Migrate Claude Code to Codex (2026): 12 Configs, 1 Dead End

Codex 0.142 /import auto-moves most of your Claude Code config. All 12 surfaces mapped: what transfers, what breaks, the 1 dead end, and the fix.

claude-codecodex

Claude Fable 5 vs Sonnet 5 (2026): 5x Pricier, When It Pays

Fable 5 lists $10/$50, 5x Sonnet 5's $2/$10, but hits 80.3% SWE-bench Pro vs 63.2%. When the ceiling model pays, and how to route both on ofox.

claudemodel-comparison

Claude Sonnet 5 vs Opus 4.8 (2026): 60% Cheaper on Paper

Claude Sonnet 5 lists $2/$10 vs Opus 4.8 $5/$25, 60% cheaper. It trails 63.2% to 69.2% on SWE-bench Pro, and agentic cost can top Opus. Which to pick.

claudemodel-comparison

How to Choose an AI Model: 3 Questions, Not the Biggest One

Picking an AI model? Don't default to the biggest. Use 3 questions (task, volume, stakes) plus a free finder that ranks 100+ models across 15 use cases.

model-selectionai-model

Codex "command failed; retry without sandbox": 6 Fixes (2026)

Fix Codex CLI "command failed; retry without sandbox": install bubblewrap, set sandbox_mode to workspace-write and approval_policy to on-request.

codex-clitroubleshooting

Grok Build Pricing: $30/mo Subscription vs $1/M API (2026)

Grok Build costs $30/mo on SuperGrok, not the $300 Heavy tier. Or meter grok-build-0.1 at $1.00/$2.00 per M with 256K context. Break-even math for both.

grokpricing

Doubao Seed 2.1 API (2026): Pro & Turbo, No Volcano Signup

Call Doubao Seed 2.1 Pro ($0.884/$4.42 per M) and Turbo (half: $0.442/$2.212) from one endpoint. 256K context, one key, no separate Volcano signup.

doubaobytedance

Kimi K2.7 Code: Does a 30% Token Cut Lower Your Bill? (2026)

Kimi K2.7 Code costs the same per token as K2.6 ($0.95/$4.00). Its 30% thinking-token cut trims ~13% off a reasoning-heavy bill, under 1% input-heavy.

kimimodel-comparison

claude-code-sdk Import Errors After the June 2026 Rename: Why and the Fix

ModuleNotFoundError: claude_code_sdk or no export from @anthropic-ai/claude-code? The SDK moved to claude-agent-sdk. Before/after fix for TS + Python.

claude-codeclaude

Rate Limit Reached in Claude Code: 429 Causes and 6 Fixes (2026)

Claude Code 429 rate limit? Start tier gives Opus 5 and Sonnet 5 2M ITPM / 1,000 RPM. Read retry-after, add jitter, cut ITPM with caching. 6 fixes.

claude-codetroubleshooting