# LLMoxy - The Out-of-the-box LLM Access Layer

LLMoxy currently offers 24 models from 6 providers, all called with one API base URL and one API key.

## Endpoints

- OpenAI Chat Completions: `POST https://llmoxy.com/v1/chat/completions`
- OpenAI Responses: `POST https://llmoxy.com/v1/responses`
- Anthropic Messages: `POST https://llmoxy.com/v1/messages`
- Model list: `GET https://llmoxy.com/v1/models`

## Model list

- [gpt-6-astra](https://en.llmoxy.com/models/gpt-6-astra.md): In ￥3.00 / 1M
- [gpt-6-sol](https://en.llmoxy.com/models/gpt-6-sol.md): In ￥0.60 / 1M
- [gpt-6.1-sol](https://en.llmoxy.com/models/gpt-6.1-sol.md): In ￥0.60 / 1M
- [gpt-6.1-terra](https://en.llmoxy.com/models/gpt-6.1-terra.md): In ￥0.30 / 1M
- [gpt-image-2](https://en.llmoxy.com/models/gpt-image-2.md): ￥0.20 / request
- [gpt-image-2.5-flare](https://en.llmoxy.com/models/gpt-image-2.5-flare.md): ￥0.20 / request
- [gpt-image-2.5-sunburst](https://en.llmoxy.com/models/gpt-image-2.5-sunburst.md): ￥0.20 / request
- [claude-fable-5-2](https://en.llmoxy.com/models/claude-fable-5-2.md): In ￥12.00 / 1M
- [claude-haiku-5-5](https://en.llmoxy.com/models/claude-haiku-5-5.md): In ￥0.15 / 1M
- [claude-opus-5-5](https://en.llmoxy.com/models/claude-opus-5-5.md): In ￥6.00 / 1M
- [claude-sonnet-5-5](https://en.llmoxy.com/models/claude-sonnet-5-5.md): In ￥3.00 / 1M
- [deepseek-v4-flash](https://en.llmoxy.com/models/deepseek-v4-flash.md): From In ￥0.06 / 1M
- [deepseek-v4-flash-0731](https://en.llmoxy.com/models/deepseek-v4-flash-0731.md): From In ￥0.06 / 1M
- [deepseek-v4-pro](https://en.llmoxy.com/models/deepseek-v4-pro.md): From In ￥0.264 / 1M
- [deepseek-v4-pro-0813](https://en.llmoxy.com/models/deepseek-v4-pro-0813.md): From In ￥0.264 / 1M
- [deepseek-v4.1-flash](https://en.llmoxy.com/models/deepseek-v4.1-flash.md): From In ￥0.06 / 1M
- [gemini-3.8-flash](https://en.llmoxy.com/models/gemini-3.8-flash.md): In ￥0.375 / 1M
- [gemini-4-argon](https://en.llmoxy.com/models/gemini-4-argon.md): In ￥1.00 / 1M
- [gemini-4-hydrogen](https://en.llmoxy.com/models/gemini-4-hydrogen.md): In ￥0.75 / 1M
- [grok-4.5](https://en.llmoxy.com/models/grok-4.5.md): In ￥0.50 / 1M
- [grok-4.6](https://en.llmoxy.com/models/grok-4.6.md): In ￥0.50 / 1M
- [grok-4.7](https://en.llmoxy.com/models/grok-4.7.md): In ￥0.50 / 1M
- [jev-latest](https://en.llmoxy.com/models/jev-latest.md): In ￥0.168 / 1M
- [jev-preview](https://en.llmoxy.com/models/jev-preview.md): In ￥0.168 / 1M

## FAQ

### How is LLMoxy billed?

Pay-as-you-go per token, tracking upstream provider rates. No monthly minimum, no commitment. Every request surfaces input/output token counts and the exact upstream cost in the console.

### Which payment methods are supported?

Alipay, WeChat Pay, Visa / MasterCard, Apple Pay, and crypto such as USDT, BTC, SOL, and TRX. Multi-currency support.

### Do you log my prompts?

By default we log token counts, latency, and error codes only — no prompt or response bodies. You can opt in to request-body retention for your own debugging under Personal Settings.

### Will my upstream account get banned?

No. LLMoxy calls the upstream vendor from our own accounts; your identity isn't exposed to them. That's the whole point.

### Do you support streaming (SSE)?

Yes — chat completions, responses, messages, and image streaming are all pass-through. We do not buffer, re-chunk, or re-order.

## Links

- [All model prices](https://en.llmoxy.com/pricing.md)
- [Documentation](https://en.llmoxy.com/docs/api-reference/api-overview.md)
- [llms.txt](https://en.llmoxy.com/llms.txt)

This is the markdown version of https://en.llmoxy.com/.
