Gemini 4 Carbon launches with $2/$10 intro pricing; Pydantic AI ships day-1 support
samuelcolvin · x · 2026-11-11
Google has released Gemini 4 Carbon, its strongest reasoning model, and Pydantic AI added day-1 support in v2.67.0.
- Pricing: $2/$10 per 1M input/output tokens until Nov 30, then $4/$20 — same tier as Argon.
- Gotcha: Carbon has no minimal thinking level and the Gemini API returns a 400 on it, so setting thinking: False in Pydantic AI actually sends thinkingLevel LOW instead; supported levels are low, medium (default), and high.
- Google recommends sticking with Gemini 4 Argon where speed matters.
- The release also brings SubAgents under durable execution, nested RepoContext instruction files, and guardrail verdicts recorded as durable operations.
More from coding & agent
- Plurai launches free agent simulation testing inside Claude Code and Cursor — PrajwalTomar_ · 2026-11-11
- AI-built game nerfed 40% after Claude playtest bot beat it in 6 minutes — builderjaydub · 2026-11-11
- Anthropic launches Claude Tag for Slack, claims 65% of its product code is AI-written — nikola_mr64990 · 2026-11-11
- The key to expert-driven evals: maximize information gain per unit of expert attention — danshipper · 2026-11-11
- Aqua launches Notetaker: meeting notes piped to AI agents via MCP — Scobleizer · 2026-11-11
- KAIST's WikiTrace: evidence-linked memory fixes agent "memory-induced degradation" — dair_ai · 2026-11-11