llms.txt
Compare with other sites' llms.txt files →# SeedRouter
> SeedRouter puts image, video and language models behind a single key. Send one request, get the result, pay only for what was delivered. A request that fails costs nothing.
## Start here
1. Browse [models and current prices](https://seedrouter.ai/models). The model guides below cover published landing pages, not every entry in the live catalog.
2. Create an [API key](https://seedrouter.ai/apikeys) and [add a USD balance](https://seedrouter.ai/billing). Send your key in the Authorization: Bearer header. Keep it in a server-side environment variable.
3. Read the selected model guide before calling it. For GPT Image 2, submit to POST https://api.seedrouter.ai/v1/images/generations, save the returned id, and poll GET https://api.seedrouter.ai/v1/tasks/{id}. The guide includes working examples and the output shape.
Billing uses prepaid USD balance, with no subscription. Unused balance does not expire. Failed requests are not charged. Rates and billing units depend on the model and its channel: Standard model IDs charge one flat price per delivered image, and Official model IDs bill the tokens each render reports. Use current rates rather than remembered prices.
## Choose by task
- [Text models and business workflows](https://seedrouter.ai/text-generation): choose a language model and connect coding assistants or workflow applications.
- [Image generation models](https://seedrouter.ai/image-generation): choose by text, editing, transparency and budget; follow links to model pricing, tutorials and API references.
- [Video generation models](https://seedrouter.ai/video-generation): choose by duration, audio, frame control, references and video editing.
## Solutions
- [Product and advertising visuals](https://seedrouter.ai/solutions/product-visuals.md): Turn product references into reviewable campaign variants, with checks for product fidelity and revision costs. (HTML: https://seedrouter.ai/solutions/product-visuals)
- [Fashion catalog photography](https://seedrouter.ai/solutions/fashion-photography.md): Plan consistent catalog images around garment details, model references and scene requirements. (HTML: https://seedrouter.ai/solutions/fashion-photography)
- [Video production](https://seedrouter.ai/solutions/video-production.md): Build a shot-based workflow with clear acceptance criteria, selective revisions and a delivery budget. (HTML: https://seedrouter.ai/solutions/video-production)
- [AI comic and series production](https://seedrouter.ai/solutions/comic-production.md): Connect scripts, character references and reusable shots for serialized visual storytelling. (HTML: https://seedrouter.ai/solutions/comic-production)
- [Storyboards and animation keyframes](https://seedrouter.ai/solutions/storyboard-animation.md): Translate a shot list and character references into keyframes that can guide animation. (HTML: https://seedrouter.ai/solutions/storyboard-animation)
- [Editable brand assets](https://seedrouter.ai/solutions/editable-brand-assets.md): Combine generated imagery with editable text, original logos and a reusable design layout. (HTML: https://seedrouter.ai/solutions/editable-brand-assets)
- [In-game scene illustrations](https://seedrouter.ai/solutions/game-scene-generation.md): Generate illustrations from game state with controls for scene accuracy, latency and reuse. (HTML: https://seedrouter.ai/solutions/game-scene-generation)
- [Ecommerce operations](https://seedrouter.ai/solutions/ecommerce-automation.md): Create reviewable product copy and campaign drafts from approved product and business information. (HTML: https://seedrouter.ai/solutions/ecommerce-automation)
- [Lead classification and handoff](https://seedrouter.ai/solutions/lead-processing.md): Extract details from incoming leads, review uncertain classifications and hand records to your business systems. (HTML: https://seedrouter.ai/solutions/lead-processing)
- [Customer support workflows](https://seedrouter.ai/solutions/customer-service-automation.md): Connect sourced answers to explicitly approved actions in your existing customer systems. (HTML: https://seedrouter.ai/solutions/customer-service-automation)
- [Invoice and document extraction](https://seedrouter.ai/solutions/invoice-extraction.md): Extract invoice fields and line items, then validate quantities, totals and source evidence. (HTML: https://seedrouter.ai/solutions/invoice-extraction)
- [Internal knowledge assistants](https://seedrouter.ai/solutions/knowledge-assistant.md): Build answers around retrieved passages, technical terminology and traceable document sources. (HTML: https://seedrouter.ai/solutions/knowledge-assistant)
- [Business data queries](https://seedrouter.ai/solutions/business-data-analysis.md): Turn business questions into reviewable queries and explain results calculated by your data systems. (HTML: https://seedrouter.ai/solutions/business-data-analysis)
- [Monthly reports](https://seedrouter.ai/solutions/report-automation.md): Combine deterministic spreadsheet processing with model-assisted classification and written analysis. (HTML: https://seedrouter.ai/solutions/report-automation)
- [Ticket and feedback analysis](https://seedrouter.ai/solutions/ticket-analysis.md): Classify feedback, aggregate counts and identify recurring issues with traceable examples. (HTML: https://seedrouter.ai/solutions/ticket-analysis)
## Industries
- [Ecommerce and retail](https://seedrouter.ai/industries/ecommerce.md): Connect product content, catalog imagery and reviewable operations to your SKU and campaign workflows. (HTML: https://seedrouter.ai/industries/ecommerce)
- [Marketing and advertising](https://seedrouter.ai/industries/marketing.md): Plan campaign variants, editable brand assets and video delivery around a clear creative brief. (HTML: https://seedrouter.ai/industries/marketing)
- [Film and animation](https://seedrouter.ai/industries/film-animation.md): Organize scripts, characters, keyframes and shot revisions into a repeatable production workflow. (HTML: https://seedrouter.ai/industries/film-animation)
- [Games and interactive experiences](https://seedrouter.ai/industries/gaming.md): Connect game state to generated scene illustrations and define the requirements for future audio assets. (HTML: https://seedrouter.ai/industries/gaming)
- [Education and language learning](https://seedrouter.ai/industries/education.md): Match teaching materials to how learners use your product, and plan bilingual voice and playback costs for future audio capabilities. (HTML: https://seedrouter.ai/industries/education)
- [Real estate](https://seedrouter.ai/industries/real-estate.md): Organize lead emails, property information and visual briefs with checks for accuracy and missing details. (HTML: https://seedrouter.ai/industries/real-estate)
- [Logistics and transport](https://seedrouter.ai/industries/logistics.md): Connect transport documents and operational data to reviewable queries and periodic reports. (HTML: https://seedrouter.ai/industries/logistics)
- [Energy](https://seedrouter.ai/industries/energy.md): Work with long technical documents, formulas and specialist terminology while keeping sources visible. (HTML: https://seedrouter.ai/industries/energy)
## Integrations
- [OpenClaw](https://seedrouter.ai/integrations/openclaw.md): Connect model access to bounded agent tasks and measure the cost of a completed, checked result. (HTML: https://seedrouter.ai/integrations/openclaw)
- [Hermes Agent](https://seedrouter.ai/integrations/hermes-agent.md): Define a useful agent task, check model compatibility and keep tool execution under your control. (HTML: https://seedrouter.ai/integrations/hermes-agent)
- [n8n](https://seedrouter.ai/integrations/n8n.md): Connect text and media requests to workflows with explicit item mapping and result handling. (HTML: https://seedrouter.ai/integrations/n8n)
- [Claude Code](https://seedrouter.ai/integrations/claude-code.md): Find SeedRouter configuration guides and task-based checks for Claude Code model access. (HTML: https://seedrouter.ai/integrations/claude-code)
- [Codex](https://seedrouter.ai/integrations/codex.md): Find configuration guides for using text models in Codex and check the API format your setup requires. (HTML: https://seedrouter.ai/integrations/codex)
- [ComfyUI](https://seedrouter.ai/integrations/comfyui.md): Connect hosted image or video tasks to a local graph while preserving reusable assets. (HTML: https://seedrouter.ai/integrations/comfyui)
- [Bubble](https://seedrouter.ai/integrations/bubble.md): Plan API Connector inputs and stable result references for a low-code application. (HTML: https://seedrouter.ai/integrations/bubble)
- [TouchDesigner](https://seedrouter.ai/integrations/touchdesigner.md): Connect generated assets to an interactive visual project without assuming real-time generation. (HTML: https://seedrouter.ai/integrations/touchdesigner)
## Model guides
- [GLM-5.3](https://seedrouter.ai/models/glm-5-3/llms.txt): Try GLM-5.3 for coding, long document review and tool workflows. Explore reasoning controls, live token pricing and complete developer examples. Channels: Text tokens (billed per input, output and prompt-cache token the finished response reports): `glm-5.3`. Current prices per channel: https://seedrouter.ai/models/glm-5-3/llms.txt. (HTML: https://seedrouter.ai/models/glm-5-3)
- [FLUX 3 Image Klein](https://seedrouter.ai/models/flux-3-image-klein/llms.txt): Create and edit images with FLUX 3 Image Klein. Combine up to ten references, choose output up to 4K, and check live prices before generating on SeedRouter. Channels: Image resolution (see current pricing): `flux-3-image-klein`. Current prices per channel: https://seedrouter.ai/models/flux-3-image-klein/llms.txt. (HTML: https://seedrouter.ai/models/flux-3-image-klein)
- [MiniMax M3.1 Flash](https://seedrouter.ai/models/minimax-m3-1-flash/llms.txt): Try MiniMax M3.1 Flash with text, images and video. Compare live token prices, control reasoning effort, and connect your app with three familiar API formats. Channels: Text tokens (billed per input, output and prompt-cache token the finished response reports): `MiniMax-M3.1-Flash`. Current prices per channel: https://seedrouter.ai/models/minimax-m3-1-flash/llms.txt. (HTML: https://seedrouter.ai/models/minimax-m3-1-flash)
- [Whisper-1](https://seedrouter.ai/models/whisper-1/llms.txt): Transcribe recordings with Whisper-1. Get readable text, word timestamps and subtitle files, check live pricing, and try your own audio online on SeedRouter. Channels: Audio duration (billed by measured recording duration, rounded up to whole seconds; transcription text length does not affect the charge): `whisper-1`. Current prices per channel: https://seedrouter.ai/models/whisper-1/llms.txt. (HTML: https://seedrouter.ai/models/whisper-1)
- [Midjourney V8.2](https://seedrouter.ai/models/midjourney-v8-2/llms.txt): Explore Midjourney V8.2 for visual concepts, style references and HD images. Compare versions, check task prices and follow a documented image workflow. Channels: Per operation (one price per image operation, determined by version, action, speed, mode and quality; returned image count is not a charge multiplier): `midjourney-v8.2`, `midjourney-v8.1`, `midjourney-v7`, `midjourney-v6.1`, `midjourney-v6`, `midjourney-v5.2`, `midjourney-v5.1`, `niji-v7`, `niji-v6`. Current prices per channel: https://seedrouter.ai/models/midjourney-v8-2/llms.txt. (HTML: https://seedrouter.ai/models/midjourney-v8-2)
- [GPT Image 2](https://seedrouter.ai/models/gpt-image-2/llms.txt): Generate images, edit references, and apply masks through one asynchronous image endpoint. Channels: Official (billed by the tokens each render reports): `gpt-image-2-official`; Standard (billed per delivered image at the current rate for the selected model and quality): `gpt-image-2`. Current prices per channel: https://seedrouter.ai/models/gpt-image-2/llms.txt. (HTML: https://seedrouter.ai/models/gpt-image-2)
- [GPT Image 2.5](https://seedrouter.ai/models/gpt-image-2-5/llms.txt): Generate and edit images with GPT Image 2.5 Flare or Sunburst through one asynchronous image endpoint, with six quality steps up to max. Channels: Standard (billed per delivered image at the current rate for the selected model and quality): `gpt-image-2.5-flare`, `gpt-image-2.5-sunburst`; Official (billed by the tokens each render reports): `gpt-image-2.5-flare-official`, `gpt-image-2.5-sunburst-official`. Current prices per channel: https://seedrouter.ai/models/gpt-image-2-5/llms.txt. (HTML: https://seedrouter.ai/models/gpt-image-2-5)
- [GPT Image 2.6](https://seedrouter.ai/models/gpt-image-2-6/llms.txt): Generate and edit images with GPT Image 2.6 on SeedRouter. Try Sunburst, animated GIF and SVG output, complexity controls and current model pricing. Channels: Default (see current pricing): `gpt-image-2.6-sunburst-official`, `gpt-image-2.6-sunburst`, `gpt-image-2.6-flare-official`, `gpt-image-2.6-flare`. Current prices per channel: https://seedrouter.ai/models/gpt-image-2-6/llms.txt. (HTML: https://seedrouter.ai/models/gpt-image-2-6)
- [Nano Banana 2 (Gemini 3.1 Flash Image)](https://seedrouter.ai/models/nano-banana-2/llms.txt): Generate and edit images with Nano Banana 2 through one async endpoint using Google's generateContent request body: up to 4K output and 14 reference images. Channels: Official (billed by the tokens each render reports): `gemini-3.1-flash-image-official`; Standard (billed per delivered image at the current rate for the selected model and quality): `gemini-3.1-flash-image`. Current prices per channel: https://seedrouter.ai/models/nano-banana-2/llms.txt. (HTML: https://seedrouter.ai/models/nano-banana-2)
- [Nano Banana 2.1 (Gemini Nano Banana 2.1)](https://seedrouter.ai/models/nano-banana-2-1/llms.txt): Generate and edit images with Nano Banana 2.1 through one async endpoint using Google's generateContent body: 1K to 4K, thinking levels, 14 reference images. Channels: Standard (billed per delivered image at the current rate for the selected model and quality): `gemini-nano-banana-2.1`; Official (billed by the tokens each render reports): `gemini-nano-banana-2.1-official`. Current prices per channel: https://seedrouter.ai/models/nano-banana-2-1/llms.txt. (HTML: https://seedrouter.ai/models/nano-banana-2-1)
- [Nano Banana Pro (Gemini 3 Pro Image)](https://seedrouter.ai/models/nano-banana-pro/llms.txt): Generate and edit images with Nano Banana Pro through one async endpoint using Google's generateContent body: built-in thinking, 4K output, 14 references. Channels: Official (billed by the tokens each render reports): `gemini-3-pro-image-official`; Standard (billed per delivered image at the current rate for the selected model and quality): `gemini-3-pro-image`. Current prices per channel: https://seedrouter.ai/models/nano-banana-pro/llms.txt. (HTML: https://seedrouter.ai/models/nano-banana-pro)
- [Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image)](https://seedrouter.ai/models/nano-banana-2-lite/llms.txt): Generate and edit 1K images with Nano Banana 2 Lite, Google's lowest-latency image model, through one async endpoint using the generateContent request body. Channels: Official (billed by the tokens each render reports): `gemini-3.1-flash-lite-image-official`. Current prices per channel: https://seedrouter.ai/models/nano-banana-2-lite/llms.txt. (HTML: https://seedrouter.ai/models/nano-banana-2-lite)
- [Nano Banana 2 (Gemini 3.1 Flash Image)](https://seedrouter.ai/models/gemini-3-1-flash-image/llms.txt): Generate and edit images with Nano Banana 2 through one async endpoint using Google's generateContent request body: up to 4K output and 14 reference images. Channels: Official (billed by the tokens each render reports): `gemini-3.1-flash-image-official`; Standard (billed per delivered image at the current rate for the selected model and quality): `gemini-3.1-flash-image`. Current prices per channel: https://seedrouter.ai/models/gemini-3-1-flash-image/llms.txt. (HTML: https://seedrouter.ai/models/gemini-3-1-flash-image)
- [Nano Banana Pro (Gemini 3 Pro Image)](https://seedrouter.ai/models/gemini-3-pro-image/llms.txt): Generate and edit images with Nano Banana Pro through one async endpoint using Google's generateContent body: built-in thinking, 4K output, 14 references. Channels: Official (billed by the tokens each render reports): `gemini-3-pro-image-official`; Standard (billed per delivered image at the current rate for the selected model and quality): `gemini-3-pro-image`. Current prices per channel: https://seedrouter.ai/models/gemini-3-pro-image/llms.txt. (HTML: https://seedrouter.ai/models/gemini-3-pro-image)
- [Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image)](https://seedrouter.ai/models/gemini-3-1-flash-lite-image/llms.txt): Generate and edit 1K images with Nano Banana 2 Lite, Google's lowest-latency image model, through one async endpoint using the generateContent request body. Channels: Official (billed by the tokens each render reports): `gemini-3.1-flash-lite-image-official`. Current prices per channel: https://seedrouter.ai/models/gemini-3-1-flash-lite-image/llms.txt. (HTML: https://seedrouter.ai/models/gemini-3-1-flash-lite-image)
- [Seedance 2.0](https://seedrouter.ai/models/seedance-2-0/llms.txt): Generate video with Seedance 2.0: text, first and last frames, and image, video or audio references. 480p to 4K, 4–15 seconds. Pay per second, no subscription. Channels: Video tokens (billed by the video tokens of the finished video, which follow resolution and length): `dreamina-seedance-2-0`. Current prices per channel: https://seedrouter.ai/models/seedance-2-0/llms.txt. (HTML: https://seedrouter.ai/models/seedance-2-0)
- [Seedance 2.0 Fast](https://seedrouter.ai/models/seedance-2-0-fast/llms.txt): Generate video with Seedance 2.0 Fast: the same inputs as Seedance 2.0 at a lower price per second, at 480p or 720p for 4–15 seconds. Pay per second of video. Channels: Video tokens (billed by the video tokens of the finished video, which follow resolution and length): `dreamina-seedance-2-0-fast`. Current prices per channel: https://seedrouter.ai/models/seedance-2-0-fast/llms.txt. (HTML: https://seedrouter.ai/models/seedance-2-0-fast)
- [Seedance 2.0 Mini](https://seedrouter.ai/models/seedance-2-0-mini/llms.txt): Generate video with Seedance 2.0 Mini, the lowest price per second in the Seedance 2.0 family: text, frames and references at 480p or 720p, 4–15 seconds. Channels: Video tokens (billed by the video tokens of the finished video, which follow resolution and length): `dreamina-seedance-2-0-mini`. Current prices per channel: https://seedrouter.ai/models/seedance-2-0-mini/llms.txt. (HTML: https://seedrouter.ai/models/seedance-2-0-mini)
- [Seedance 2.5](https://seedrouter.ai/models/seedance-2-5/llms.txt): Generate, edit and extend video with Seedance 2.5: up to 30 seconds at 1080p, with up to 30 image, 10 video and 10 audio references. Pay per second of video. Channels: Video tokens (billed by the video tokens of the finished video, which follow resolution and length): `dreamina-seedance-2-5`. Current prices per channel: https://seedrouter.ai/models/seedance-2-5/llms.txt. (HTML: https://seedrouter.ai/models/seedance-2-5)
- [SD Video](https://seedrouter.ai/models/sd-video/llms.txt): SD Video turns a prompt, a first frame or your own references into a 5–15 second clip with matching dialogue and sound. 480p or 768p, six aspect ratios. Channels: Video seconds (see current pricing): `sd-video`. Current prices per channel: https://seedrouter.ai/models/sd-video/llms.txt. (HTML: https://seedrouter.ai/models/sd-video)
- [Veo 3.1](https://seedrouter.ai/models/veo-3-1/llms.txt): Veo 3.1 makes 4–8 second clips at 720p, 1080p or 4k from a prompt or images. Pay per clip, or per second with audio, seed and more. Failed runs are free. Channels: Per clip (one price per 8-second clip, by output resolution): `veo-3.1-fast`, `veo-3.1-quality`, `veo-3.1-lite`; Per seco