Skip to content
Skip to content
Models / CritiqueCode All In6 min read

The All In models we recommend, and the ones that burn the allowance

Sonnet 5, GPT-5.6 Terra, Luna, Kimi K2.7 Code, Kimi K3, and Qwen 3.8 Max are now on every All In plan. Use the cheap lane first.

Repath Khan

Every All In plan now includes Claude Sonnet 5, GPT-5.6 Terra, GPT-5.6 Luna, Kimi K2.7 Code, Kimi K3, and Qwen 3.8 Max. That is the interesting part of the picker, not the default. These routes draw from the same monthly inference dollars as DeepSeek V4.1 Flash. The expensive ones will empty that allowance while you still have cloud sessions left.

The default stack

Start on DeepSeek V4.1 Flash. Move to GLM-5.3 Flash when the change needs more shape. Use GLM-5.3 when the work is actually hard. Keep Terra, Sonnet 5, Kimi K3, and Qwen 3.8 Max for the jobs that earn the burn.

All In $10 includes $20 of inference at provider cost. Counting prompts does not explain why one afternoon of Sonnet 5 can cost more than a week of Flash. The recommended stack is the one that still leaves room for a second and third session.

Recommended first. Frontier on purpose.
Burn is relative All In inference cost at provider rates, not a credit count. Live availability still depends on the route.
ModelUse it forAll In burn
DeepSeek V4.1 FlashDeepSeek V4.1 FlashDefault author. Fast edits, tests, and everyday hosted sessions.Lowest
GLM-5.3 FlashGLM-5.3 FlashThe step up when Flash-class DeepSeek needs more coding shape, still cheap.Low
GLM-5.3GLM-5.3Hard coding. People keep comparing it to Opus 5; a lot of them prefer GLM and it costs a lot less.Low to mid
GPT-5.6 LunaGPT-5.6 LunaPlanning and decomposition. More efficient than Terra, still an OpenAI reasoning model.Mid
Kimi K2.7 CodeKimi K2.7 CodeCoding-first Moonshot lane. Long-horizon implementation without jumping to K3.Mid
GPT-5.6 TerraGPT-5.6 TerraStrong OpenAI model when Luna is not enough. Burns faster.High
Kimi K3Kimi K3Planning and long-horizon reasoning. Pair with K2.7 Code, do not live here.High
Claude Sonnet 5Claude Sonnet 5When you specifically want Sonnet. It is now on All In, and it is not cheap.High
Qwen 3.8 MaxQwen 3.8 MaxAlibaba’s higher-end Max route. Useful, faster to drain the allowance.High

Opus 5 remains on Founders Edition. GLM-5.3 is on every All In plan. The comparison people keep making is not subtle: for coding agents, a lot of operators now treat GLM-5.3 as the model that does Opus-5 work at a price that does not end the month. We are not going to dress that up as a private leaderboard. It is what we hear, and it matches how the credit floors sit (GLM-5.3 at 3, Opus 5 at 30).

GLM-5.3 Flash is the cheap sibling. Use it when you want GLM’s coding habits without paying the full GLM-5.3 token burn. DeepSeek V4.1 Flash stays the default because it is the fastest way to get a hosted session moving.

GPT-5.6 Terra is a serious model. If you want OpenAI at full strength, it is in the picker now. It also drains All In inference quickly, which is why /code warns when you select it.

GPT-5.6 Luna is the efficient OpenAI route. It is already good at planning: break the task up, name the files, decide the order, then hand implementation to a cheaper coder. That split is how you keep speed without lighting the dollar cap.

Kimi K2.7 Code is the coding specialist. Keep it on the implementation loop. Kimi K3 is the larger planning model. Using K3 to think and K2.7 Code to edit is the Moonshot version of Luna-then-Flash: more reasoning where it pays, more throughput where it does not.

K3 used to sit on Founders Edition. It is now on All In $10 and $30. That is the whole reason the warning exists. A planning model at K3’s rate can finish the monthly inference allowance in a handful of long sessions.

Hosted Code now has a reasoning control next to the model picker: Low → Medium → High → Extra high. OpenAI and Anthropic routes expose Extra high. Everyone else stops at High. Default is still Medium.

Turn it up when the task is ambiguous. Leave it at Medium for ordinary edits. Extra high on Terra or Sonnet 5 is how you discover the inference cap before lunch.

Open /code and pick the cheap lane
All In now includes the frontier names. The recommended stack is still Flash, GLM Flash, and GLM-5.3. The picker will tell you when you leave that lane.
Independent reviewVerified repairReal repositoriesBuilt for developersLoved by agents