news

Introducing Claude Sonnet 5

Anthropic launched Claude Sonnet 5 on June 30, priced at $2/$10 per million input/output tokens through Aug 31, then $3/$15. It pitches the model as approaching Opus 4.8 quality at a lower price.

Published 2026-07-01Source: Anthropic
Anthropic source artwork

Why it matters

For teams routing work across model tiers, a Sonnet that lands near Opus 4.8 resets the default. Reaching for the flagship on every call gets harder to justify once the mid-tier handles most agentic work at Sonnet prices.

Tokenmaxxing read

Watch the fine print: Anthropic's updated tokenizer maps the same text to roughly 1.0-1.35x more tokens than before. A lower per-token sticker can be partly eaten by higher token counts, so re-measure spend on your own prompts before assuming Sonnet 5 is cheaper per task.

Source takeaway

Anthropic pitches Sonnet 5 as its most autonomous Sonnet to date, able to plan and drive tools such as browsers and terminals by itself, with the introductory rate held through Aug 31 before standard $3/$15 pricing takes over.

Topic links

tokenmaxxingcoding-agentstopicagentstopicscoreboards
Related projects

Tools that match this angle

#4In spirit
Agents

LangGraph

langchain-ai/langgraph

A framework for building resilient stateful agents with explicit graphs, persistence, human-in-the-loop flows, and controllable execution.

39.9K6.7KMIT
agentsstateworkflows
#5Direct
Evaluation

promptfoo

promptfoo/promptfoo

A CLI and CI workflow for testing prompts, agents, and RAG systems across models, with evals and red-team style checks.

24.3K2.2KMIT
prompt-evalscirag
#6In spirit
Evaluation

DSPy

stanfordnlp/dspy

A framework for programming and optimizing language-model pipelines rather than hand-tuning one prompt at a time.

37.3K3.2KMIT
optimizationprogrammingevals
Related feed

More source-linked context

CNX Software - Embedded Systems News source artwork
newsCS
news

Token Monitor - An ESP32-S3 desktop display that tracks AI coding assistant usage (Crowdfunding) - CNX Software

Fractal Manifold is crowdfunding Token Monitor, a EUR 99 ESP32-S3 desk display with a 4-inch touchscreen that shows quota use, session limits, reset timers and estimated token costs for Claude Code, Codex CLI and Antigravity CLI.

tokenmaxxingcoding-agentsagents
Read note
theclimatebrink.com source artwork
newsT
news

The real energy use of agentic AI

Climate scientist Zeke Hausfather metered his own Claude Code habit: 1,138 typed prompts fanned out to more than 14,000 model calls and 3.2 billion tokens in eight weeks, drawing roughly 170 kWh of data-center electricity.

tokenmaxxingcoding-agentsagents
Read note
HackerNoon source artwork
newsH
newsmedium review

Claude Code Was Burning Tokens Until I Put a Gate in Front of It | HackerNoon

Prateek Kapoor wrapped Claude Code in a PreToolUse hook that rejects unbounded greps and whole-file reads, hands the agent a corrected command, and reports 75% to 80% lower token use on heavy editing tasks.

tokenmaxxingcoding-agentsagents
Read note