Claude Opus 4.7

LLM Provider / Model · Complex refactors, agentic coding, hard debugging, deep reasoning

At a glance

Input price	$15
Output price	$75
Cache price	$1.50
Price tier	Premium
Context window	200K
Max output	32K
Context tier	128K-500K
Speed tier	Slow/Reasoning
Latency	medium
Knowledge cutoff	Jan 2026
Modality	Multimodal (vision)
Model ID	claude-opus-4-7
Provider	Anthropic
HumanEval	94%
MMLU	88%
SWE-Bench	72%
Benchmark	SWE-bench: top
Released	Nov 2025
Hosting	Closed/API
Capabilities	Vision, Tool use, Extended thinking, Streaming, Structured output, Prompt caching

Vision, Tool use, Extended thinking, Streaming, Structured output, Prompt caching

Complex refactors, agentic coding, hard debugging, deep reasoning

OpenAI Codex (VS Code) is tied to OpenAI's GPT-5.1 Codex family — Claude Opus 4.7 is not selectable inside this integration.
Gemini CLI is locked to Google Gemini models — your LLM is Claude Opus 4.7.
Devin uses Cognition's proprietary model internally — your selected Claude Opus 4.7 will be ignored.
OpenAI Codex (Cloud) runs GPT-5.1 Codex internally — your selected Claude Opus 4.7 will be ignored.
Jules runs Gemini models internally — your selected Claude Opus 4.7 will be ignored.
Lovable uses a fixed internal model — your selected Claude Opus 4.7 will be ignored.
Replit Agent 3 uses its own model selection internally — your selected Claude Opus 4.7 will be ignored.

Build a full stack around Claude Opus 4.7 — Flowpicker shows compatibility warnings before you commit.