Explore the model catalog
Compare current models by provider, capability, context window, and Credit price.
Open model catalogX-AIO DEVELOPER PLATFORM
Connect open and proprietary models across IDE, CLI, and API workflows
Choose models, connect AI tools, manage Tokens Plan and Credits, and inspect usage from one development workspace.
Model availability and live pricing are maintained in the dashboard.
Model access
Open + proprietary
Workflows
IDE + CLI + API
Interfaces
Chat + Responses + Anthropic
Unified meter
Credits
START HERE
Go directly to the documentation or dashboard area that matches your current task.
MODEL ACCESS
Move between open models and proprietary frontier models as the task changes. Models, contexts, and promotions update over time.
OPEN MODELS
A flexible and cost-effective choice for coding and general reasoning workloads.
PROPRIETARY MODELS
Frontier coding, long-context, and complex agentic workflows.
CREDITS / 1M TOKENS
The model catalog shows Credit prices per 1M Tokens and separates cached-input pricing.
The homepage does not hard-code model counts or prices that can become stale.
ONE WORKFLOW
Choose a model and interface first, then connect it to the editor, terminal, or application you already use.
01 / INTERFACE
Use OpenAI Chat, Responses, or Anthropic according to each model family.
02 / IDE & CLI
Use the same model access from IDEs, editor extensions, and CLI agents.
03 / APP & MCP
Connect chat clients, office tools, agent platforms, and MCP-enabled services.
PLANS & CREDITS
Credits are the unified unit for model usage. RMB wallet balance and Credits remain separate.
RECURRING
Credits issued each subscription period for steady development workloads.
ONE-TIME
One-time Credits available immediately and consumed by purchase order.
LONG-TERM
Long-lived Credit capacity that can replenish by period and accumulate.
Default consumption order
OBSERVABILITY
The dashboard separates aggregate usage from individual request records for cost, performance, and reliability analysis.
View usage analyticsRequest count, success rate, and failure status
Input/output Tokens and cache hit rate
Total cost with input and output breakdowns
Average latency, time to first token, and request duration
Start with an integration guide, or open the dashboard to inspect current models and plans.