Open Source
TokenMix
by Token Limited
A hosted API relay run by Token Limited in Hong Kong that resells access to Claude, OpenAI, Gemini, DeepSeek, Qwen and image, video and audio models through one OpenAI-compatible endpoint and a prepaid wallet. It is not open source.
Our verdict
A hosted API relay run by Token Limited in Hong Kong that resells access to Claude, OpenAI, Gemini, DeepSeek, Qwen and image, video and audio models through one OpenAI-compatible endpoint and a prepaid wallet. It is not open source.
Best for: Developers who want one prepaid wallet across many model families, topped up in small amounts.
Choose something else if: you need a service level agreement or a direct contract with the model maker. TokenMix is an intermediary and offers no SLA.
Source review
Using TokenMix in practice
Where it runs
Hosted by Token Limited, with servers in Hong Kong. Each request is relayed to the upstream provider for the model you call.
How to install
Register with your email, create a key under Dashboard and API Keys, top up, then point an OpenAI-compatible client at https://api.tokenmix.ai/v1. Claude Code uses https://api.tokenmix.ai, without /v1.
Install commands
export ANTHROPIC_BASE_URL=https://api.tokenmix.ai
export ANTHROPIC_AUTH_TOKEN=sk-tm-your-api-key-hereAs published in the linked sources. Not run by us.
What it costs
Prepaid wallet billed per token, with no monthly fee. Top-ups start at US$1, depending on the payment method. Unused credit can be refunded within 14 days of purchase.
Prices and plans change. Check the linked sources before committing.
Why consider it
- One OpenAI-compatible base URL and key across text, image, video, audio and embedding models.
- Top-ups from US$1, and purchased credit does not expire.
What to watch for
- An intermediary: requests go through Token Limited to upstream providers, and you must also follow those providers' terms.
- Standard logs leave out prompt and response content, but limited records may be archived for security, support or disputes.
- Its servers are in Hong Kong.
A first task to try
Top up the minimum, call one model with a non-sensitive prompt, then compare the usage record with the model maker's list price.
Suggested exercise, not an installation test. We reviewed the linked documentation; no host compatibility is implied.
Other options to understand
Related tools can solve different parts of the same job. Compare fit before treating them as replacements.
Key facts
What we have checked
Not checked yet. Dated facts such as prices, releases and repository activity appear here once we have confirmed them from a source.
Alternatives
Alternatives to TokenMix
| Record | Type | How we know | Checked |
|---|---|---|---|
| FreeLLMAPIThis is an alternative to it | Open source | Named in the listing | Not dated |
| LiteLLMThis is an alternative to it | Open source | Named in the listing | Not dated |
Compare
Compare TokenMix side by side
Sources
Where this comes from
- API summaryOur review
- Client setup, including Claude CodeOur review
- Terms of ServiceOur review
- Privacy policyOur review
A source shows what was published when we checked it. It does not certify security, performance or a working installation. Read our method.
Changelog
What changed
No changes recorded yet. Releases, price changes and deprecations appear here, with their dates, once we track them for this record.
Get the free Developer’s Field Guide
A 27-page field guide to the AI coding workflow with Claude. Claude Code, MCP servers, the prompt patterns that work, and what to delegate. Free.
Enter your work email. We send it straight over, plus a few short notes worth knowing. Unsubscribe any time.