Qoder IDE includes world-class SOTA AI models and offers a flexible selection mechanism to help you find the optimal balance between development efficiency, output quality, and cost.
In addition to built-in models, you can also connect your own models via API keys. See Custom Models for details.
The Model Tier Selector provides developers with four high-performance model pools, each striking a different balance between cost and performance. Like driving modes in a smart car, choose the right gear for each task.
Tier
Description
Use Cases
Credit Usage
Auto (Smart Routing)
Intelligently selects the most suitable model, balancing performance and cost
Most daily development work, recommended as default
~0.5×
Ultimate
Expert-level deep reasoning and thinking capabilities
Complex system design, high-difficulty problem analysis
Standard reasoning capabilities, high cost-effectiveness
Basic code generation, unit tests, daily Q&A
0.3×0.0× (Limited-time free (paid users))
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.
The table below shows Credit consumption examples for different tiers when completing a moderately complex coding task:
Model Tier
Credit Consumption Rate
Example Task Consumption
Auto
~0.5×
5 Credits
Ultimate
~2.0×
20 Credits
Performance
~1.1×
11 Credits
Efficient
0.3×0.0× (Limited-time free (paid users))
3 Credits0 Credits (paid users)
Due to variations in tasks and codebases, actual consumption rates may differ.
Experts Mode is selected separately from model tiers. In Experts Mode, you can choose between Auto (1.0x) and Ultimate (1.6x) tiers. It coordinates multiple expert agents in parallel, so actual Credit usage depends on task complexity, expert turns, and tools invoked.
In addition to tier selection, you can directly choose a specific model from a particular provider. Ideal for scenarios where you have clear model preferences or specific requirements.
Currently, only a selection of models is available for direct selection.
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×
Qwen3.7-Max
Qwen's latest model, with top-tier agentic capabilities, autonomously handles complex tasks up to 35 hours long
0.5×
Qwen3.7-Plus
Comprehensive leap in reasoning capability, efficiency, and multimodal experience
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
Kimi's most powerful model, with 2.8T parameters, built for software engineering, knowledge work, and deep reasoning
1.4×
Kimi-K2.8-Preview
Built for long-context coding: precise instruction following and reliable execution of long-running tasks.
0.8×
MiniMax-M3
Native multimodal perception, frontier coding, and 1M context depth for highly demanding workflows
0.2×
The rates in the table are overall estimates. Actual Credit usage can vary with parameter settings: changing the context window, Thinking Effort, or speed may change the rate. DeepSeek-V4-Pro and DeepSeek-Flash use peak and off-peak pricing. Peak hours are Monday through Friday, 09:00–12:00 and 14:00–18:00 Beijing Time (UTC+8); all other hours are off-peak. The off-peak price is 50% of the peak price. For details, see DeepSeek's official pricing. Final charges are based on actual usage.
Some models support configuring parameters to better adapt to different task types. In the model selector dropdown, hover over a model name to reveal a parameter panel on the left, then click the Edit button to configure parameters.
Controls how deeply the model reasons before generating a response. Available options vary by model — the interface will show the supported levels after you select a model.
Option
Description
low
Minimal reasoning, fastest responses
medium
Balanced reasoning depth
high
Thorough reasoning for complex tasks
xhigh
Deep analysis for high-difficulty problems
max
Maximum reasoning depth, best for the most complex challenges
Currently, Ultimate, Performance, DeepSeek-V4-Pro, DeepSeek-Flash, Qwen3.8-Max, Qwen3.8-Flash, Qwen3.7-Max, Qwen3.7-Plus, GLM-5.3, GLM-5.3-Flash, MiniMax-M3, Kimi-K3, and Kimi-K2.8-Preview support parameter configuration. Qwen3.7-Max, Qwen3.7-Plus, and MiniMax-M3 support Context only; the others support both Context and Thinking Effort.
In the AI Chat input box, click the model selector dropdown menu
Select Model Tier or Specific Model
The selection takes effect immediately, and the new model will apply to subsequent conversations in the current session
When Credits run out, requests that require Credits cannot continue. Paid users can manually switch to Efficient during the limited-time free offer, or acquire more Credits. Service Account usage is excluded from the offer.
Yes. Qoder IDE continuously introduces outstanding new models from the industry, and will retire or replace some older models based on model performance and market conditions, keeping the model list high-quality and reliable.
Yes. You can switch model tiers or specific models at any time using the dropdown menu in the chat input box. The new selection takes effect instantly for subsequent conversations, allowing you to adjust dynamically based on real-time task needs.
What's the difference between model tiers and specific models?
The Model Tier Selector intelligently matches the most suitable model based on the selected tier—you don't need to know which specific model is being used. Specific model selection lets you directly choose a particular model from a specific provider, ideal for scenarios where you have clear preferences or specific requirements.
How is Credit consumption calculated for different models?
Your Credit consumption is determined by the number of tokens used per request and the unit price of the model used. For detailed billing rules, please refer to Credits.
