Quickstart
TokenFlux is a unified interface for large language models: call mainstream models across various clients through a unified API key.
For AGENTS
For bulk Markdown reads, use markdown-sitemap.xml. For a single page, append .md to any documentation URL that does not end with /, for example /en/docs/quickstart.md.
Getting Started
- Choose a client below. In the model marketplace, confirm that the target model's group supports the required protocol and client.
- Read Billing, check prices, then top up or subscribe for inference credits.
- Create an API key on the group you selected.
- Follow the client guide below to enter the key, endpoint, and model ID.
- Send a message and check the reply and usage log to confirm the integration.
For groups, account pools, inference credits, and other terms, see Core Concepts.
Client Options
Best for terminal workflows, programming tasks, or users who want AI Agent assistance while developing.
Follow the guide for your client. To manage keys and models together, use tf-cli to launch clients through tf in the terminal. For graphical provider configuration, use CC-Switch. Neither tool is a prerequisite.
| Client guide | Best for |
|---|---|
| Claude Code | Anthropic's official CLI, terminal coding |
| Codex | OpenAI's official CLI and desktop app |
| Codex++ | Adds extra capabilities on top of Codex |
| OpenCode | Open-source terminal agent with model switching |
| Pi | Extensible terminal coding agent |
| DeepSeek Harness | Desktop and Web UI with custom model APIs |
| Hermes | Lightweight terminal agent |
Confirm the Integration
- Select the target model in your client, start a new conversation, and send "Reply with OK only". This incurs inference charges.
- Confirm that you receive model-generated text, not just a model list or a "configuration saved" message.
- Find the request in the usage logs, check the key, model, and charge, and confirm the group matches your key configuration.
This only confirms that this text conversation worked. Test tool calls, images, or other capabilities separately if needed. If there is no reply or the usage record differs from your expectations, see Troubleshooting.
Going Further
After integration, the following may be useful:
- Creative Studio - generate images directly on the web without client or API configuration
- Composite Key - bind one key to several groups and switch with prefixes
- Fast Mode - force the high-priority tier at the key level
- Team - share the owner's balance while everyone keeps their own keys
- Referral Rewards - earn inference credits by inviting friends
Troubleshooting
- Troubleshooting - find the problem by symptom, with a report template
- Error Codes - the full error reference
- FAQ - enterprise integration, model detection, and other common questions
- API Endpoints - choosing an endpoint and migrating from deprecated routes
- Usage Policy - what gets accounts banned