a
Intelligent Multi-Channel Routing
One model configured with multiple backend channels. Automatically selects the optimal channel to reduce costs and improve stability.
Learn moreLive142 models · 14 providers
The ultimate AI media API.
One endpoint for Seedance, Veo, Nano Banana, GPT Image and the rest of the top image and video models — with GPT, Claude and Gemini supported too. Better prices than going direct. Pay as you go, no subscription.
api.apipod.ai/v1route · weighted routing
- Models, one endpoint
- 142
- Model providers
- 14
- Curated prompts
- 1,243
- SDK formats supported
- 3
One gateway for every major model provider
01/Models
View All ModelsThe image, video and language models teams ship with
The newest image and video models alongside frontier LLMs — all on one key.
02/Platform
Built like infrastructure. Billed like a utility.
More than a proxy: every request is routed, protected, observed and metered.
b
Circuit Breaker Protection
Real-time health monitoring with automatic fault isolation. Auto circuit-break for 30 seconds after 3 consecutive failures, preventing cascading failures and ensuring business continuity.
Learn morec
Observability Platform
Real-time request logs, token usage stats, cost analysis dashboards. Complete monitoring metrics help optimize AI app performance and costs.
Learn mored
Flexible Billing System
Supports per-token, per-request, per-duration billing. Tiered pricing and custom strategies meet needs from startups to enterprises.
Learn moreBuilt for
Autonomous AI Agents
Chain multiple models (GPT-5.4, Claude 4.6) to build agents that can reason, code, and execute tasks autonomously.
Automated Content Production
Generate blog posts, marketing copies, and social media images in bulk using a single API call pipeline.
Enterprise AI Gateway
Centralize all your AI traffic through one gateway to enforce compliance, logging, and spend management.
03/Developers
A few lines of code.AI image and video, in your product.
Image and video share one async flow — submit a task, poll for the result — while LLMs work with the OpenAI SDK as-is. One key, one auth and billing layer, and copy-paste examples for Node, Python and cURL.
- 1Create an API key
- 2Submit a generation task, get a task_id
- 3Poll the status, fetch your image or video URL
- const API = "https://api.apipod.ai/v1";
- const headers = {
- Authorization: "Bearer " + process.env.API_KEY,
- "Content-Type": "application/json",
- };
- // 1. Submit the generation task
- const { data } = await fetch(API + "/videos/generations", {
- method: "POST",
- headers,
- body: JSON.stringify({
- model: "seedance-2.5-t2v",
- prompt: "30-second cinematic aerial action spectacle: a battleship cuts through storm waves as a fighter jet bursts from volumetric clouds",
- aspect_ratio: "16:9",
- duration: 30,
- }),
- }).then((r) => r.json());
- // 2. Poll until the task completes
- let task;
- do {
- await new Promise((r) => setTimeout(r, 3000));
- const res = await fetch(API + "/videos/status/" + data.task_id, { headers });
- task = (await res.json()).data;
- } while (!["completed", "failed"].includes(task.status));
- console.log(task.result[0]); // → output URL
200 OKtask_id=vid_7f3a9ccompletedseedance-2.5-t2v
04/Seedance
Seedance promptsSeedance: cinematic AI video, built into your product
ByteDance's Seedance family: up to 30-second multi-shot stories, native synced audio, and image, video and audio references. Every 2.5 and 2.0 edition is live — official, discounted or special-price, to fit your budget.
Seedance 2.5 is live
30 seconds of audio-synced storytelling
Seedance 2.5 generates up to 30 seconds per run with native synced audio, taking up to 30 images + 10 videos + 10 audios as references. The selection guide helps you decide between 2.5 and 2.0 for your scenario.
- Up to 30s multi-shot storytelling with native audio-video sync
- All-modal references: 30 images + 10 videos + 10 audios
- 480P/720P on discount routes, 720P on special-offer routes
Seedance 2.0 — all versions live
One model, three versions, your call
The official edition at 8.8–9% off by default, the 720P deal from ~40% off, plus the per-request X ultra-low-price routes. The edition guide picks the right fit in 30 seconds.
- Up to 4K 10-bit output with 4–15s multi-shot storytelling
- All-modal references: 9 images + 3 videos + 3 audios
- Native stereo audio generated in sync with the picture
05/Prompts
1,243
Battle-Tested Prompts for Every Model
1,243 curated prompt examples across 7 models — video, image and more. Copy, adapt, and generate in seconds.
Technical Animation Of A Levitating Exploding Vintage Television
The vintage orange television slowly lifts off the table and levitates into the air. As it rises, the outer casing smoothly peels away and separates into multiple floating panels, revealing the intricate internal circuit
Seedance 2.0
Rainbow Lorikeet Home Video Prompt For Seedance 2 0
A vibrant rainbow lorikeet parrot with glossy black head, bright orange beak, vivid red-orange chest, emerald green wings and back, and long yellow-green tail feathers perched confidently on a soft gray knitted blanket…
Seedance 2.0
15 Second Multi Scene Video Prompt For A Sacred Eastern Realm
15 seconds, theme of a sacred Eastern realm, solemn and peaceful, magnificent and holy, cinematic lighting, ultra-clear details, volumetric light, glazed material, golden particles, lotus elements, transparent and pure,…
Seedance 2.0
Seedance 2 0 Transformation Prompt 10 World Female Armors
Core visual prompt @94d74b42-17ec-45d3-ab60-487c3a1700cb: Complete 10 sets of world female armor transformations in 12 seconds, without wearing glasses throughout, full armor set with helmet + weapon, pure female…
Seedance 2.0
Sci Fi Soldier Transformation Vfx
Cinematic VFX sci-fi transformation shot on Arri Alexa Mini LF with a low-angle steady-cam orbit. The scene features a rugged American soldier standing in a dusty desert hangar; as he activates a wrist-mounted neural tri
Seedance 2.0
Shattering And Reforming Smartphone Sequence
Prompt 1: Dynamic movement, a smart phone drops from the sky and falls onto the city street, shattering into individual pieces, each part shown specifically in slow motion, camera orbits it. Prompt 2: Continue this video
Seedance 2.0
06/Pricing
View full pricingTransparent pricing for every model
Pay as you go, no subscription. Scroll to explore live rates for all models.
| Model | Provider | Category | Pricing |
|---|---|---|---|
| GPT 5.6 Sol gpt-5.6-sol |  | llm | BaseTiered · 2 tiers · Input ≤ 272K Input$5/1M Output$30/1M Cache-R$0.5/1M Cache-W$6.25/1M Channel discounts OPENAI×0.80 Azure×0.60 Codex×0.40 |
| Claude Fable 5 claude-fable-5 |  | llm | Base Input$10/1M Output$50/1M Cache-R$1/1M Cache-W 5m$12.5/1M Cache-W 1h$20/1M Channel discounts Anthropic×0.80 Claude Lite×0.10 Claude Max×0.30 Claude Mix×0.60 |
| GPT Image 2.5 Flare Lite gpt-image-2.5-flare-lite | | text_to_imageimage_to_image | Quality 1K · Resolution 1K$0.02/request Quality 1K · Resolution 2K$0.04/request Quality 1K · Resolution 4K$0.08/request |
| GPT Image 2.5 Sunburst Lite gpt-image-2.5-sunburst-lite | | text_to_imageimage_to_image | Quality 1K · Resolution 1K$0.03/request Quality 1K · Resolution 2K$0.06/request Quality 1K · Resolution 4K$0.12/request |
| Kimi K3 kimi-k3 |  | llm | Base Input$3/1M Output$15/1M Cache-R$0.3/1M Channel discounts Kimi×0.70 |
| Wan 3.0 Pro Spicy T2V wan3.0-pro-spicy-t2v |  | text_to_video | Resolution 2K$0.24/sec Resolution 2k$0.24/sec Resolution 4K$0.3/sec |
| Wan 3.0 Pro Spicy I2V wan3.0-pro-spicy-i2v | | image_to_video | Resolution 2K$0.24/sec Resolution 2k$0.24/sec Resolution 4K$0.3/sec |
| Wan 3.0 Pro Spicy R2V wan3.0-pro-spicy-r2v | | image_to_videovideo_to_video | Resolution 2K$0.24/sec Resolution 2k$0.24/sec Resolution 4K$0.3/sec |
| Wan 3.0 Spicy T2V wan3.0-spicy-t2v | | text_to_video | Resolution 480P$0.06/sec Resolution 480p$0.06/sec Resolution 720P$0.12/sec |
| Wan 3.0 Spicy I2V wan3.0-spicy-i2v | | image_to_video | Resolution 480P$0.06/sec Resolution 480p$0.06/sec Resolution 720P$0.12/sec |
| Wan 3.0 Spicy R2V wan3.0-spicy-r2v | | image_to_videovideo_to_video | Resolution 480P$0.06/sec Resolution 480p$0.06/sec Resolution 720P$0.12/sec |
| Seedance 2.5 X Text to Video seedance-2.5-x-t2v |  | text_to_video | $0.1/sec |
| Seedance 2.5 X Reference to Video seedance-2.5-x-r2v | | image_to_videovideo_to_video | $0.1/sec |
| Seedance 2.0 X Text to Video seedance-2.0-x-t2v | | text_to_video | $0.7/request |
| Seedance 2.0 X Reference to Video seedance-2.0-x-r2v | | image_to_videovideo_to_video | $0.7/request |
| Nano Banana 2.1 nano-banana-2.1 |  | text_to_imageimage_to_image | Quality 1K$0.02/request Quality 2K$0.04/request Quality 4K$0.05/request |
| Seedream 5.0 Pro Layer seedream-5.0-pro-layer | | image_to_image | Quality 1K$0.035/request Quality 2K$0.07/request Quality 1.5K$0.035/request |
| Seedream 5.0 Flash seedream-5.0-flash | | text_to_image | $0.018/request |
| Seedream 5.0 Flash Edit seedream-5.0-flash-edit | | image_to_image | $0.018/request |
| Seedream 5.0 Flash Layer seedream-5.0-flash-layer | | image_to_image | $0.018/request |
| Seedream 5.0 Pro seedream-5.0-pro | | text_to_image | Quality 1K$0.035/request Quality 2K$0.07/request Quality 1.5K$0.035/request |
| Seedream 5.0 Pro Edit seedream-5.0-pro-edit | | image_to_image | Quality 1K$0.035/request Quality 2K$0.07/request Quality 1.5K$0.035/request |
| Seedance 2.5 Draft seedance-2.5-draft | | image_to_videovideo_to_video | Resolution 480p · No reference video$0.098/sec Resolution 480p · With reference video$0.0588/sec Resolution 720p · No reference video$0.2205/sec |
| Claude Sonnet 5.5 claude-sonnet-5-5 | | llm | Base Input$2/1M Output$10/1M Cache-R$0.2/1M Cache-W 5m$2.5/1M Cache-W 1h$4/1M Channel discounts Claude Max×0.30 |
| GPT Image 2 1K gpt-image-2-1k | | text_to_imageimage_to_image | $0.007/request |
| Claude Opus 5.5 claude-opus-5-5 | | llm | Base Input$4/1M Output$20/1M Cache-R$0.2/1M Cache-W 5m$5/1M Cache-W 1h$8/1M Channel discounts Claude Max×0.30 |
| DeepSeek Flash deepseek-flash |  | llm | Base Input$0.3/1M Output$1.2/1M Cache-R$0.03/1M Channel discounts DeepSeek×0.50 |
| Gemini Omni Flash 1.1 Text to Video gemini-omni-flash-1.1-t2v | | text_to_video | Resolution 4k$0.12/sec Resolution 360p$0.06/sec Resolution 720p$0.06/sec |
| Gemini Omni Flash 1.1 Image to Video gemini-omni-flash-1.1-i2v | | image_to_video | Resolution 4k$0.12/sec Resolution 360p$0.06/sec Resolution 720p$0.06/sec |
| Gemini Omni Flash 1.1 Reference to Video gemini-omni-flash-1.1-r2v | | image_to_video | Resolution 4k · No reference video$0.12/sec Resolution 4k · With reference video$0.072/sec Resolution 480p · No reference video$0.06/sec |
| Gemini Omni Flash 1.1 Video Extend gemini-omni-flash-1.1-extend | | video_to_video | Resolution 4k$1.2/request Resolution 360p$0.8/request Resolution 720p$0.8/request |
| GPT Image 2.5 Sunburst gpt-image-2.5-sunburst | | text_to_imageimage_to_image | Input$4/1M Output$24/1M |
| GPT Image 2.5 Flare gpt-image-2.5-flare | | text_to_imageimage_to_image | Input$4/1M Output$24/1M |
| Seedance 2.5 Video Edit seedance-2.5-edit | | video_to_video | Resolution 480p · No reference video$0.098/sec Resolution 480p · With reference video$0.0588/sec Resolution 720p · No reference video$0.2205/sec |
| Seedance 2.5 Video Extend seedance-2.5-extend | | video_to_video | Resolution 480p · No reference video$0.098/sec Resolution 480p · With reference video$0.0588/sec Resolution 720p · No reference video$0.2205/sec |
| GPT 6 Astra gpt-6-astra | | llm | BaseTiered · 2 tiers · Input ≤ 272K Input$10/1M Output$50/1M Cache-R$1/1M Cache-W$12.5/1M Channel discounts Codex×0.40 |
| Gemini 3.8 Flash gemini-3.8-flash | | llm | Base Input$1.5/1M Output$7.5/1M Cache-R$0.15/1M Channel discounts Google×0.40 |
| Nano Banana 2 Lite nano-banana-2-lite | | text_to_imageimage_to_image | $0.02/request |
| MiniMax H3 Max Text to Video minimax-h3-max-t2v |  | text_to_video | Resolution 480P$0.05/sec Resolution 480p$0.05/sec Resolution 768P$0.08/sec |
| MiniMax H3 Max Image to Video minimax-h3-max-i2v | | image_to_video | Resolution 480P$0.05/sec Resolution 480p$0.05/sec Resolution 768P$0.08/sec |
| WAN 3.0 Prime Text to Video wan3.0-prime-t2v | | text_to_video | Resolution 480P$0.06/sec Resolution 480p$0.06/sec Resolution 720P$0.12/sec |
| WAN 3.0 Prime Image to Video wan3.0-prime-i2v | | image_to_video | Resolution 480P$0.06/sec Resolution 480p$0.06/sec Resolution 720P$0.12/sec |
| WAN 3.0 Prime Reference to Video wan3.0-prime-r2v | | image_to_videovideo_to_video | Resolution 480P$0.06/sec Resolution 480p$0.06/sec Resolution 720P$0.12/sec |
| Seedance 2.5 Reference to Video(Lite) seedance-2.5-lite-r2v | | image_to_videovideo_to_video | Resolution 720p · No reference video$0.15/sec Resolution 720p · With reference video$0.09/sec |
| Seedance 2.5 Image to Video(Lite) seedance-2.5-lite-i2v | | image_to_video | Resolution 720p$0.15/sec |
| Seedance 2.5 Text to Video(Lite) seedance-2.5-lite-t2v | | text_to_video | Resolution 720p$0.15/sec |
| Seedance 2.0 Mini Reference to Video(Lite) seedance-2.0-mini-lite-r2v | | image_to_videovideo_to_video | Resolution 720p · No reference video$0.025/sec Resolution 720p · With reference video$0.015/sec |
| Seedance 2.0 Mini Image to Video(Lite) seedance-2.0-mini-lite-i2v | | image_to_video | Resolution 720p$0.025/sec |
| Seedance 2.0 Mini Text to Video(Lite) seedance-2.0-mini-lite-t2v | | text_to_video | Resolution 720p$0.025/sec |
| Seedance 2.0 Fast Reference to Video(Lite) seedance-2.0-fast-lite-r2v | | image_to_videovideo_to_video | Resolution 720p · No reference video$0.07/sec Resolution 720p · With reference video$0.042/sec |
| Seedance 2.0 Fast Image to Video(Lite) seedance-2.0-fast-lite-i2v | | image_to_video | Resolution 720p$0.07/sec |
| Seedance 2.0 Fast Text to Video(Lite) seedance-2.0-fast-lite-t2v | | text_to_video | Resolution 720p$0.07/sec |
| Seedance 2.5 Reference to Video seedance-2.5-r2v | | image_to_videovideo_to_video | Resolution 480p · No reference video$0.098/sec Resolution 480p · With reference video$0.0588/sec Resolution 720p · No reference video$0.2205/sec |
| Seedance 2.5 Image to Video seedance-2.5-i2v | | image_to_video | Resolution 480p$0.098/sec Resolution 720p$0.2205/sec Resolution 1080p$0.54194/sec |
| Seedance 2.5 Text to Video seedance-2.5-t2v | | text_to_video | Resolution 480p$0.098/sec Resolution 720p$0.2205/sec Resolution 1080p$0.54194/sec |
| Seedance 2.0 Reference to Video(Lite) seedance-2.0-lite-r2v | | image_to_videovideo_to_video | Resolution 720p · No reference video$0.085/sec Resolution 720p · With reference video$0.051/sec Resolution 1080p · No reference video$0.17/sec |
| Seedance 2.0 Image to Video(Lite) seedance-2.0-lite-i2v | | image_to_video | Resolution 720p$0.085/sec Resolution 1080p$0.17/sec |
| Seedance 2.0 Text to Video(Lite) seedance-2.0-lite-t2v | | text_to_video | Resolution 720p$0.085/sec Resolution 1080p$0.17/sec |
| Grok 4.6 grok-4.6 |  | llm | Base Input$2/1M Output$6/1M Cache-R$0.5/1M Channel discounts xAI×0.70 |
| DeepSeek V4 Pro deepseek-v4-pro | | llm | Base Input$1.35/1M Output$4.05/1M Cache-R$0.045/1M Channel discounts DeepSeek×0.70 |
| DeepSeek V4 Flash deepseek-v4-flash | | llm | Base Input$0.45/1M Output$1.35/1M Cache-R$0.015/1M Channel discounts DeepSeek×0.70 |
| WAN 3.0 Reference to Video wan3.0-r2v | | image_to_videovideo_to_video | Resolution 480P$0.045/sec Resolution 480p$0.045/sec Resolution 720P$0.09/sec |
| WAN 3.0 Image to Video wan3.0-i2v | | image_to_video | Resolution 480P$0.045/sec Resolution 480p$0.045/sec Resolution 720P$0.09/sec |
| WAN 3.0 Text to Video wan3.0-t2v | | text_to_video | Resolution 480P$0.045/sec Resolution 480p$0.045/sec Resolution 720P$0.09/sec |
| MiniMax H3 Reference to Video minimax-h3-r2v |  | image_to_videovideo_to_video | Resolution 2K$0.1395/sec Resolution 768P$0.09/sec |
| MiniMax H3 Image to Video minimax-h3-i2v | | image_to_video | Resolution 2K$0.1395/sec Resolution 768P$0.09/sec |
| MiniMax H3 Text to Video minimax-h3-t2v | | text_to_video | Resolution 2K$0.1395/sec Resolution 768P$0.09/sec |
| Grok Imagine Video 1.5 VIP grok-imagine-1.5-vip | | image_to_video | Resolution 480P$0.055/sec Resolution 480p$0.055/sec Resolution 720P$0.11/sec |
| Gemini 3.6 Flash gemini-3.6-flash | | llm | Base Input$1.5/1M Output$7.5/1M Cache-R$0.15/1M Channel discounts Google×0.40 Gemini Mix×0.60 |
| GPT Image 2 Fast gpt-image-2-fast | | text_to_imageimage_to_image | Resolution 1K$0.015/request Resolution 2K$0.03/request Resolution 4K$0.06/request |
| GPT Image 2 Lite gpt-image-2-lite | | text_to_imageimage_to_image | $0.015/request |
| Claude Opus 5 claude-opus-5 | | llm | Base Input$5/1M Output$25/1M Cache-R$0.5/1M Cache-W 5m$6.25/1M Cache-W 1h$10/1M Channel discounts Anthropic×0.80 Claude Max×0.30 |
| Grok Imagine Video 1.5 Fast grok-imagine-1.5-fast | | image_to_video | $0.018/sec |
| GLM 5.2 glm-5.2 |  | llm | Base Input$1.4/1M Output$4.4/1M Cache-R$0.26/1M Channel discounts Z.AI×0.70 |
| Grok 4.5 grok-4.5 | | llm | BaseTiered · 2 tiers · Input ≤ 200K Input$2/1M Output$6/1M Cache-R$0.5/1M Channel discounts xAI×0.70 Grok Lite×0.10 |
| GPT 5.6 Luna gpt-5.6-luna | | llm | BaseTiered · 2 tiers · Input ≤ 272K Input$0.2/1M Output$1.2/1M Cache-R$0.02/1M Cache-W$0.25/1M Channel discounts OPENAI×0.80 Azure×0.60 Codex×0.40 |
| GPT 5.6 Terra gpt-5.6-terra | | llm | BaseTiered · 2 tiers · Input ≤ 272K Input$2/1M Output$12/1M Cache-R$0.2/1M Cache-W$2.5/1M Channel discounts OPENAI×0.80 Azure×0.60 Codex×0.40 |
| GPT 5.5 gpt-5.5 | | llm | BaseTiered · 2 tiers · Input ≤ 272K Input$5/1M Output$30/1M Cache-R$0.5/1M Channel discounts OPENAI×0.80 Azure×0.60 Codex×0.20 |
| Claude Sonnet 5 claude-sonnet-5 | | llm | Base Input$2/1M Output$10/1M Cache-R$0.2/1M Cache-W 5m$2.5/1M Cache-W 1h$4/1M Channel discounts Anthropic×0.80 Claude Max×0.30 |
| Claude Opus 4.8 claude-opus-4-8 | | llm | Base Input$5/1M Output$25/1M Cache-R$0.5/1M Cache-W 5m$6.25/1M Cache-W 1h$10/1M Channel discounts Anthropic×0.80 Claude Max×0.30 |
| Seedance 2.0 Mini Reference to Video seedance-2.0-mini-r2v | | image_to_videovideo_to_video | Resolution 480p · No reference video$0.016/sec Resolution 480p · With reference video$0.0096/sec Resolution 720p · No reference video$0.032/sec |
| Seedance 2.0 Mini Image to Video seedance-2.0-mini-i2v | | image_to_video | Resolution 480p$0.016/sec Resolution 720p$0.032/sec |
| Seedance 2.0 Mini Text to Video seedance-2.0-mini-t2v | | text_to_video | Resolution 480p$0.016/sec Resolution 720p$0.032/sec |
| Gemini Omni Reference to video gemini-omni-r2v | | image_to_video | $0.25/request |
| Gemini Omni Extend gemini-omni-extend | | video_to_video | $0.25/request |
| Grok Imagine Video 1.5 Preview grok-imagine-1.5-preview | | image_to_video | Resolution 480p$0.02/sec Resolution 720p$0.04/sec |
| Gemini Omni Image to Video gemini-omni-i2v | | image_to_video | $0.25/request |
| Gemini Omni Text to Video gemini-omni-t2v | | text_to_video | $0.25/request |
| Gemini 3.5 Flash gemini-3.5-flash | | llm | Base Input$1.5/1M Output$9/1M Cache-R$0.15/1M Channel discounts Google×0.40 Gemini Mix×0.60 |
| GPT Image 2 gpt-image-2 | | text_to_imageimage_to_image | Quality 1K · Resolution 1K$0.02/request Quality 1K · Resolution 2K$0.04/request Quality 1K · Resolution 4K$0.08/request |
| Claude Opus 4.7 claude-opus-4-7 | | llm | Base Input$5/1M Output$25/1M Cache-R$0.5/1M Cache-W 5m$6.25/1M Cache-W 1h$10/1M Channel discounts Anthropic×0.80 Claude Max×0.30 |
| Seedance 2.0 Fast Reference to Video seedance-2.0-fast-r2v | | image_to_videovideo_to_video | Resolution 480p · No reference video$0.045/sec Resolution 480p · With reference video$0.027/sec Resolution 720p · No reference video$0.09/sec |
| Seedance 2.0 Fast Image to Video seedance-2.0-fast-i2v | | image_to_video | Resolution 480p$0.045/sec Resolution 720p$0.09/sec |
| Seedance 2.0 Fast Text to Video seedance-2.0-fast-t2v | | text_to_video | Resolution 480p$0.045/sec Resolution 720p$0.09/sec |
| Veo 3.1 Lite 4K veo3-1-lite-4k | | text_to_videoimage_to_video | $0.4/request |
| Veo 3.1 Lite veo3-1-lite | | text_to_videoimage_to_video | $0.08/request |
| WAN 2.7 Video Edit wan2.7-videoedit | | video_to_video | Resolution 720P$0.1/sec Resolution 1080P$0.15/sec |
| WAN 2.7 Image to Video wan2.7-i2v | | image_to_video | Resolution 720P$0.1/sec Resolution 1080P$0.15/sec |
| WAN 2.7 Text to Video wan2.7-t2v | | text_to_video | Resolution 720P$0.1/sec Resolution 1080P$0.15/sec |
| Seedance 2.0 Text to Video seedance-2.0-t2v | | text_to_video | Resolution 4k$0.7245/sec Resolution 480p$0.063/sec Resolution 720p$0.126/sec |
| WAN 2.7 Image Edit Pro wan2.7-image-pro-edit | | image_to_image | Requests$0.075/req |
| WAN 2.7 Text to Image Pro wan2.7-image-pro | | text_to_image | Requests$0.075/req |
| WAN 2.7 Image Edit wan2.7-image-edit | | image_to_image | Requests$0.03/req |
| WAN 2.7 Text to Image wan2.7-image | | text_to_image | Requests$0.03/req |
| GPT 5.4 nano gpt-5.4-nano | | llm | Base Input$0.2/1M Output$1.25/1M Cache-R$0.02/1M Channel discounts OPENAI×0.80 |
| GPT 5.4 mini gpt-5.4-mini | | llm | Base Input$0.75/1M Output$4.5/1M Cache-R$0.075/1M Channel discounts OPENAI×0.80 Azure×0.60 Codex×0.20 |
| Seedance 2.0 Reference seedance-2.0-r2v | | image_to_video | Resolution 4k · No reference video$0.7245/sec Resolution 4k · With reference video$0.4347/sec Resolution 480p · No reference video$0.063/sec |
| Seedance 2.0 Image to Video seedance-2.0-i2v | | image_to_video | Resolution 4k$0.7245/sec Resolution 480p$0.063/sec Resolution 720p$0.126/sec |
| Sora 2 VIP sora-2-vip | | text_to_videoimage_to_video | $0.09/sec |
| Gemini 3.1 Flash-Lite Preview gemini-3.1-flash-lite-preview | | llm | Base Input$0.25/1M Output$1.5/1M Cache-R$0.025/1M Channel discounts Google×0.40 Gemini Mix×0.60 |
| Gemini 3.1 Pro Preview gemini-3.1-pro-preview | | llm | Base Input$2/1M Output$12/1M Cache-R$0.2/1M Cache-W 1h$4.5/1M Channel discounts Google×0.40 Gemini Mix×0.60 |
| Claude Opus 4.6 claude-opus-4-6 | | llm | Base Input$5/1M Output$25/1M Cache-R$0.5/1M Cache-W 5m$6.25/1M Cache-W 1h$10/1M Channel discounts Anthropic×0.80 Claude Max×0.30 |
| Kling 2.6 Motion Control kling-2.6-motion-control |  | text_to_videoimage_to_video | Quality pro$0.105/sec Quality std$0.07/sec |
| Grok Imagine Image to Video grok-imagine-i2v | | image_to_video | Resolution 480p$0.018/sec Resolution 720p$0.036/sec |
| Grok Imagine Text to Video grok-imagine-t2v | | text_to_video | Resolution 480p$0.018/sec Resolution 720p$0.036/sec |
| GPT 5.4 Pro gpt-5.4-pro | | llm | BaseTiered · 2 tiers · Input ≤ 272K Input$30/1M Output$180/1M Channel discounts OPENAI×0.80 Azure×0.60 |
| GPT 5.4 gpt-5.4 | | llm | BaseTiered · 2 tiers · Input ≤ 272K Input$2.5/1M Output$15/1M Cache-R$0.25/1M Channel discounts OPENAI×0.80 Azure×0.60 Codex×0.20 |
| Nano Banana 2 nano-banana-2 | | text_to_imageimage_to_image | Quality 1K$0.04/request Quality 2K$0.06/request Quality 4K$0.08/request |
| Seedream 5.0 Lite Edit seedream-5.0-lite-edit | | image_to_image | $0.035/request |
| Seedream 5.0 Lite seedream-5.0-lite | | text_to_image | $0.035/request |
| Claude Sonnet 4.6 claude-sonnet-4-6 | | llm | Base Input$3/1M Output$15/1M Cache-R$0.3/1M Cache-W 5m$3.75/1M Cache-W 1h$6/1M Channel discounts Anthropic×0.80 Claude Max×0.30 |
| Seedance 1.0 Lite Image to Video Reference seedance-1.0-lite-i2v-ref | | image_to_video | Resolution 480p$0.02/sec Resolution 720p$0.06/sec Resolution 1080p$0.12/sec |
| Motion Control motion-control-m1 | | video_to_video | $1/request |
| Seedance 1.0 Lite Image to Video seedance-1.0-lite-i2v | | image_to_video | Resolution 480p$0.02/sec Resolution 720p$0.06/sec Resolution 1080p$0.12/sec |
| Seedance 1.0 Lite Text to Video seedance-1.0-lite-t2v | | text_to_video | Resolution 480p$0.02/sec Resolution 720p$0.06/sec Resolution 1080p$0.12/sec |
| Seedance 1.0 Pro Fast Image to Video seedance-1.0-pro-fast-i2v | | image_to_video | Resolution 480p$0.012/sec Resolution 720p$0.024/sec Resolution 1080p$0.048/sec |
| Seedance 1.0 Pro Fast Text to Video seedance-1.0-pro-fast-t2v | | text_to_video | Resolution 480p$0.012/sec Resolution 720p$0.024/sec Resolution 1080p$0.048/sec |
| Seedance 1.0 Pro Image to Video seedance-1.0-pro-i2v | | image_to_video | Resolution 480p$0.03/sec Resolution 720p$0.06/sec Resolution 1080p$0.12/sec |
| Seedance 1.0 Pro Text to Video seedance-1.0-pro-t2v | | text_to_video | Resolution 480p$0.03/sec Resolution 720p$0.06/sec Resolution 1080p$0.12/sec |
| Seedance 1.5 Pro Image to Video seedance-1.5-pro-i2v | | image_to_video | Resolution 480p$0.025/sec Resolution 720p$0.075/sec Resolution 1080p$0.125/sec |
| Seedance 1.5 Pro Text to Video seedance-1.5-pro-t2v | | text_to_video | Resolution 480p$0.025/sec Resolution 720p$0.075/sec Resolution 1080p$0.125/sec |
| Veo 3.1 Quality 4K veo3-1-quality-4k | | text_to_videoimage_to_video | $1.2/request |
| Veo 3.1 Fast 4K veo3-1-fast-4k | | text_to_videoimage_to_video | $0.5/request |
| Claude Haiku 4.5 claude-haiku-4-5 | | llm | Base Input$1/1M Output$5/1M Cache-R$0.1/1M Cache-W 5m$1.25/1M Cache-W 1h$2/1M Channel discounts Anthropic×0.80 Claude Max×0.30 |
| Sora 2 Pro sora-2-pro | | text_to_videoimage_to_video | $0.5/request |
| Sora 2 sora-2 | | text_to_videoimage_to_video | $0.15/request |
| Veo 3.1 Fast Reference veo3-1-fast-ref | | image_to_video | $0.18/request |
| Seedream V4.5 Edit seedream-v4.5-edit | | image_to_image | Quality 1K$0.04/request Quality 2K$0.04/request Quality 4K$0.06/request |
| Seedream V4.5 Text to Image seedream-v4.5 | | text_to_image | Quality 1K$0.04/request Quality 2K$0.04/request Quality 4K$0.06/request |
| Veo 3.1 Quality veo3-1-quality | | text_to_videoimage_to_video | $0.8/request |
| Veo 3.1 Fast veo3-1-fast | | text_to_videoimage_to_video | $0.18/request |
| Nano Banana Pro nano-banana-pro | | text_to_imageimage_to_image | Quality 1K$0.06/request Quality 2K$0.09/request Quality 4K$0.12/request |
Live rates from the API, per 1M tokens or the unit shown. Actual billing follows the console.
07/FAQ
Frequently asked questions
What developers usually ask about APIPod's image, video and LLM APIs.
01What is APIPod?
APIPod is an AI media generation platform for developers. One API key gives you Seedance, Veo, Nano Banana, GPT Image and other top image and video models, plus mainstream LLMs such as GPT, Claude and Gemini. Every request goes through multi-channel routing with automatic failover, and you pay only for what you use — no subscription.
02Which models are supported?
Video: Seedance, Veo, Sora, Wan, MiniMax, Grok Imagine and more. Image: Seedream, Nano Banana, GPT Image and more. LLMs: GPT, Claude, Gemini, Grok and more. New models are added as soon as they launch — see the models page for the full list and live prices.
03How do image and video calls work, and how long do they take?
Image and video run as async tasks. A POST to https://api.apipod.ai/v1/images/generations or https://api.apipod.ai/v1/videos/generations returns a task_id immediately; poll GET https://api.apipod.ai/v1/images/status/{task_id} or GET https://api.apipod.ai/v1/videos/status/{task_id} (matching the endpoint you called) as it moves through pending, processing and completed or failed, and read the output URLs from result. Pass a callback_url instead to be notified when the task finishes, with no polling. Duration depends on the model, resolution and length.
04How does billing work? Am I charged for failed tasks?
Pay as you go — no monthly fee, no subscription. Depending on the model you are billed per token, per request or per second, and many models offer official, discounted and special-price channels so you can pick by budget. Costs are reserved when a task is submitted and refunded automatically if it fails; every charge is itemised in the console.
05How do I get started?
Sign up, create an API key in the console, then copy a Node, Python or cURL example from the homepage or the docs and swap in your key to submit your first task. New accounts get free trial credits, no credit card required.
06What happens when a channel goes down?
A model can be served by several upstream channels, and requests are spread by weight or round-robin. On a retryable upstream error the failed channel is excluded and the request moves to the next healthy one; a channel that keeps failing is circuit-broken for a cooldown and probed before it gets traffic again, so outages don't cascade into your product.
07Is APIPod compatible with the OpenAI, Anthropic and Gemini SDKs?
Yes. Chat completions are fully OpenAI-compatible — just point your SDK's base_url at the API address shown in your console. Anthropic Messages and the native Gemini API formats are supported too, so existing code needs little to no change.
08Can I use it without writing code?
Yes. The site includes online AI image and AI video generators — type a prompt and create right away, using the same account and balance as the API. The prompt library also has ready-to-use prompts for every model.
In a few minutes, your first AI video.
Sign up, grab a key, and call image, video and language models from one endpoint. Register now for free trial credits, no credit card required.