Choose a model tier or specific model for a task and understand the displayed Credit rate.
The task composer in Qoder includes a model selector. Choose the model after you understand the task scope, then check the displayed Credit rate before sending. You can use automatic routing or a model tier, or select an available model directly.
Lite supports Auto, Efficient, and a curated selection of models. See models available with Lite; check your account’s model selector for current availability and Credit rates.
Users should access Qoder through officially supported methods and must not relay or resell Qoder services without authorization, or provide shared access to third parties. In cases of suspected misuse of this kind, Qoder reserves rights regarding the relevant access or adjustments to available models and service capabilities. If a violation is confirmed, the relevant services may be suspended or terminated; in serious cases, account services may be suspended or terminated.
Use the badges and current rate beside a model's name to help choose:
When the model entry shows an update notification, open the list and view the relevant groups to clear their notifications. Viewing an update does not select a model; choose one before sending your next message.
Availability, badges, and rates depend on your account's current display. An absent load indicator does not guarantee an idle model, and custom API-key models may not provide load information.
Start with Auto for general work. Choose Ultimate for complex work where result quality matters most, Fast for well-defined tasks that need fast turnaround, and Efficient for smaller tasks.
The selector separates models into Default and Enterprise. Default contains the tiers and models available to the signed-in account. Enterprise contains models provided by the current organization. If the Enterprise tab is empty or unavailable, the account does not currently have an enterprise model to select.
In addition to tier selection, you can directly choose a specific model from a particular provider. This is ideal when you have a clear model preference or a specific requirement.
Select Manage models at the bottom of the selector and configure model parameters under Default. Available parameters and ranges vary by model.
Thinking controls whether reasoning is enabled, while thinking effort adjusts its depth.
The context window determines how much context the model can use when processing a request. Adjust the slider in the model's context window column to select a supported size.
With thinking enabled, open the thinking effort dropdown for a model that supports adjustable effort. Available levels depend on the model. For example, Qwen3.8-Max offers low, medium, and extra high effort. When thinking is off, the column shows that thinking is disabled; this is not a level in the effort dropdown.
An always-on thinking model may still support adjustable effort. Check the thinking switch and effort control separately. Check the credit-usage hint when choosing a level; higher effort may use more Credits.
Click Save settings after making changes. Reopen model management to check the saved values. Click Cancel to discard the current changes.
Under Default in model management, use the display toggles to show or hide models in the selector. To configure your own API key, switch to Custom. See Custom Models.
Yes. The new selection applies to later messages and keeps the current task context; earlier responses are not regenerated.
Models vary by client version, account availability, and service updates. The names, labels, and rates shown in the composer are authoritative for the current task.
A tier lets Qoder route by policy. Select a specific model when you explicitly need that model or capability combination.
Credit usage depends on the tokens used, the selected tier or model, configured parameters, and tool activity. Check the rate shown in the selector before sending.
When Credits run out, you can continue using free basic models, subject to daily and monthly limits. Paid users, including Lite subscribers, can manually switch to Efficient during the limited-time free offer, or acquire more Credits. Service Account usage is excluded from the offer. Please note that free and trial benefits are for the user’s own use only. Qoder may revoke these benefits if the user violates the usage rules above.
To use your own API key, add a custom model under Settings → Models. After it is added, the model becomes available to task, Agent, and automation model selectors. See Custom Models.
Usage Rules and Benefits
Users should access Qoder through officially supported methods and must not relay or resell Qoder services without authorization, or provide shared access to third parties. In cases of suspected misuse of this kind, Qoder reserves rights regarding the relevant access or adjustments to available models and service capabilities. If a violation is confirmed, the relevant services may be suspended or terminated; in serious cases, account services may be suspended or terminated.
Switch models
1
Open the selector
Select the current model at the bottom of a new or existing task composer.
2
Choose a tier or model
Select Auto, another model tier, or a specific model from the list.
3
Continue the task
The selection applies to subsequent messages. Before sending, check the model and rate shown in the composer.
Check model status and update notifications
Use the badges and current rate beside a model's name to help choose:
| Display | What to check |
|---|---|
| New | A newly available model you can select if it suits the task. |
| Free | A current free offer; also check the displayed rate and the offer's eligibility rules. |
| Crowded or busy indicator | The model is under load. Consider another model if you need a faster response; the indicator is not a completion-time estimate. |
| Struck-through and current rates | The struck-through value is the original rate. Check the current value beside it before sending. |
Choose a tier
| Tier | Description | Use cases | Credit usage |
|---|---|---|---|
| Auto (Smart Routing) | Intelligently selects the most suitable model, balancing performance and cost | Most daily work, recommended as default | ~0.5× |
| Ultimate | Expert-level deep reasoning and thinking capabilities | Complex system design, high-difficulty problem analysis | ~2.0× |
| Fast | Fast and efficient, with faster responses and lower Credits consumption | Tasks that need fast turnaround: daily reports, business code, bug fixes, and new features | ~0.8× |
| Efficient | Standard reasoning capabilities, high cost-effectiveness | Basic code generation, unit tests, daily Q&A |
During the limited-time offer, Efficient is free for paid users (0.0×). Service Account usage is excluded and billed at the regular 0.3× multiplier. Calls to specific models by sub-agents are billed separately. See offer details.
Credit consumption comparison
| Model tier | Credit consumption rate | Example task consumption |
|---|---|---|
| Auto | ~0.5× | 5 Credits |
| Ultimate | ~2× | 20 Credits |
| Fast | ~0.8× | 8 Credits |
| Efficient |
Due to variations in tasks and codebases, actual consumption rates may differ.Actual Credit use varies with the task, repository, selected parameters, and tool calls. The rate shown in the selector is the authoritative estimate for the next request.
Default and Enterprise models
The selector separates models into Default and Enterprise. Default contains the tiers and models available to the signed-in account. Enterprise contains models provided by the current organization. If the Enterprise tab is empty or unavailable, the account does not currently have an enterprise model to select.
Select a specific model
In addition to tier selection, you can directly choose a specific model from a particular provider. This is ideal when you have a clear model preference or a specific requirement.
| Model name | Description | Credit consumption rate |
|---|---|---|
| Qwen3.8-Max | Qwen's latest foundation model, with 2.4T parameters, leading in software engineering, office work, and deep reasoning | 0.5× |
| Qwen3.8-Flash | Qwen's open-weight multimodal MoE model, delivering an excellent balance of capability, latency, and cost | 0.1× |
| DeepSeek-V4-Pro | Excels at complex reasoning, code generation, and engineering tasks | 0.5× |
| DeepSeek-Flash | Fast reasoning and low cost with balanced capabilities | 0.1× |
| GLM-5.3 | Zhipu's open-source flagship model, with coding capabilities competitive with leading international models, plus security review and vulnerability reasoning | 0.8× |
| GLM-5.3-Flash | Zhipu's new natively multimodal model, with deep image and video understanding for research, analysis, and document creation | 0.1× |
| Kimi-K3.1-Pro | Kimi's most powerful model, built for software engineering, knowledge work, and deep reasoning | 1.0× |
| Kimi-K2.8-Preview | Built for long-context coding: precise instruction following and reliable execution of long-running tasks. | 0.8× |
| MiniMax-M3.1-Flash | MiniMax’s next-generation Flash model with native multimodality and upgraded coding, agent, and cybersecurity capabilities for complex workflows | 0.1× |
Models, capability labels, and rates can change by client version and account availability. The selector in the task composer is authoritative.