Opus 4.7 with thinking enabled (default budget: 16k tokens).

Reasoning
Vision
Native PDF input
Tool Calling
Structured Output

Added Apr 16, 2026

Pricing

Auto routing · per 1M tokens

Input: $5.00
Output: $25.00
Cache read: $0.50

Compare provider prices

Specifications

Context window: 1M
Max output: 128K
Avg output (7d): 1.7K tokens; Longer than 88% of models

Benchmarks

Artificial Analysis

Vectara

Sourced from Artificial Analysis.

Intelligence Index

40.7

Better than 93% of models compared

Coding Index

73.6

Better than 88% of models compared

Agentic Index

38.6

Better than 76% of models compared

Agentic work

T²-Bench Telecom (legacy)

Legacy fallback · Conversational AI agents in dual-control scenarios

88.6%

Better than 83% of models compared

AA-Briefcase

Agentic knowledge work (Elo)

1254 Elo

Better than 65% of models compared

GDPval-AA v2

Economically valuable tasks (Elo)

1356 Elo

Better than 71% of models compared

Document reasoning

AA-LCR v1.1

Long context reasoning with updated grading

78.7%

Better than 81% of models compared

Reasoning

HLE

Humanity's Last Exam

42.3%

Better than 90% of models compared

IFBench

Instruction-following benchmark

58.6%

Better than 70% of models compared

CritPt

Research-level physics reasoning

12.0%

Coding

Terminal-Bench Hard (legacy)

Legacy fallback · Agentic coding and terminal use

51.5%

Better than 95% of models compared

Knowledge

AA-Omniscience Accuracy

Proportion of correctly answered questions

48.9%

AA-Omniscience Hallucination Rate

Rate of incorrect answers among non-correct responses

42.3%

Legacy benchmarks

GPQA Diamond (legacy)

Graduate-level scientific reasoning

91.4%

Better than 92% of models compared

AA-LCR (unversioned / legacy)

Long context reasoning evaluation

78.7%

Better than 81% of models compared

GDPval-AA (unversioned / legacy)

Economically valuable tasks

42.6%

Last updated Oct 14, 2026