# Full model list

> 208 callable models — 105 text across 12 vendors, 25 image, 70 video, generated from the pricing registry

来源：https://oem.dflop.top/en/docs/reference/models

The platform currently offers **208 callable models**: **105 text chat models** across **12 vendors**, plus **25 image** and **70 video** generators, and 8 music / voice / avatar SKUs (last section on this page). Text pricing is in credits per 1M tokens; images bill per image and video per second.

> This page is **generated from the same pricing registry the gateway bills against**, so every id here is callable and every price is the one you are charged.
>
> ⚠️ The 208 here and the 213 on the [model catalogue](https://oem.dflop.top/models) count different things — this is not drift: the plaza additionally shows not-yet-launched placeholder cards (badged "coming soon"), while this page lists only ids you can call **today**. A few API-only SKUs appear on neither. Live data: `GET https://oemoemapi.dflop.top/api/v1/models/public`, or the [model catalogue](https://oem.dflop.top/models).

## Reading the tables

| Column | Meaning |
|---|---|
| capability `tools` | function calling |
| capability `vision` | image input |
| capability `web_search` | built-in web search tool |
| capability `image_gen` / `video_gen` | generate images / video inside a conversation |
| capability `thinking` | reasoning / thinking mode |
| capability `json` | enforced JSON output |
| `cached` | the price when input hits the prompt cache |

> **Cached pricing needs no opt-in**: when upstream usage reports `cached_tokens`, the gateway settles that portion of the input at the cached rate automatically — clients don't (and can't) enable it explicitly. Models without a `cached` figure bill all input at the Input price.

> **Only Anthropic Claude charges for cache *writes*.** The first time Claude writes a prefix into the cache, those tokens bill at **Input × 1.25** (`cache_creation_input_tokens`); later hits bill at the `cached` rate above (Input × 0.1). The cache lives about **5 minutes**, refreshed on every hit — if no follow-up turn reuses the prefix within that window, the write premium buys nothing. Every other vendor (OpenAI / xAI / Alibaba / Zhipu / Moonshot / DeepSeek / MiniMax / Tencent / Volcengine) only has a hit discount and does not bill writes separately.

> **Limited-time promotion**: the whole Anthropic Claude line is charged at **40% off** (list price × 0.6) and the whole OpenAI GPT text line at **70% off** (× 0.3), with cached rates discounted equally. The tables show list prices; actual billing always uses the discounted rate, for both API-key calls and in-platform conversations. Discounted models carry an "X% OFF" badge on the model catalogue.

> **Long-context tier**: for `grok-4.5` / `grok-4.6`, a prompt of **≥200K tokens** bills input, cache-hit and output all at **2× the table price**. That is xAI's whole-turn doubling for very long requests, passed straight through (verified to the cent on 2026-08-23). The trigger is the total prompt size of the turn, independent of how much was generated. No other model has this tier.

> **Server-side tools bill per call**: when a grok model runs web search / tools, the upstream charges **2.022 points per tool call** on top of tokens. The count comes from the upstream's `usage.num_server_side_tools_used` and is written to the `server_tool_calls` column of every usage-log row, so you can re-derive your bill. Turns that use no tools incur no such charge.


## Anthropic (11)

| Model ID | Name | Context | Input (积分/1M) | Output (积分/1M) | Capabilities |
|---|---|---|---|---|---|
| `claude-fable-5` | Claude Fable 5 | 200K | 4044 (cached 404.4) | 20220 | tools / vision / web_search / thinking / json |
| `claude-haiku-4-5-20251001` | Claude Haiku 4.5 | 200K | 404.4 (cached 40.44) | 2022 | tools / vision / web_search / thinking / json |
| `claude-opus-4-5-thinking` | Claude Opus 4.5 Thinking | 200K | 6066 (cached 606.6) | 30330 | tools / vision / web_search / thinking / json |
| `claude-opus-4-6` | Claude Opus 4.6 | 1M | 6066 (cached 606.6) | 30330 | tools / vision / web_search / thinking / json |
| `claude-opus-4-6-thinking` | Claude Opus 4.6 Thinking | 1M | 6066 (cached 606.6) | 30330 | tools / vision / web_search / thinking / json |
| `claude-opus-4-7` | Claude Opus 4.7 | 1M | 6066 (cached 606.6) | 30330 | tools / vision / web_search / thinking / json |
| `claude-opus-4-8` | Claude Opus 4.8 | 1M | 6066 (cached 606.6) | 30330 | tools / vision / web_search / thinking / json |
| `claude-opus-5` | Claude Opus 5 | 1M | 6066 (cached 606.6) | 30330 | tools / vision / web_search / thinking / json |
| `claude-sonnet-4-5-20250929` | Claude Sonnet 4.5 | 200K | 1213.2 (cached 121.32) | 6066 | tools / vision / web_search / thinking / json |
| `claude-sonnet-4-6` | Claude Sonnet 4.6 | 1M | 1213.2 (cached 121.32) | 6066 | tools / vision / web_search / thinking / json |
| `claude-sonnet-5` | Claude Sonnet 5 | 1M | 1213.2 (cached 121.32) | 6066 | tools / vision / web_search / thinking / json |

## OpenAI (8)

| Model ID | Name | Context | Input (积分/1M) | Output (积分/1M) | Capabilities |
|---|---|---|---|---|---|
| `codex-auto-review` | Codex Auto Review | 272K | 80.88 (cached 8.088) | 485.28 | tools / vision / web_search / image_gen / thinking / json |
| `gpt-5.5` | GPT-5.5 | 1M | 2022 (cached 202.2) | 12132 | tools / vision / web_search / image_gen / thinking / json |
| `gpt-5.6-luna` | GPT-5.6 Luna | 1M | 80.88 (cached 8.088) | 485.28 | tools / vision / web_search / image_gen / thinking / json |
| `gpt-5.6-sol` | GPT-5.6 Sol | 1M | 2022 (cached 202.2) | 12132 | tools / vision / web_search / image_gen / thinking / json |
| `gpt-5.6-terra` | GPT-5.6 Terra | 1M | 2022 (cached 202.2) | 12132 | tools / vision / web_search / image_gen / thinking / json |
| `gpt-6` | GPT-6 | 1.05M | 4044 (cached 404.4) | 20220 | tools / vision / web_search / image_gen / thinking / json |
| `gpt-6-astra` | GPT-6 Astra | 1.05M | 4044 (cached 404.4) | 20220 | tools / vision / web_search / image_gen / thinking / json |
| `gpt-oss-120b-medium` | GPT-OSS 120B (Medium) | 131K | 60.66 | 242.64 | tools / thinking / json / open-source |

## Google (9)

| Model ID | Name | Context | Input (积分/1M) | Output (积分/1M) | Capabilities |
|---|---|---|---|---|---|
| `gemini-3-flash` | Gemini 3 Flash | 1M | 161.76 (cached 40.44) | 1213.2 | tools / vision / web_search / thinking / json |
| `gemini-3-flash-agent` | Gemini 3 Flash (Agent) | 1M | 161.76 (cached 40.44) | 1213.2 | tools / vision / web_search / thinking / json |
| `gemini-3-pro` | Gemini 3 Pro | 1M | 606.6 (cached 151.65) | 4852.8 | tools / vision / thinking / json |
| `gemini-3.1-flash-lite` | Gemini 3.1 Flash Lite | 1M | 40.44 (cached 10.11) | 161.76 | tools / vision / web_search / thinking / json |
| `gemini-3.1-pro-low` | Gemini 3.1 Pro | 2M | 606.6 (cached 151.65) | 4852.8 | tools / vision / web_search / thinking / json |
| `gemini-3.5-flash-low` | Gemini 3.5 Flash | 1M | 161.76 (cached 40.44) | 1213.2 | tools / vision / web_search / thinking / json |
| `gemini-3.6-flash` | Gemini 3.6 Flash | 1M | 303.3 (cached 30.33) | 1516.5 | tools / vision / web_search / thinking / json |
| `gemini-3.7-flash` | Gemini 3.7 Flash | 1M | 303.3 (cached 30.33) | 1516.5 | tools / vision / web_search / thinking / json |
| `gemini-pro-agent` | Gemini Pro (Agent) | 2M | 606.6 (cached 151.65) | 4852.8 | tools / vision / web_search / thinking / json |

## xAI (10)

| Model ID | Name | Context | Input (积分/1M) | Output (积分/1M) | Capabilities |
|---|---|---|---|---|---|
| `grok-3-mini` | Grok 3 Mini | 131K | 121.32 (cached 30.33) | 202.2 | tools / web_search / thinking / json |
| `grok-3-mini-fast` | Grok 3 Mini Fast | 131K | 242.64 (cached 60.66) | 1617.6 | tools / web_search / thinking / json |
| `grok-4.20-0309-non-reasoning` | Grok 4.20 (Non-Reasoning) | 256K | 1213.2 (cached 194.11) | 6066 | tools / vision / web_search / json |
| `grok-4.20-0309-reasoning` | Grok 4.20 (Reasoning) | 256K | 1213.2 (cached 194.11) | 6066 | tools / vision / web_search / thinking / json |
| `grok-4.20-multi-agent-0309` | Grok 4.20 Multi-Agent | 256K | 2022 (cached 323.52) | 10110 | tools / vision / web_search / thinking / json |
| `grok-4.3` | Grok 4.3 | 256K | 1213.2 (cached 194.11) | 6066 | tools / vision / web_search / thinking / json |
| `grok-4.5` | Grok 4.5 | 500K | 808.8 (cached 121.32) | 2426.4 | tools / vision / web_search / thinking / json |
| `grok-4.6` | Grok 4.6 | 500K | 808.8 (cached 202.2) | 2426.4 | tools / vision / web_search / thinking / json |
| `grok-build-0.1` | Grok Build 0.1 | 256K | 1213.2 (cached 242.64) | 6066 | tools / thinking / json |
| `grok-composer-2.5-fast` | Grok Composer 2.5 Fast | 131K | 404.4 (cached 101.1) | 2022 | — |

## Zhipu GLM (8)

| Model ID | Name | Context | Input (积分/1M) | Output (积分/1M) | Capabilities |
|---|---|---|---|---|---|
| `glm-4.7` | GLM-4.7 | 200K | 283.08 (cached 70.77) | 283.08 | tools / thinking / json / open-source |
| `glm-5` | GLM-5 | 200K | 456.97 (cached 114.24) | 1593.34 | tools / thinking / json / open-source |
| `glm-5-turbo` | GLM-5-Turbo | 200K | 485.28 (cached 121.32) | 1617.6 | tools / json / open-source |
| `glm-5.1` | GLM-5.1 | 200K | 456.97 (cached 114.24) | 1593.34 | tools / thinking / json / open-source |
| `glm-5.2` | GLM-5.2 | 200K | 456.97 (cached 114.24) | 1593.34 | tools / thinking / json / open-source |
| `glm-5.3` | GLM-5.3 | 1M | 480 (cached 120) | 1680 | tools / thinking / json / open-source |
| `glm-5.3-flash` | GLM-5.3-Flash | 1M | 48 (cached 13.8) | 168 | tools / vision / thinking / json / open-source |
| `glm-5v-turbo` | GLM-5V-Turbo | 200K | 420 (cached 108) | 1560 | tools / vision / thinking / json / open-source |

## DeepSeek (7)

| Model ID | Name | Context | Input (积分/1M) | Output (积分/1M) | Capabilities |
|---|---|---|---|---|---|
| `deepseek-v3-0324` | DeepSeek V3 (0324) | 128K | 109.19 (cached 28.31) | 444.84 | tools / json / open-source |
| `deepseek-v3.1` | DeepSeek V3.1 | 128K | 109.19 (cached 28.31) | 444.84 | tools / json / open-source |
| `deepseek-v3.1-terminus` | DeepSeek V3.1 Terminus | 128K | 109.19 (cached 28.31) | 444.84 | tools / json / open-source |
| `deepseek-v3.2` | DeepSeek V3.2 | 64K | 109.19 (cached 28.31) | 444.84 | tools / json / open-source |
| `deepseek-v4-flash` | DeepSeek V4 Flash | 1M | 126.04 (cached 15.17) | 378.72 | tools / thinking / json |
| `deepseek-v4-pro` | DeepSeek V4 Pro | 128K | 378.05 (cached 50.55) | 1134.86 | tools / thinking / json |
| `deepseek-v4.1-flash` | DeepSeek V4.1 Flash | 1M | 120 (cached 2.4) | 480 | tools / vision / thinking / json / open-source |

## ByteDance Doubao (14)

| Model ID | Name | Context | Input (积分/1M) | Output (积分/1M) | Capabilities |
|---|---|---|---|---|---|
| `doubao-1-5-lite-32k-250115` | Doubao 1.5 Lite 32K | 32K | 18 (cached 3.6) | 36 | tools / json |
| `doubao-1-5-pro-32k-250115` | Doubao 1.5 Pro 32K | 32K | 48 (cached 9.6) | 120 | tools / json |
| `doubao-seed-1-6-250615` | Doubao Seed 1.6 | 256K | 48 (cached 9.6) | 480 | tools / vision / thinking / json |
| `doubao-seed-1-6-flash-250828` | Doubao Seed 1.6 Flash | 256K | 9 (cached 1.8) | 90 | tools / vision / thinking / json |
| `doubao-seed-1-6-vision` | Doubao Seed 1.6 Vision | 256K | 48 (cached 9.6) | 480 | tools / vision / thinking / json |
| `doubao-seed-1-8-251228` | Doubao Seed 1.8 | 256K | 48 (cached 9.6) | 480 | tools / vision / thinking / json |
| `doubao-seed-2-0-code-preview-260215` | Doubao Seed 2.0 Code Preview | 256K | 182.38 (cached 36.4) | 911.52 | tools / vision / thinking / json |
| `doubao-seed-2-0-lite-260215` | Doubao Seed 2.0 Lite | 128K | 34.37 (cached 6.87) | 205.03 | tools / vision / json |
| `doubao-seed-2-0-lite-260428` | Doubao Seed 2.0 Lite (04-28) | 128K | 34.37 (cached 6.87) | 205.03 | tools / vision / json |
| `doubao-seed-2-0-mini-260215` | Doubao Seed 2.0 Mini | 64K | 11.73 (cached 2.43) | 114.04 | tools / vision / json |
| `doubao-seed-2-0-mini-260428` | Doubao Seed 2.0 Mini (04-28) | 64K | 11.73 (cached 2.43) | 114.04 | tools / vision / json |
| `doubao-seed-2-0-pro-260215` | Doubao Seed 2.0 Pro | 256K | 182.38 (cached 36.4) | 911.52 | tools / vision / thinking / json |
| `doubao-seed-2-1-pro-260628` | Doubao Seed 2.1 Pro | 256K | 360 (cached 72) | 1800 | tools / vision / thinking / json |
| `doubao-seed-2-1-turbo-260628` | Doubao Seed 2.1 Turbo | 256K | 180 (cached 36) | 900 | tools / vision / thinking / json |

## Tencent Hunyuan (4)

| Model ID | Name | Context | Input (积分/1M) | Output (积分/1M) | Capabilities |
|---|---|---|---|---|---|
| `hunyuan-2.0-instruct-20251111` | Tencent Hunyuan 2.0 Instruct | 144K | 202.2 | 808.8 | tools / json |
| `hunyuan-2.0-thinking-20251109` | Tencent Hunyuan 2.0 Thinking | 192K | 202.2 | 808.8 | tools / thinking / json |
| `hunyuan-role-latest` | Tencent Hunyuan Role | 32K | 109.19 | 444.84 | tools / json |
| `hy3` | 腾讯混元 Hy3 | 256K | 72 (cached 24) | 240 | tools / json / open-source |

## Moonshot Kimi (4)

| Model ID | Name | Context | Input (积分/1M) | Output (积分/1M) | Capabilities |
|---|---|---|---|---|---|
| `kimi-k2.5` | Kimi K2.5 | 256K | 242.64 (cached 40.44) | 1011 | tools / thinking / json / open-source |
| `kimi-k2.6` | Kimi K2.6 | 256K | 242.64 (cached 40.44) | 1011 | tools / thinking / json / open-source |
| `kimi-k2.7-code` | Kimi K2.7 Code | 256K | 242.64 (cached 40.44) | 1011 | tools / thinking / json / open-source |
| `kimi-k3` | Kimi K3 | 256K | 960 (cached 227.83) | 4800 | tools / thinking / json / open-source |

## MiniMax (3)

| Model ID | Name | Context | Input (积分/1M) | Output (积分/1M) | Capabilities |
|---|---|---|---|---|---|
| `MiniMax-M2.5` | MiniMax M2.5 | 200K | 121.32 (cached 24.26) | 606.6 | tools / json |
| `MiniMax-M2.7` | MiniMax M2.7 | 200K | 121.32 (cached 24.26) | 606.6 | tools / json |
| `MiniMax-M3` | MiniMax M3 | 200K | 108.41 (cached 36.02) | 433.62 | tools / json |

## Alibaba Qwen (26)

| Model ID | Name | Context | Input (积分/1M) | Output (积分/1M) | Capabilities |
|---|---|---|---|---|---|
| `qwen-flash` | Qwen Flash | 1M | 9 (cached 1.8) | 90 | tools / json |
| `qwen-long` | Qwen Long | 10M | 30 (cached 6) | 120 | json |
| `qwen-mt-turbo` | Qwen MT Turbo | 16K | 42 (cached 8.4) | 117 | json |
| `qwen-plus` | Qwen Plus | 1M | 48 (cached 9.6) | 480 | tools / json |
| `qwen3-coder-plus` | Qwen3 Coder Plus | 1M | 240 (cached 48) | 960 | tools / json |
| `qwen3-max` | Qwen3-Max | 256K | 150 (cached 30) | 600 | tools / json |
| `qwen3-max-preview` | Qwen3-Max Preview | 256K | 360 (cached 72) | 1440 | tools / json |
| `qwen3-omni-flash` | Qwen3 Omni Flash | 64K | 108 (cached 21.6) | 762 | tools / vision / json |
| `qwen3-vl-flash` | Qwen3-VL Flash | 256K | 9 (cached 1.8) | 90 | tools / vision / json |
| `qwen3-vl-plus` | Qwen3-VL Plus | 256K | 60 (cached 12) | 600 | tools / vision / json |
| `qwen3.5-122b-a10b` | Qwen3.5-122B-A10B | 128K | 48 (cached 9.6) | 384 | tools / thinking / json / open-source |
| `qwen3.5-27b` | Qwen3.5-27B | 128K | 36 (cached 7.2) | 288 | tools / thinking / json / open-source |
| `qwen3.5-35b-a3b` | Qwen3.5-35B-A3B | 128K | 24 (cached 4.8) | 192 | tools / thinking / json / open-source |
| `qwen3.5-397b-a17b` | Qwen3.5-397B-A17B | 128K | 72 (cached 14.4) | 432 | tools / thinking / json / open-source |
| `qwen3.5-flash` | Qwen3.5-Flash | 1M | 12 (cached 2.4) | 120 | tools / thinking / json |
| `qwen3.5-plus` | Qwen3.5-Plus | 1M | 48 (cached 9.6) | 288 | tools / thinking / json |
| `qwen3.6-27b` | Qwen3.6-27B | 256K | 180 (cached 36) | 1080 | tools / thinking / json / open-source |
| `qwen3.6-35b-a3b` | Qwen3.6-35B-A3B | 256K | 108 (cached 21.6) | 648 | tools / thinking / json / open-source |
| `qwen3.6-flash` | Qwen3.6-Flash | 1M | 72 (cached 14.4) | 432 | tools / thinking / json |
| `qwen3.6-max-preview` | Qwen3.6-Max Preview | 256K | 540 (cached 108) | 3240 | tools / thinking / json |
| `qwen3.6-plus` | Qwen3.6-Plus | 1M | 120 (cached 24) | 720 | tools / thinking / json |
| `qwen3.7-flash` | Qwen3.7-Flash | 1M | 12 (cached 2.4) | 48 | tools / thinking / json |
| `qwen3.7-max` | Qwen3.7-Max | 1M | 720 (cached 144) | 2160 | tools / thinking / json |
| `qwen3.7-plus` | Qwen3.7-Plus | 1M | 120 (cached 24) | 480 | tools / thinking / json |
| `qwen3.8-27b` | Qwen3.8-27B | 1M | 180 (cached 36) | 720 | tools / thinking / json / open-source |
| `qwen3.8-max` | Qwen3.8-Max | 1M | 683.48 (cached 85.43) | 2050.47 | tools / thinking / json |

## Xiaomi MiMo (1)

| Model ID | Name | Context | Input (积分/1M) | Output (积分/1M) | Capabilities |
|---|---|---|---|---|---|
| `mimo-v2.5-pro` | MiMo V2.5 Pro | 1M | 175.91 (cached 1.46) | 351.83 | tools / thinking / json / open-source |

## Image generation models (25)

Billed **per image** through `POST /v1/images/generations`. See [Image / video APIs](./media-apis.md).

### ByteDance Seedream / Seedance / Dreamina

| Model ID | Name | Price |
|---|---|---|
| `doubao-seedream-4-0-250828` | Seedream 4.0 | 11.73/image |
| `doubao-seedream-4-5-251128` | Seedream 4.5 | 14.96/image |
| `doubao-seedream-5-0-260128` | Seedream 5.0 | 12.94/image |
| `doubao-seedream-5-0-pro-260628` | Seedream 5.0 Pro | 17.79/image ≤ 2.36 MP, 35.59 above plus 1.21 per input reference image |
| `tvod-seedream-4.5` | Seedream 4.5 (X3) | 16.18/image |
| `tvod-seedream-5.0-lite` | Seedream 5.0 Lite (X3) | 16.18/image |

### Google

| Model ID | Name | Price |
|---|---|---|
| `nano-banana` | Nano Banana | 15.77/image |
| `nano-banana-2` | Nano Banana 2 | 16.18/image |
| `nano-banana-pro` | Nano Banana Pro | 54.19/image |

### OpenAI

| Model ID | Name | Price |
|---|---|---|
| `gpt-image-2` | GPT-Image 2 | 23.86/image |
| `gpt-image-2.5-flare` | GPT-Image 2.5 Flare | 12/image |
| `gpt-image-2.5-sunburst` | GPT-Image 2.5 Sunburst | 12/image |

### xAI Grok

| Model ID | Name | Price |
|---|---|---|
| `grok-imagine-image` | Grok Imagine (Image) | 28.31/image |
| `grok-imagine-image-quality` | Grok Imagine (Image · Quality) | 28.31/image |

### Midjourney

| Model ID | Name | Price |
|---|---|---|
| `tvod-midjourney-v7` | Midjourney v7 | 32.35/image |
| `tvod-midjourney-v8.1` | Midjourney v8.1 | 40.44/image |

### Kuaishou Kling

| Model ID | Name | Price |
|---|---|---|
| `tvod-kling-expand` | Kling Outpainting | 20.22/image |
| `tvod-kling-image-2.1` | Kling Image 2.1 | 12.13/image |
| `tvod-kling-image-3.0` | Kling Image 3.0 | 20.22/image |
| `tvod-kling-image-3.0-omni` | Kling Image 3.0 Omni | 24.26/image |

### Shengshu Vidu

| Model ID | Name | Price |
|---|---|---|
| `tvod-vidu-image` | Vidu Image | 20.22/image |

### Tencent Hunyuan

| Model ID | Name | Price |
|---|---|---|
| `tvod-hunyuan-panorama` | Hunyuan 360 panorama | 283.08/image |

### Alibaba Qwen

| Model ID | Name | Price |
|---|---|---|
| `tvod-qwen-image` | Qwen Image | 16.18/image |
| `qwen-image-3.0` | Qwen Image 3.0 | 10.8/image |
| `qwen-image-3.0-pro` | Qwen Image 3.0 Pro | 1K 15 / 2K 30 per image |

> `gpt-image-2`, `gpt-image-2.5-flare` and `gpt-image-2.5-sunburst` all accept `POST /v1/images/edits` for reference-image edits (sketch-to-image works the same way). **The upstream ignores `size`** — put the aspect ratio in the prompt; latency is 30–215s.
>
> **The two Midjourney entries are priced per image, but one request always produces 4 of them (a 2×2 grid) and `n` does not change that** — a single request costs `161.76` (v8.1) / `129.41` (v7) credits. `size` only sets the aspect ratio, never exact pixels; the output tier goes at the end of the prompt (`--sd` / `--hd`). Integration details in [Image / video APIs](./media-apis.md#post-v1imagesgenerations).
>
> Since 2026-07-08 the three nano entries are the only way in: older ids (`gemini-2.5-flash-image`, `gemini-3-pro-image-preview`, `gemini-3.1-flash-image(-preview)`, `tvod-nano-*`) keep working as aliases onto the canonical entries above.

## Video generation models (70)

Billed **per second** as an async task through `POST /v1/videos/generations`. Where tiers are listed (resolution, or operation for the subtitle SKU) you are billed at the tier you request. See [Image / video APIs](./media-apis.md).

### ByteDance Seedream / Seedance / Dreamina

| Model ID | Name | Price |
|---|---|---|
| `doubao-seedance-2.0` | Seedance 2.0 | 480p 27.72144 / 720p 59.616 / 1080p 148.716 per second; token rate by delivery tier: 480p 2760/1M (no video input) 1680/1M (with video input), 720p 2760/1M (no video input) 1680/1M (with video input), 1080p 3060/1M (no video input) 1860/1M (with video input) |
| `doubao-seedance-2.0-fast` | Seedance 2.0 Fast | 480p 22.29768 / 720p 47.952 / 1080p 107.892 per second; token rate by delivery tier: 480p 2220/1M (no video input) 1320/1M (with video input), 720p 2220/1M (no video input) 1320/1M (with video input), 1080p 2220/1M (no video input) 1320/1M (with video input) |
| `doubao-seedance-2.0-fast-lite` | Seedance 2.0 Fast Lite | 720p 47.952 / 1080p 107.892 per second; billed by token = **token rate x tokens + upscale rate x delivered seconds**. Token rate 720p 4525.29/1M (no video input) 2690.71/1M (with video input), 1080p 4763.52/1M (no video input) 2832.36/1M (with video input). Upscale add-on: 720p 2.5/s, 1080p 5/s (charged on **delivered** seconds only, never on the reference video) |
| `doubao-seedance-2.0-lite` | Seedance 2.0 Lite | 720p 59.616 / 1080p 148.716 per second; billed by token = **token rate x tokens + upscale rate x delivered seconds**. Token rate 720p 5686.58/1M (no video input) 3461.4/1M (with video input), 1080p 6653.52/1M (no video input) 4049.97/1M (with video input). Upscale add-on: 720p 2.5/s, 1080p 5/s (charged on **delivered** seconds only, never on the reference video) |
| `doubao-seedance-2.0-mini` | Seedance 2.0 Mini | 480p 13.86072 / 720p 29.808 per second; token rate by delivery tier: 480p 1380/1M (no video input) 840/1M (with video input), 720p 1380/1M (no video input) 840/1M (with video input) |
| `doubao-seedance-2.0-mini-lite` | Seedance 2.0 Mini Lite | 720p 29.808 / 1080p 74.358 per second; billed by token = **token rate x tokens + upscale rate x delivered seconds**. Token rate 720p 2718.84/1M (no video input) 1654.95/1M (with video input), 1080p 3211.02/1M (no video input) 1954.53/1M (with video input). Upscale add-on: 720p 2.5/s, 1080p 5/s (charged on **delivered** seconds only, never on the reference video) |
| `doubao-seedance-2.5` | Seedance 2.5 | 480p 40.3515 / 720p 90.72 / 1080p 224.532 per second; token rate by delivery tier: 4200/1M (no video input), 2520/1M (with video input); the **1080p tier** bills 4620/1M and 2760/1M |
| `doubao-seedance-2.5-lite` | Seedance 2.5 Lite | 720p 42.8515 / 1080p 95.72 per second; billed by token = **token rate x tokens + upscale rate x delivered seconds**. Token rate 4200/1M (no video input), 2520/1M (with video input). Upscale add-on: 720p 2.5/s, 1080p 5/s (charged on **delivered** seconds only, never on the reference video) |
| `tvod-jimeng-1.0-lite-i2v` | Dreamina 1.0 Lite (image-to-video) | 720p 18.2 / 1080p 28.31 per second |
| `tvod-jimeng-1.0-pro` | Dreamina 1.0 Pro | 720p 18.2 / 1080p 28.31 per second |
| `tvod-jimeng-1.0-pro-fast` | Dreamina 1.0 Pro Fast | 720p 18.2 / 1080p 28.31 per second |
| `tvod-jimeng-1.5-pro` | Dreamina 1.5 Pro | 720p 18.2 / 1080p 28.31 per second |
| `tvod-jimeng-3.0` | Dreamina 3.0 | 720p 18.2 / 1080p 28.31 per second |
| `tvod-jimeng-3.0-pro` | Dreamina 3.0 Pro | 720p 18.2 / 1080p 28.31 per second |
| `tvod-jimeng-4.0` | Dreamina 4.0 | 720p 18.2 / 1080p 28.31 per second |

### Alibaba Wan

| Model ID | Name | Price |
|---|---|---|
| `wan2.7-t2v` | Wan 2.7 text-to-video | 720p 36 / 1080p 60 per second |
| `wan3.0-video` | Wan 3.0 video | 480p 18 / 720p 36 / 1080p 72 per second |
| `wan3.0-video-prime` | Wan 3.0 video Prime | 480p 27 / 720p 54 / 1080p 108 per second |

> Both Wan 3.0 cards share one capability set: 2-30s, 480P/720P/1080P, 30fps, aspect `16:9 / 4:3 / 1:1 / 3:4 / 9:16 / adaptive`; text-to-video, image-to-video (first frame, first+last frame), and image / video / audio references. **Prime is the accelerated tier** (same quality, markedly faster) at 1.5x the standard rate. **The default delivery is 1080P** — pass `resolution` explicitly for a cheaper tier.

> ⚠️ **On rounds that carry a reference video, the input video's seconds are billed too.** This is the upstream's own basis: billed duration = input duration + output duration, and the rate above applies to both legs (upstream's price table heads that column "input and output unit price"). Reference videos are `[1,15]`s each and 15s total; we hold against that ceiling at submit time and refund the difference once upstream reports the real input duration. Reconcile against the top-level `input_video_duration_sec` in the response (`duration_sec` still means the delivered clip only, excluding the input). **Text-to-video and image-to-video rounds are unaffected** (image input is free upstream, and we don't charge for it either). See [Media APIs - how `usage` relates to billing](./media-apis.en.md#how-usage-relates-to-billing).

### Google

| Model ID | Name | Price |
|---|---|---|
| `tvod-veo-3.1` | Veo 3.1 | 720p 24.26 / 1080p 40.44 / 4k 121.32 per second |
| `tvod-veo-3.1-fast` | Veo 3.1 Fast | 720p 16.18 / 1080p 28.31 per second |
| `tvod-veo-3.1-lite` | Veo 3.1 Lite | 720p 16.18 / 1080p 28.31 per second |

### OpenAI

| Model ID | Name | Price |
|---|---|---|
| `tvod-sora-2` | Sora 2 | 720p 60.66 / 1080p 101.1 per second |

### xAI Grok

| Model ID | Name | Price |
|---|---|---|
| `grok-imagine-video` | Grok Imagine Video | 283.08/second |
| `grok-imagine-video-1.5-preview` | Grok Imagine Video 1.5 | 586.38/second |

### Kuaishou Kling

| Model ID | Name | Price |
|---|---|---|
| `tvod-kling-video-1.6` | Kling 1.6 | 720p 16.18 / 1080p 24.26 per second |
| `tvod-kling-video-2.0` | Kling 2.0 | 720p 16.18 / 1080p 24.26 per second |
| `tvod-kling-video-2.1` | Kling 2.1 | 720p 16.18 / 1080p 24.26 per second |
| `tvod-kling-video-2.5-turbo` | Kling 2.5 Turbo | 720p 12.13 / 1080p 20.22 per second |
| `tvod-kling-video-2.6` | Kling 2.6 | 720p 16.18 / 1080p 24.26 per second |
| `tvod-kling-video-3.0` | Kling 3.0 | 720p 20.22 / 1080p 32.35 / 4k 97.06 per second |
| `tvod-kling-video-3.0-omni` | Kling 3.0 Omni | 720p 20.22 / 1080p 32.35 / 4k 97.06 per second |
| `tvod-kling-video-master` | Kling 2.1 Master | 720p 32.35 / 1080p 48.53 per second |
| `tvod-kling-video-o1` | Kling O1 | 720p 12.13 / 1080p 20.22 per second |

### MiniMax Hailuo

| Model ID | Name | Price |
|---|---|---|
| `tvod-hailuo-02` | Hailuo 02 | 720p 16.18 / 1080p 24.26 per second |
| `tvod-hailuo-2.3` | Hailuo 2.3 | 720p 16.18 / 1080p 24.26 per second |
| `tvod-hailuo-2.3-fast` | Hailuo 2.3 Fast | 720p 16.18 / 1080p 24.26 per second |
| `tvod-hailuo-h3` | Hailuo H3 | 2k 45.7 / 4k 136.69 per second |

### Shengshu Vidu

| Model ID | Name | Price |
|---|---|---|
| `tvod-vidu-video-2.0` | Vidu 2.0 | 720p 16.18 / 1080p 24.26 per second |
| `tvod-vidu-video-q1` | Vidu Q1 | 720p 16.18 / 1080p 24.26 per second |
| `tvod-vidu-video-q1-classic` | Vidu Q1 Classic | 720p 16.18 / 1080p 24.26 per second |
| `tvod-vidu-video-q2` | Vidu Q2 | 720p 16.18 / 1080p 24.26 per second |
| `tvod-vidu-video-q2-pro` | Vidu Q2 Pro | 720p 16.18 / 1080p 24.26 per second |
| `tvod-vidu-video-q2-pro-fast` | Vidu Q2 Pro Fast | 720p 16.18 / 1080p 24.26 per second |
| `tvod-vidu-video-q2-turbo` | Vidu Q2 Turbo | 720p 16.18 / 1080p 24.26 per second |
| `tvod-vidu-video-q3` | Vidu Q3 | 720p 18.2 / 1080p 28.31 / 4k 80.88 per second |
| `tvod-vidu-video-q3-ad` | Vidu Q3 Ads | 720p 18.2 / 1080p 28.31 / 4k 80.88 per second |
| `tvod-vidu-video-q3-drama` | Vidu Q3 Drama | 720p 18.2 / 1080p 28.31 / 4k 80.88 per second |
| `tvod-vidu-video-q3-pro` | Vidu Q3 Pro | 720p 18.2 / 1080p 28.31 / 4k 80.88 per second |
| `tvod-vidu-video-q3-turbo` | Vidu Q3 Turbo | 720p 18.2 / 1080p 28.31 per second |

### Tencent Hunyuan

| Model ID | Name | Price |
|---|---|---|
| `tvod-hunyuan-video-1.0` | Hunyuan Video 1.0 | 720p 20.22 / 1080p 32.35 / 4k 97.06 per second |
| `tvod-hunyuan-video-1.1` | Hunyuan Video 1.1 | 720p 20.22 / 1080p 32.35 / 4k 97.06 per second |

### PixVerse

| Model ID | Name | Price |
|---|---|---|
| `tvod-pixverse-c1` | PixVerse C1 | 720p 20.22 / 1080p 24.26 per second |
| `tvod-pixverse-v5.6` | PixVerse V5.6 | 720p 20.22 / 1080p 20.22 per second |
| `tvod-pixverse-v6` | PixVerse V6 | 720p 20.22 / 1080p 20.22 / 4k 46.51 per second |

### Happyhorse

| Model ID | Name | Price |
|---|---|---|
| `happyhorse-1.0-i2v` | Happyhorse 1.0 image-to-video | 720p 52.57 / 1080p 88.97 per second |
| `happyhorse-1.0-r2v` | Happyhorse 1.0 omni-reference | 720p 52.57 / 1080p 88.97 per second |
| `happyhorse-1.0-t2v` | Happyhorse 1.0 text-to-video | 720p 52.57 / 1080p 88.97 per second |
| `happyhorse-1.0-video-edit` | Happyhorse 1.0 video edit | 720p 52.57 / 1080p 88.97 per second |
| `happyhorse-1.1-i2v` | Happyhorse 1.1 image-to-video | 720p 54 / 1080p 72 per second |
| `happyhorse-1.1-r2v` | Happyhorse 1.1 omni-reference | 720p 54 / 1080p 72 per second |
| `happyhorse-1.1-t2v` | Happyhorse 1.1 text-to-video | 720p 54 / 1080p 72 per second |

### Digital human / smart clip

| Model ID | Name | Price |
|---|---|---|
| `clip-mixcut` | Smart clip · B-roll mixcut | 4.04/second |
| `clip-news` | Smart clip · news brief | 2.43/second |
| `clip-realman` | Smart clip · real-person VO | 4.04/second |
| `dh-avatar` | Digital-human video | 3.76/second |
| `dh-lipsync` | Digital human lip sync · fast | 4.04/second |
| `dh-lipsync-max` | Digital human lip sync · master | 12.13/second |
| `dh-lipsync-pro` | Digital human lip sync · HD | 8.09/second |
| `dh-motion` | Digital human · motion transfer | fast 4.04 / standard 8.09 / max 12.13 per second |

### Video processing (not generation)

| Model ID | Name | Price |
|---|---|---|
| `tvod-subtitle-soft` | Video subtitles · ASR + translation | asr 0.0607 / translate 0.0404 per second |

## Music / voice / avatar creation (8)

These have their own endpoints and billing units. Full request/response shapes: [Image / video / music APIs](./media-apis.md) and [Digital human APIs](./digital-human-apis.md).

| Model ID | Name | Price | Endpoint |
|---|---|---|---|
| `dh-avatar-create` | Create digital-human avatar | 210.29/avatar | `POST /v1/videos/generations` (avatar-creation task) |
| `suno-v3.5` | Suno V3.5 | 19.41/track | `POST /v1/music/generations` |
| `suno-v4` | Suno V4 | 19.41/track | `POST /v1/music/generations` |
| `suno-v4.5` | Suno V4.5 | 19.41/track | `POST /v1/music/generations` |
| `suno-v5` | Suno V5 | 19.41/track | `POST /v1/music/generations` |
| `suno-v5.5` | Suno V5.5 (latest) | 19.41/track | `POST /v1/music/generations` |
| `voice-clone-pro` | Voice clone · create a voice | 40.44/voice | `POST /v1/audio/voice-clone` |
| `voice-tts-pro` | Text to speech | 0.1254/character | `POST /v1/audio/speech` |

## Cross-vendor protocol support

Different models support different client SDKs, and **the [compatibility matrix](./compatibility-matrix.md) is authoritative on what is actually reachable**. The catalog's `supported_protocols` field reflects only the **native / primary path**; many models are additionally reachable on other protocols through gateway translation (the response then carries an `X-Protocol-Translation` header). Native paths, counted from the registry that generated this page:

- **OpenAI Chat** (`/v1/chat/completions`) — all 105 text models
- **Anthropic Messages** (`/v1/messages`) — 11 models: `claude-fable-5`, `claude-haiku-4-5-20251001`, `claude-opus-4-5-thinking`, `claude-opus-4-6`, `claude-opus-4-6-thinking`, `claude-opus-4-7`, `claude-opus-4-8`, `claude-opus-5`, `claude-sonnet-4-5-20250929`, `claude-sonnet-4-6`, `claude-sonnet-5`
- **OpenAI Responses** (`/v1/responses`) — 23 models: `claude-haiku-4-5-20251001`, `claude-opus-4-6`, `claude-opus-4-7`, `claude-opus-4-8`, `claude-sonnet-4-6`, `claude-sonnet-5`, `codex-auto-review`, `gpt-5.5`, `gpt-5.6-luna`, `gpt-5.6-sol`, `gpt-5.6-terra`, `gpt-6`, `gpt-6-astra`, `grok-3-mini`, `grok-3-mini-fast`, `grok-4.20-0309-non-reasoning`, `grok-4.20-0309-reasoning`, `grok-4.20-multi-agent-0309`, `grok-4.3`, `grok-4.5`, `grok-4.6`, `grok-build-0.1`, `grok-composer-2.5-fast`
- **Gemini Native** (`/v1beta/...`) — 9 models: `gemini-3-flash`, `gemini-3-flash-agent`, `gemini-3-pro`, `gemini-3.1-flash-lite`, `gemini-3.1-pro-low`, `gemini-3.5-flash-low`, `gemini-3.6-flash`, `gemini-3.7-flash`, `gemini-pro-agent`

For a model × protocol combination with no reachable channel, the gateway returns `503 no_channel_available` (the model exists but has no channel on that protocol — **not a 404**); switch to a supported protocol.

## Legacy ids (aliases)

134 older ids still resolve onto the canonical entries above, so integrations pinned to them keep working. An id that is neither in the tables above nor an alias returns `model_not_found` — the catalog endpoint is the source of truth.

## Live data

The model list and prices track upstream changes. For live data see [https://oem.dflop.top/models](https://oem.dflop.top/models) or the public catalog endpoint (no auth required):

```bash
curl https://oemoemapi.dflop.top/api/v1/models/public | jq .
```

The response looks like `{ "models": [...] }`. Note that this endpoint returns **every registered entry** — including placeholder SKUs that aren't live yet and non-chat SKUs — so filter on the three fields below when consuming it from a script rather than looping over the whole list:

| Field | Meaning |
|---|---|
| `callable` | `false` means a placeholder SKU (listed but not live); calling it returns `model_not_found` |
| `endpoint_type` | `null` means an ordinary chat model. `images_generations`, `videos_generations`, `contents_generations_tasks` and similar mean the model uses its own dedicated endpoint and cannot be sent to `/v1/chat/completions` — see [Image / video / music APIs](./media-apis.md) |
| `supported_protocols` | the client protocols available for this model (see above) |

To take only the models you can send straight to `/v1/chat/completions`:

```bash
curl -s https://oemoemapi.dflop.top/api/v1/models/public \
  | jq -r '.models[] | select(.callable and (.supported_protocols | index("openai_chat"))) | .id'
```