Claude Sonnet 4.6

LLM Provider / Model · Day-to-day coding, fast agentic loops, balanced cost/quality

At a glance

Input price	$3
Output price	$15
Cache price	$0.30
Price tier	Mid
Context window	1M+
Max output	128K
Context tier	500K+
Speed tier	Standard
Latency	medium
Knowledge cutoff	Aug 2025
Modality	Multimodal (vision)
Model ID	claude-sonnet-4-6
Provider	Anthropic
HumanEval	92%
MMLU	86%
SWE-Bench	64%
Benchmark	SWE-bench: high
Released	Feb 2026
Hosting	Closed/API
Capabilities	Vision, Tool use, Adaptive thinking, Effort control, Streaming, Structured output, Prompt caching

Vision, Tool use, Adaptive thinking, Effort control, Streaming, Structured output, Prompt caching

Day-to-day coding, fast agentic loops, balanced cost/quality

OpenAI Codex (VS Code) is tied to OpenAI's hosted GPT-5 and Codex models — Claude Sonnet 4.6 is not selectable inside this integration.
Gemini CLI is locked to Google Gemini models — your LLM is Claude Sonnet 4.6.
Devin uses Cognition's proprietary model internally — your selected Claude Sonnet 4.6 will be ignored.
OpenAI Codex (Cloud) runs GPT-5.1 Codex internally — your selected Claude Sonnet 4.6 will be ignored.
Jules runs Gemini models internally — your selected Claude Sonnet 4.6 will be ignored.
Lovable uses a fixed internal model — your selected Claude Sonnet 4.6 will be ignored.
Replit Agent 3 uses its own model selection internally — your selected Claude Sonnet 4.6 will be ignored.

Build a full stack around Claude Sonnet 4.6 — Flowpicker shows compatibility warnings before you commit.