Models
Every chat session runs on one model at one reasoning effort, such as Opus 5.5 (xHigh). Pick it in the Model row when you create a session, or from the model picker in the chat header. A session you do not set starts on its Assignee's Default Model.
Pick a model
- Open the model picker. In a session it sits on the right of the chat header. In the New Session dialog and in a Backlog session's details it is the Model row.
- Hover over a model to open its Reasoning effort menu.
- Pick an effort.
Some OpenAI models also have a Speed group under the efforts. See Choose a speed.
The picker groups models under Anthropic, OpenAI, Z.ai and Moonshot AI. It offers the providers the session's Assignee can run. In the chat header of a session assigned to you or to no one, a provider you cannot run shows "Needs auth", with a link to AI Providers where you connect it. In a session assigned to someone else, providers they cannot run are hidden. The New Session dialog and a Backlog session's details hide providers the Assignee cannot run.
Reasoning effort sets how long the agent thinks before it acts. A higher effort suits hard problems. A lower one is faster for mechanical edits.
Available models
| Provider | Model | Reasoning efforts | Context window (tokens) |
|---|---|---|---|
| Anthropic | Fable 5.1 | Low, Medium, High, xHigh, Max, Ultracode | 1,000,000 |
| Anthropic | Opus 5.5 | Low, Medium, High, xHigh, Max, Ultracode | 1,000,000 |
| Anthropic | Sonnet 5.5 | Low, Medium, High, xHigh, Max | 1,000,000 |
| Anthropic | Haiku 5.5 | Low, Medium, High, xHigh, Max | 1,000,000 |
| OpenAI | GPT 6 Astra | Low, Medium, High, xHigh, Max | 872,000 |
| OpenAI | GPT 6.1 Sol | Low, Medium, High, xHigh, Ultra | 872,000 |
| OpenAI | GPT 5.6 Terra | Low, Medium, High, xHigh, Ultra | 872,000 |
| OpenAI | GPT 6 Luna | Low, Medium, High, xHigh | 872,000 |
| Z.ai | GLM-5.3 | Low, High, Max | 1,000,000 |
| Z.ai | GLM-5.3-Flash | Low, High, Max | 1,000,000 |
| Moonshot AI | Kimi K3 | Low, High, Max | 200,000 |
Anthropic, GLM and Kimi models run in Claude Code. OpenAI models run in Codex. That choice decides a few things in the session:
- Skills start with
/in Claude, GLM and Kimi sessions, and with$in Codex sessions. - A
/compactfocus is Claude Code's prompt for the summary. Codex compacts without a prompt, so your focus stays in the conversation's history as a note, which Codex may not follow.
GLM-5.3 reads text only. For images and PDFs, use GLM-5.3-Flash or Kimi K3. OpenAI models read images but not PDFs. See Messages, Up next and steering for attachment limits.
Retired models sit under Legacy at the bottom of the picker.
Choose a speed
Some OpenAI models can answer faster at a higher price. Their menu has a Speed group under the efforts. Standard is the default and costs nothing extra.
- Open the model picker and hover over the model.
- Under Speed, pick Fast or Ultrafast. The menu stays open.
- Pick an effort. When the session is already on that model, the speed applies at once and keeps its effort.
| Speed | What it does | Models |
|---|---|---|
| Standard | Runs at the normal price. | Every model |
| Fast | About 1.5x to 2x faster, depending on the model. Costs more. | GPT 6.1 Sol, GPT 6 Astra, GPT 6 Luna, GPT 5.6 Terra, and the Legacy GPT 6 Sol, GPT 5.6 Sol and GPT 5.6 Luna |
| Ultrafast | The fastest tier. Costs the most. | GPT 6 Astra |
The model then reads, for example, GPT 6 Astra (High, Fast). Changing the effort keeps the speed. Picking another model goes back to Standard. Every model picker has the Speed group, so you can save a speed on a session, a Cron, your Default Model or the deploy agent.
Ultra, a reasoning effort on GPT 6.1 Sol and GPT 5.6 Terra, is not a speed. A Codex agent can run agents of its own at every effort.
Whether a turn gets its speed depends on the OpenAI login it runs on, as AI providers lists. A turn that cannot get it stops, and the chat says why, for example "Fast isn't available to this OpenAI account". It never runs at Standard instead. Pick Standard to run it.
Set your Default Model
Your Default Model is the one your new sessions start on when nobody picks one.
- Open Settings > Your Account > AI Providers.
- Under Default Model, pick a model and effort, or Automatic.
The setting follows you into every workspace. On Automatic, new sessions use the workspace's Workspace Default Model when its admins have set one and you can run its provider. Otherwise Kosuke picks a model you can run and prefers your own Subscription over the workspace's Credentials. It takes the first provider you can use, in the order Anthropic, OpenAI, Z.ai, Moonshot AI:
| Provider | Automatic picks |
|---|---|
| Anthropic | Opus 5.5 (xHigh) |
| OpenAI | GPT 6.1 Sol (xHigh) |
| Z.ai | GLM-5.3 (High) |
| Moonshot AI | Kimi K3 (High) |
If your Default Model's provider is not available in a workspace, settings say so, and new sessions there use an available model.
A new session starts on its Assignee's Default Model, whoever creates it. If you create a Backlog session without picking a model, the Model row shows "Default Model". The session's details then show its Assignee's Default Model, which it takes when it starts.
Switch model during a session
You can change the model of an Active session while the agent is idle. While a turn runs, the picker is locked.
- Open the model picker in the chat header.
- Pick the new model and effort.
- Send your next message. The new model takes effect with it.
Switching within the same provider keeps the conversation as it is. Switching to another provider starts a fresh conversation for the new agent. Kosuke hands it the conversation so far as text. The text carries what you and the agent said, and the branch and sandbox still hold the work. The transcript marks the switch, for example "Switched from Anthropic - Opus 5.5 (xHigh) to OpenAI - GPT 6.1 Sol (xHigh), conversation handed over".
A very long conversation is shortened for the new agent. It keeps your opening prompt and the latest exchanges. After /clear, nothing said before the clear is handed over.
Where each provider runs
| What | Providers | Where the model is picked |
|---|---|---|
| Chat sessions | Anthropic, OpenAI, Z.ai, Moonshot AI | The chat header, or the New Session dialog |
| Deploy agent | Anthropic, OpenAI | The Deploy Chat header in project settings |
| The Lead | Anthropic, OpenAI | The Lead's composer |
AI providers explains whose credentials run each one. The Lead does not offer Ultracode or Ultra. A default that uses one runs the Lead at the next effort down.
To reassign a session, the new Assignee must be able to run its model. See Chat sessions and the board. The API and the CLI name models by id. See the models reference.