RSS
Tips

Gemini, Codex, GPT and other AI coding models: our coverage

Our coverage of the AI coding models and tools beyond Claude: Google's Gemini 4 family, OpenAI's Codex and GPT-6.2, GitHub Copilot, Qwen, DeepSeek and open models, plus our side-by-side comparisons with Claude.

Two roads between trees illustrating Gemini, Codex, GPT and other AI coding models
Photo by Jens Lelie on Unsplash

claudefox is mostly about Claude, but most readers use more than one model. This page lists what we have written about the alternatives: Google's Gemini models and tools, OpenAI's Codex and GPT models, GitHub Copilot and other labs' models, both closed and open-weight.

Start with the comparisons if you are deciding what to use. Prices and benchmarks change quickly, so check the date on each post before relying on a figure.

Comparisons with Claude

Side-by-side posts on price and benchmarks. Claude Code vs Codex is our evergreen comparison of the two coding agents; the rest compare models.

PostWhat it coversDate
Claude Code vs GitHub Copilot (2026): pricing, Claude models, which to useClaude Code vs GitHub Copilot: plans, which Claude models each Copilot plan offers, credits and agent features.Nov 20, 2026
Claude Code vs OpenCode (2026): cost, Claude access, which to useClaude Code vs OpenCode: licence, how OpenCode can use Claude, costs, permissions and features.Nov 20, 2026
Claude Code vs Cursor (2026): pricing, models, which to useClaude Code vs Cursor judged on the same criteria: plans, models, agent features, limits, privacy and switching.Nov 20, 2026
Claude Code vs Gemini CLI (2026): access, pricing, featuresClaude Code vs Gemini CLI and Antigravity CLI: who can still use which, pricing, limits and migration.Nov 20, 2026
Claude Code vs Codex CLI (2026): which coding agent to useClaude Code vs Codex CLI: pricing, usage limits, sandboxing, extensions and install, side by side.Nov 20, 2026
Gemini 4 Neon vs Claude Opus 5.5 and Sonnet 5.5: price, per-task cost and when to switchGemini 4 Neon at $3/$15 per million tokens, priced between Claude Sonnet 5.5 and Opus 5.5.Nov 19, 2026
Tencent Hy4 flash: price, coding benchmarks and how it compares to Claude Haiku 5.5Tencent's open-weight Hy4 flash at $0.070/$0.281 per million tokens, tested against Claude Haiku 5.5.Nov 18, 2026
GPT-6.2 benchmarks vs Claude Fable 5.2: what independent evaluators foundIndependent tests of GPT-6.2 Astra and Sol: Fable 5.2 leads the broad indexes.Nov 18, 2026
Gemini 4 Hydrogen vs Claude Sonnet 5.5 for coding: price, speed and benchmarksGemini 4 Hydrogen ($1.50/$7.50) vs Claude Sonnet 5.5 ($2/$10), and where each wins on coding tests.Nov 18, 2026
Gemini 4 Carbon vs Claude Opus 5.5 and Fable 5.2: benchmarks and pricing comparedGemini 4 Carbon vs Claude Opus 5.5 and Fable 5.2: published prices and benchmark tables, with sources.Nov 18, 2026
FrontierHarness Eval v1.1: with open models, Claude Code was among the costliest harnesses per solved task22 configurations of 18 coding-agent harnesses on five open models: the best-value harness changed per model.Nov 17, 2026

Google Gemini

Gemini 4 model launches and prices, the Gemini API's new endpoints, and Google's agent tools, including how to call Gemini from Claude Code.

PostWhat it coversDate
Gemini API Tool Retrieval: how tool_search and defer_loading work, what they cost, and how they compare to ClaudeGemini API preview that lets agents defer tool schemas and load them through a tool_search tool.Nov 19, 2026
Gemini computer use on Mac: requirements, how to turn it on, and the risks Google listsGemini for Mac's @Computer use: what it needs (Apple Silicon, macOS 15+, a paid plan) and how to set it up.Nov 19, 2026
Google Antigravity Orchestrator explained: how it works, who gets it and when to use itHow Antigravity's Orchestrator pairs a Gemini 4 planner with Gemini 4 Hydrogen as the executor.Nov 18, 2026
How to call Gemini 4 Hydrogen from Claude Code: gemini-api CLI, Docs MCP and skillsWays Google's docs describe to use Gemini 4 Hydrogen from a coding agent such as Claude Code.Nov 18, 2026
Google patched glitch tokens in the Gemma 4 E2B and E4B tokenizers: how to check your copyGoogle's tokenizer patch for Gemma 4 E2B and E4B that stops 217 to 233 glitch tokens garbling output.Nov 16, 2026
Gemini 4 Hydrogen costs $1.50/$7.50, and it only gets much cheaper than Carbon on December 1Gemini 4 Hydrogen, a fast model at $1.50/$7.50 per million tokens on every API tier including free.Nov 13, 2026
Google's Gemini Decisions API scores up to 1,000 yes/no and multiple-choice questions in one callA Gemini endpoint that answers closed questions with calibrated probabilities instead of generated text.Nov 12, 2026
Gemini 4 Carbon is available to paying API developers, with launch pricing that doubles after November 30Gemini 4 Carbon opens to all paying Gemini API developers at $2 input and $10 output per million tokens.Nov 12, 2026

OpenAI Codex and GPT

Codex CLI releases and configuration, and GPT model pricing. For the head-to-head with Claude Code, see the comparison table above.

PostWhat it coversDate
Codex CLI 0.171.0: the TUI workspace sidebar is on by default, GPT-6.2 Sol is the default model, and codex exec gets --remoteWorkspace sidebar on by default, GPT-6.2 Sol as the default model, and codex exec --remote.Nov 20, 2026
Codex sandbox permission profiles: config.toml rules for secrets, domains and MCP serversHow permission profiles in Codex's config.toml control what commands can read, write and reach.Nov 19, 2026
GPT-6.2 Astra and Sol in the API: prices, the Ultrafast change in March, and what to fix before you switchgpt-6.2-astra at $8/$40 per million tokens, 20% below GPT-6 Astra; gpt-6.2-sol stays at $2/$10.Nov 17, 2026

Copilot, Qwen, DeepSeek and open models

Other labs' models and the infrastructure around them, including open-weight models you can run on your own hardware.

PostWhat it coversDate
MAI Code 2 in GitHub Copilot: plans, per-token prices, and what the benchmark math assumesMAI Code 2 and MAI Code 2 Flash in the Copilot model picker: which plans get them and what they cost.Nov 17, 2026
Hugging Face Inference Providers now route through OpenRouter: what changes for your code, keys and Claude CodeHugging Face now routes Inference Providers requests through OpenRouter, with automatic retries.Nov 17, 2026
Qwen4-Max is out: 1M context, $1.50/$4.50 pricing, and a Claude Code setupAlibaba's Qwen4-Max at $1.50 in and $4.50 out per million tokens, 25% below Qwen3.8-Max.Nov 16, 2026
llama-modchip runs the 284B DeepSeek-V4-Flash on a 64 GB PC with no GPU, using patched llama.cppllama.cpp patches and quant formats that run the 284B DeepSeek-V4-Flash in 64 GB of RAM with no GPU.Nov 16, 2026
DeepSeek opens its app's search, file, voice and safety features to the APIDeepSeek's API now offers web search, URL reading and file parsing, plus Search, Fetch, OCR, ASR and TTS endpoints.Nov 15, 2026
Edge0-145B: pitched for laptops, but no laptop appears in its speed tableEdge0-145B and 120B, sparse models that keep hot experts on the GPU and stream the rest from RAM.Nov 13, 2026
Researcher says released weights show six Chinese models were started on Nvidia Blackwell GPUsA report that starting weights reveal the GPU that made them, and that six Chinese models match Nvidia Blackwell.Nov 13, 2026

Our other topic hubs

The rest of the archive, grouped the same way.

HubWhat it covers
Claude models, pricing and apps: our full coverageEvery claudefox post on Claude models, API prices, plan limits, Claude apps and connectors, agent memory, science results and Anthropic company news.
Claude Code features, releases and tips: our full coverageAll claudefox coverage of Claude Code: install and pricing guides, release notes, mods, workflows from the Claude Code team, and security fixes to know.
Claude Code plugins, skills and MCP servers: our full coverageEvery Claude Code plugin, agent skill and MCP server claudefox has reviewed, grouped by job: coding, review, video, design, research and agent tools.
Built with Claude Code: apps, games and open-source projectsApps, games, TV tools and open-source projects people built with Claude Code, plus useful open-source developer tools, each with a one-line summary.
AI agent security, privacy and policy: our coverageclaudefox posts on coding agent security: leaked secrets, sandboxes, permissions, vulnerability disclosure, major CVEs, data exposure and AI chip rules.

Source: Gemini models - Gemini API, Codex CLI - OpenAI, API pricing - OpenAI