# TokenRa

> TokenRa is an OpenAI-compatible AI API gateway for model access, developer integrations, usage, and billing.

## Public pages

- [Home](https://tokenra.io/)
- [Model catalog](https://tokenra.io/models.html)
- [Developer documentation](https://tokenra.io/docs.html)
- [Console](https://tokenra.io/dashboard/overview)
- [Pricing (per-model rates)](https://tokenra.io/models.html)
- [Refund policy](https://tokenra.io/refund.html)
- [Contact](https://tokenra.io/contact.html)
- [FAQ](https://tokenra.io/faq.html)
- [Zero data retention (how API request content is handled)](https://tokenra.io/zero-data-retention.html)

## Per-model guides (llms.txt)

One plain-text guide per model: its model ID, endpoints, tested request parameters, a runnable example, current rates and known limits. URL pattern: https://tokenra.io/docs/<model-id>/llms.txt, where <model-id> is the main ID listed below; Chinese guides use https://tokenra.io/zh/docs/<model-id>/llms.txt. Each guide repeats what the model's API docs page says. All English guides in one file: https://tokenra.io/llms-full.txt

- [Seedance 2.0 Pro](https://tokenra.io/docs/seedance-2-0-pro/llms.txt): `seedance-2-0-pro`; video model, ByteDance
- [Seedance 2.0 Fast](https://tokenra.io/docs/seedance-2-0-fast/llms.txt): `seedance-2-0-fast`; video model, ByteDance
- [Seedance 2.0 Mini](https://tokenra.io/docs/seedance-2-0-mini/llms.txt): `seedance-2-0-mini`; video model, ByteDance
- [Seedance 2.5 Pro](https://tokenra.io/docs/artsdance-2-5-pro-260801/llms.txt): `artsdance-2-5-pro-260801`; video model, ByteDance
- [GPT Image 2.5 Flare](https://tokenra.io/docs/gpt-image-2.5-flare/llms.txt): `gpt-image-2.5-flare`; image model, OpenAI
- [GPT Image 2.5 Sunburst](https://tokenra.io/docs/gpt-image-2.5-sunburst/llms.txt): `gpt-image-2.5-sunburst`; image model, OpenAI
- [MiniMax M3.1 Flash](https://tokenra.io/docs/minimax-m3.1-flash/llms.txt): `minimax-m3.1-flash`; text model, MiniMax
- [MiniMax M3](https://tokenra.io/docs/minimax-m3/llms.txt): `minimax-m3`; text model, MiniMax
- [Space Bunny Alpha](https://tokenra.io/docs/space-bunny-alpha/llms.txt): `space-bunny-alpha`; text model, MiniMax
- [Qwen3.8 Max](https://tokenra.io/docs/qwen3.8-max/llms.txt): `qwen3.8-max`; text model, Alibaba Qwen
- [Qwen3.8 Flash](https://tokenra.io/docs/qwen3.8-flash/llms.txt): `qwen3.8-flash`; text model, Alibaba Qwen
- [Qwen3.8 Omni Flash](https://tokenra.io/docs/qwen3.8-omni-flash/llms.txt): `qwen3.8-omni-flash`; text model, Alibaba Qwen
- [GLM-5.3](https://tokenra.io/docs/glm-5.3/llms.txt): `glm-5.3`; text model, Zhipu AI
- [GLM-5.3 Flash](https://tokenra.io/docs/glm-5.3-flash/llms.txt): `glm-5.3-flash`, `glm‑5.3‑flash‑discounted`; text model, Zhipu AI
- [GLM-5.3 FlashX](https://tokenra.io/docs/glm-5.3-flashx/llms.txt): `glm-5.3-flashx`; text model, Zhipu AI
- [Kimi K3](https://tokenra.io/docs/kimi-k3/llms.txt): `kimi-k3`, `kimi-k3-50off`; text model, Moonshot AI
- [Kimi K3.1 Pro](https://tokenra.io/docs/kimi-k3.1-pro/llms.txt): `kimi-k3.1-pro`; text model, Moonshot AI
- [DeepSeek V4.1 Flash](https://tokenra.io/docs/deepseek-v4.1-flash/llms.txt): `deepseek-v4.1-flash`, `deepseek-v4.1-flash-50off`; text model, DeepSeek
- [DeepSeek V4.1 Flash 1017](https://tokenra.io/docs/deepseek-v4.1-flash-1017/llms.txt): `deepseek-v4.1-flash-1017`; text model, DeepSeek
- [DeepSeek V4 Flash](https://tokenra.io/docs/deepseek-v4-flash/llms.txt): `deepseek-v4-flash`; text model, DeepSeek
- [DeepSeek V4 Flash 0731 Fast](https://tokenra.io/docs/deepseek-v4-flash-0731-fast/llms.txt): `deepseek-v4-flash-0731-fast`; text model, DeepSeek
- [DeepSeek V4 Flash Vision Exp](https://tokenra.io/docs/deepseek-v4-flash-vision-exp/llms.txt): `deepseek-v4-flash-vision-exp`; text model, DeepSeek
- [Gemini 3.8 Flash](https://tokenra.io/docs/gemini-3.8-flash/llms.txt): `gemini-3.8-flash`; text model, Google
- [HY3](https://tokenra.io/docs/hy3/llms.txt): `hy3`; text model, Tencent Hunyuan
- [HY4 Preview](https://tokenra.io/docs/hy4-preview/llms.txt): `hy4-preview`; text model, Tencent Hunyuan
- [Step 5 Preview](https://tokenra.io/docs/step-5-preview/llms.txt): `step-5-preview`; text model, StepFun
- [MiMo V2.5](https://tokenra.io/docs/mimo-v2.5/llms.txt): `mimo-v2.5`; text model, Xiaomi, retired (archived guide)
- [Union Alpha](https://tokenra.io/docs/union-alpha/llms.txt): `union-alpha`; text model
- [Ox Alpha](https://tokenra.io/docs/ox-alpha/llms.txt): `ox-alpha`; text model
- [Omen Alpha](https://tokenra.io/docs/omen-alpha/llms.txt): `omen-alpha`; text model
- [Jev](https://tokenra.io/docs/jev-latest/llms.txt): `jev-latest`; decision model, TypeSafe AI

## Model guides

- [GPT Image 2.5](https://tokenra.io/models/gpt-image-2-5.html)
- [Kimi K2.8 Preview](https://tokenra.io/models/kimi-k2-8-preview.html)
- [Kimi K3](https://tokenra.io/models/kimi-k3-api.html)
- [Kimi K3.1 Pro](https://tokenra.io/models/kimi-k3-1-pro-api.html)
- [GLM-5.3-Flash](https://tokenra.io/models/glm-5-3-flash.html)
- [GLM-5.3-FlashX](https://tokenra.io/models/glm-5-3-flashx.html)
- [DeepSeek V4.1 Flash](https://tokenra.io/models/deepseek-v4.1-flash-api.html)
- [DeepSeek-V4.1-Flash-1017](https://tokenra.io/models/deepseek-v4.1-flash-1017.html)
- [Omen Alpha](https://tokenra.io/models/omen-alpha-api.html)
- [Ox Alpha](https://tokenra.io/models/ox-alpha.html)
- [Qwen3.8-Omni-Flash](https://tokenra.io/models/qwen-3.8-omni-flash.html)
- [MiniMax M3.1 Flash (released model, formerly Space Bunny)](https://tokenra.io/models/minimax-m3.1-flash-api.html)
- [Space Bunny Alpha (earlier stealth build of MiniMax M3.1 Flash)](https://tokenra.io/models/space-bunny-alpha-api.html)
- [Union Alpha](https://tokenra.io/models/union-alpha.html)
- [Jev (TypeSafe)](https://tokenra.io/models/jev-api.html)
- [Seedance 2.0 Pro](https://tokenra.io/models/seedance-2-0-api.html)
- [Seedance 2.0 Mini](https://tokenra.io/models/seedance-2-0-mini.html)
- [Seedance 2.5](https://tokenra.io/models/seedance-2-5-api.html)

## API docs (one page per model)


Request parameters, tested behaviour and code samples (cURL, Python, JavaScript, Java) for each model.

- [Docs home](https://tokenra.io/docs.html)
- [Quickstart](https://tokenra.io/docs/quickstart.html)
- [API basics: base URL, auth, errors, retries](https://tokenra.io/docs/common.html)
- [Model list](https://tokenra.io/docs/models.html)
- [Seedance 2.0 Pro (seedance-2-0-pro)](https://tokenra.io/docs/seedance-2-0-pro.html)
- [Seedance 2.0 Fast (seedance-2-0-fast)](https://tokenra.io/docs/seedance-2-0-fast.html)
- [Seedance 2.0 Mini (seedance-2-0-mini)](https://tokenra.io/docs/seedance-2-0-mini.html)
- [Seedance 2.5 Pro (artsdance-2-5-pro-260801)](https://tokenra.io/docs/artsdance-2-5-pro-260801.html)
- [GPT Image 2.5 Flare (gpt-image-2.5-flare)](https://tokenra.io/docs/gpt-image-2.5-flare.html)
- [GPT Image 2.5 Sunburst (gpt-image-2.5-sunburst)](https://tokenra.io/docs/gpt-image-2.5-sunburst.html)
- [MiniMax M3.1 Flash (minimax-m3.1-flash)](https://tokenra.io/docs/minimax-m3.1-flash.html)
- [MiniMax M3 (minimax-m3)](https://tokenra.io/docs/minimax-m3.html)
- [Space Bunny Alpha (space-bunny-alpha)](https://tokenra.io/docs/space-bunny-alpha.html)
- [Qwen3.8 Max (qwen3.8-max)](https://tokenra.io/docs/qwen3.8-max.html)
- [Qwen3.8 Flash (qwen3.8-flash)](https://tokenra.io/docs/qwen3.8-flash.html)
- [Qwen3.8 Omni Flash (qwen3.8-omni-flash)](https://tokenra.io/docs/qwen3.8-omni-flash.html)
- [GLM-5.3 (glm-5.3)](https://tokenra.io/docs/glm-5.3.html)
- [GLM-5.3 Flash (glm-5.3-flash, glm‑5.3‑flash‑discounted)](https://tokenra.io/docs/glm-5.3-flash.html)
- [GLM-5.3 FlashX (glm-5.3-flashx)](https://tokenra.io/docs/glm-5.3-flashx.html)
- [Kimi K3 (kimi-k3, kimi-k3-50off)](https://tokenra.io/docs/kimi-k3.html)
- [Kimi K3.1 Pro (kimi-k3.1-pro)](https://tokenra.io/docs/kimi-k3.1-pro.html)
- [DeepSeek V4.1 Flash (deepseek-v4.1-flash, deepseek-v4.1-flash-50off)](https://tokenra.io/docs/deepseek-v4.1-flash.html)
- [DeepSeek V4.1 Flash 1017 (deepseek-v4.1-flash-1017)](https://tokenra.io/docs/deepseek-v4.1-flash-1017.html)
- [DeepSeek V4 Flash (deepseek-v4-flash)](https://tokenra.io/docs/deepseek-v4-flash.html)
- [DeepSeek V4 Flash 0731 Fast (deepseek-v4-flash-0731-fast)](https://tokenra.io/docs/deepseek-v4-flash-0731-fast.html)
- [DeepSeek V4 Flash Vision Exp (deepseek-v4-flash-vision-exp)](https://tokenra.io/docs/deepseek-v4-flash-vision-exp.html)
- [Gemini 3.8 Flash (gemini-3.8-flash)](https://tokenra.io/docs/gemini-3.8-flash.html)
- [HY3 (hy3)](https://tokenra.io/docs/hy3.html)
- [HY4 Preview (hy4-preview)](https://tokenra.io/docs/hy4-preview.html)
- [Step 5 Preview (step-5-preview)](https://tokenra.io/docs/step-5-preview.html)
- [MiMo V2.5 (mimo-v2.5)](https://tokenra.io/docs/mimo-v2.5.html)
- [Union Alpha (union-alpha)](https://tokenra.io/docs/union-alpha.html)
- [Ox Alpha (ox-alpha)](https://tokenra.io/docs/ox-alpha.html)
- [Omen Alpha (omen-alpha)](https://tokenra.io/docs/omen-alpha.html)
- [Jev (jev-latest)](https://tokenra.io/docs/jev-latest.html)

Setup guides for coding tools (base URL, API key, model ID, tested models):

- [Use TokenRa in Claude Code](https://tokenra.io/docs/claude-code.html)
- [Use TokenRa in Cursor](https://tokenra.io/docs/cursor.html)
- [Use TokenRa in Cline](https://tokenra.io/docs/cline.html)
- [Use TokenRa in Codex CLI](https://tokenra.io/docs/codex-cli.html)
- [Use TokenRa in CC Switch](https://tokenra.io/docs/cc-switch.html)
- Chinese versions use /zh/docs/ instead of /docs/, for example https://tokenra.io/zh/docs/kimi-k3.html

## API access

Chat completions endpoint:

`https://tokenra.io/v1/chat/completions`

Image generation endpoint:

`https://tokenra.io/v1/images/generations`

Video generation endpoint (asynchronous tasks):

`https://tokenra.io/v1/video/generations`

Typed decision endpoint (Jev):

`https://tokenra.io/v1/decisions`

Use a TokenRa API key and a model identifier enabled for the account. Keep API keys server-side. Current model IDs, pricing, rate limits, and availability are shown in the live console.