Claude Sonnet 5

LLM Provider / Model · Day-to-day coding and agentic loops where speed and cost both matter

At a glance

Input price	$2
Output price	$10
Cache price	$0.20
Price tier	Mid
Context window	1M+
Max output	128K
Context tier	500K+
Speed tier	Fast
Latency	fast
Knowledge cutoff	Jan 2026
Modality	Multimodal (vision)
Model ID	claude-sonnet-5
Provider	Anthropic
Benchmark	Near-Opus quality on coding and agentic work at Sonnet cost
Released	Jun 2026
Hosting	Closed/API
Capabilities	Vision, Tool use, Adaptive thinking, Effort control (low-max), Streaming, Structured output, Prompt caching, Task budgets

Vision, Tool use, Adaptive thinking, Effort control (low-max), Streaming, Structured output, Prompt caching, Task budgets

Day-to-day coding and agentic loops where speed and cost both matter

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

Build a full stack around Claude Sonnet 5 — Flowpicker shows compatibility warnings before you commit.