OpenAI Codex CLI shipped rust-v0.159.1 on 2026-09-29 (npm @openai/[email protected]): GPT-6.1 Sol is now the default in the bundled catalog and Amazon Bedrock Mantle/Runtime catalogs (API id gpt-6.1-sol). Official pricing $2/$10 per 1M tokens (cached input $0.10), 1.05M context, 128k max output. ~3 commits / 29 files vs v0.159.0.
Key Takeaways
- ✓Release rust-v0.159.1; ~3 commits / 29 files vs v0.159.0
- ✓Default model is GPT-6.1 Sol in bundled + Bedrock Mantle/Runtime catalogs (#49323, #49342)
- ✓Pricing: $2/$10 per 1M, cached input $0.10; 1.05M context / 128k max out
- ✓Supports Responses tools, computer use, MCP, Skills; reasoning.effort low→max
- ✓Upgrade:
npm i -g @openai/[email protected]; docs at developers.openai.com/codex
Key Decision Metrics at a Glance
Turn your technical choice into a development budget
Compare 40 dev plans & simulate token costs vs $20/mo subscriptions
Project Links & Resources
Direct AccessIn-Depth Technical Analysis
Background
Codex’s default model drives cost and latency. v0.159.1 wires GPT-6.1 Sol into the bundled catalog and Amazon Bedrock Mantle/Runtime catalogs so CLI and Bedrock paths stay aligned.
What shipped
rust-v0.159.1 (#49323, #49342). API id gpt-6.1-sol. Diff vs v0.159.0: ~3 commits / 29 files. npm @openai/[email protected].
Benchmarks
No SWE-bench in the release notes. Official specs: $2/$10 per 1M, cached input $0.10, 1.05M context, 128k max out; computer use / MCP / Skills supported. Validate Astra vs Sol on your tasks.
Get started
npm i -g @openai/[email protected]; override with --model gpt-6.1-sol if config pins an older model. Docs: developers.openai.com/codex.
Benchmark side-by-side against alternatives, or calculate monthly token cost vs subscription break-even.
Discussion & Comments
0Sign in to join the discussion
Connect with AI developers to exchange benchmark insights.