# SeedRouter

> SeedRouter puts image, video, language and audio 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.

## Model guides

- [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 (one flat price per delivered image, at any size or 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 (one flat price per delivered image, at any size or 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)
- [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 (one flat price per delivered image, at any size or 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 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 (one flat price per delivered image, at any size or 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 (one flat price per delivered image, at any size or 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 (one flat price per delivered image, at any size or 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)
- [Claude Fable 5.1](https://seedrouter.ai/models/claude-fable-5-1/llms.txt): Call Claude Fable 5.1 with the Anthropic or OpenAI SDK. Deep reasoning, 1M-token context, cheap cached reads, live pricing and a playground to try it today. Channels: Text tokens (billed per input, output and prompt-cache token the finished response reports): `claude-fable-5-1`. Current prices per channel: https://seedrouter.ai/models/claude-fable-5-1/llms.txt. (HTML: https://seedrouter.ai/models/claude-fable-5-1)
- [Claude Fable 5](https://seedrouter.ai/models/claude-fable-5/llms.txt): Call Claude Fable 5 with the Anthropic or OpenAI SDK. Deep reasoning, 1M-token context, forced tool use, live per-token pricing and a playground to test it. Channels: Text tokens (billed per input, output and prompt-cache token the finished response reports): `claude-fable-5`. Current prices per channel: https://seedrouter.ai/models/claude-fable-5/llms.txt. (HTML: https://seedrouter.ai/models/claude-fable-5)
- [Claude Opus 5.5](https://seedrouter.ai/models/claude-opus-5-5/llms.txt): Call Claude Opus 5.5 with the Anthropic or OpenAI SDK. 1M-token context, adaptive thinking, live per-token pricing and a playground you can try right now. Channels: Text tokens (billed per input, output and prompt-cache token the finished response reports): `claude-opus-5-5`. Current prices per channel: https://seedrouter.ai/models/claude-opus-5-5/llms.txt. (HTML: https://seedrouter.ai/models/claude-opus-5-5)
- [GPT-6 Astra](https://seedrouter.ai/models/gpt-6-astra/llms.txt): Call GPT-6 Astra with the OpenAI SDK. OpenAI's most capable model, with a 1.05M-token context, live per-token pricing and a playground you can try right now. Channels: Text tokens (billed per input, output and prompt-cache token the finished response reports): `gpt-6-astra`. Current prices per channel: https://seedrouter.ai/models/gpt-6-astra/llms.txt. (HTML: https://seedrouter.ai/models/gpt-6-astra)
- [GPT-6 Sol](https://seedrouter.ai/models/gpt-6-sol/llms.txt): Call GPT-6 Sol with the OpenAI SDK. 1.05M-token context, reasoning effort from none to max, live per-token pricing and a playground you can try right now. Channels: Text tokens (billed per input, output and prompt-cache token the finished response reports): `gpt-6-sol`. Current prices per channel: https://seedrouter.ai/models/gpt-6-sol/llms.txt. (HTML: https://seedrouter.ai/models/gpt-6-sol)
- [GPT-6 Luna](https://seedrouter.ai/models/gpt-6-luna/llms.txt): Call GPT-6 Luna with the OpenAI SDK. The lowest-cost GPT-6 model, with a 1.05M-token context, live per-token pricing and a playground you can try right now. Channels: Text tokens (billed per input, output and prompt-cache token the finished response reports): `gpt-6-luna`. Current prices per channel: https://seedrouter.ai/models/gpt-6-luna/llms.txt. (HTML: https://seedrouter.ai/models/gpt-6-luna)
- [Kimi K3](https://seedrouter.ai/models/kimi-k3/llms.txt): Call Kimi K3 with the OpenAI or Anthropic SDK. 1M-token context, always-on reasoning with low, high or max effort, live per-token pricing and a playground. Channels: Text tokens (billed per input, output and prompt-cache token the finished response reports): `kimi-k3`. Current prices per channel: https://seedrouter.ai/models/kimi-k3/llms.txt. (HTML: https://seedrouter.ai/models/kimi-k3)
- [DeepSeek V4.1 Flash](https://seedrouter.ai/models/deepseek-v4-1-flash/llms.txt): Call DeepSeek V4.1 Flash with the OpenAI or Anthropic SDK. 1M-token context, thinking on or off, image input, live peak and off-peak pricing and a playground. Channels: Text tokens (billed per input, output and prompt-cache token the finished response reports): `deepseek-v4.1-flash`. Current prices per channel: https://seedrouter.ai/models/deepseek-v4-1-flash/llms.txt. (HTML: https://seedrouter.ai/models/deepseek-v4-1-flash)

## How to read this site

Each published model landing page has a companion at https://seedrouter.ai/models/<slug>/llms.txt: capabilities, current pricing and a worked estimate, parameters, examples, output format, and error handling. Start with that file when integrating a model.
Documentation is also available as Markdown: append .md to the English HTML URL. For example, https://seedrouter.ai/docs/gpt-image-2 becomes https://seedrouter.ai/docs/gpt-image-2.md. These are the same authored documents.
Machine-readable request and response schemas: [GPT Image 2 OpenAPI](https://seedrouter.ai/docs/gpt-image-2.openapi.json) (Standard and Official IDs) and [GPT Image 2.5 OpenAPI](https://seedrouter.ai/docs/gpt-image-2-5.openapi.json).

## Documentation

- API Reference > [Authentication](https://seedrouter.ai/docs/api/authentication.md): Use an API key to authenticate requests. (HTML: https://seedrouter.ai/docs/api/authentication)
- API Reference > [Balance](https://seedrouter.ai/docs/api/balance.md): Manage credits and inspect task charges. (HTML: https://seedrouter.ai/docs/api/balance)
- API Reference > [Errors](https://seedrouter.ai/docs/api/errors.md): Interpret request errors and failed image tasks. (HTML: https://seedrouter.ai/docs/api/errors)
- API Reference > [Overview](https://seedrouter.ai/docs/api/overview.md): Endpoints and conventions for the asynchronous image API. (HTML: https://seedrouter.ai/docs/api/overview)
- API Reference > [Quickstart](https://seedrouter.ai/docs/api/quickstart.md): Submit your first image task and retrieve its result. (HTML: https://seedrouter.ai/docs/api/quickstart)
- API Reference > [Tasks](https://seedrouter.ai/docs/api/tasks.md): Poll task status and retrieve generated images. (HTML: https://seedrouter.ai/docs/api/tasks)
- API Reference > [Webhooks](https://seedrouter.ai/docs/api/webhooks.md): Completion notifications for image tasks. (HTML: https://seedrouter.ai/docs/api/webhooks)
- Models and getting started > [Claude Fable 5](https://seedrouter.ai/docs/claude-fable-5.md): Call Claude Fable 5 with the official Anthropic Messages API, or the OpenAI Chat Completions and Responses formats: adaptive thinking, a 1M-token context window and up to 128K output tokens. (HTML: https://seedrouter.ai/docs/claude-fable-5)
- Models and getting started > [Claude Fable 5.1](https://seedrouter.ai/docs/claude-fable-5-1.md): Call Claude Fable 5.1 with the official Anthropic Messages API, or the OpenAI Chat Completions and Responses formats: adaptive thinking, a 1M-token context window and up to 128K output tokens. (HTML: https://seedrouter.ai/docs/claude-fable-5-1)
- Models and getting started > [Claude Opus 5.5](https://seedrouter.ai/docs/claude-opus-5-5.md): Call Claude Opus 5.5 with the official Anthropic Messages API, or the OpenAI Chat Completions and Responses formats: adaptive thinking, a 1M-token context window and up to 128K output tokens. (HTML: https://seedrouter.ai/docs/claude-opus-5-5)
- Models and getting started > [DeepSeek V4.1 Flash](https://seedrouter.ai/docs/deepseek-v4-1-flash.md): Call DeepSeek V4.1 Flash with the official Chat Completions, Responses or Anthropic Messages API: a 1M-token context, thinking on or off and images. (HTML: https://seedrouter.ai/docs/deepseek-v4-1-flash)
- Models and getting started > [Nano Banana 2 (Gemini 3.1 Flash Image)](https://seedrouter.ai/docs/gemini-3-1-flash-image.md): 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. (HTML: https://seedrouter.ai/docs/gemini-3-1-flash-image)
- Models and getting started > [Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image)](https://seedrouter.ai/docs/gemini-3-1-flash-lite-image.md): 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. (HTML: https://seedrouter.ai/docs/gemini-3-1-flash-lite-image)
- Models and getting started > [Nano Banana Pro (Gemini 3 Pro Image)](https://seedrouter.ai/docs/gemini-3-pro-image.md): Generate and edit images with Nano Banana Pro through one async endpoint using Google's generateContent body: built-in thinking, 4K output, 14 references. (HTML: https://seedrouter.ai/docs/gemini-3-pro-image)
- Models and getting started > [GPT-6 Astra](https://seedrouter.ai/docs/gpt-6-astra.md): Call GPT-6 Astra with the official OpenAI Responses or Chat Completions API: a 1.05M-token context window, up to 128K output tokens and reasoning effort you choose. (HTML: https://seedrouter.ai/docs/gpt-6-astra)
- Models and getting started > [GPT-6 Luna](https://seedrouter.ai/docs/gpt-6-luna.md): Call GPT-6 Luna with the official OpenAI Responses or Chat Completions API: a 1.05M-token context window, up to 128K output tokens and reasoning effort you choose. (HTML: https://seedrouter.ai/docs/gpt-6-luna)
- Models and getting started > [GPT-6 Sol](https://seedrouter.ai/docs/gpt-6-sol.md): Call GPT-6 Sol with the official OpenAI Responses or Chat Completions API: a 1.05M-token context window, up to 128K output tokens and reasoning effort you choose. (HTML: https://seedrouter.ai/docs/gpt-6-sol)
- Models and getting started > [GPT Image 2](https://seedrouter.ai/docs/gpt-image-2.md): Generate images, edit references, and apply masks through one asynchronous image endpoint. (HTML: https://seedrouter.ai/docs/gpt-image-2)
- Models and getting started > [GPT Image 2.5](https://seedrouter.ai/docs/gpt-image-2-5.md): Generate and edit images with GPT Image 2.5 Flare or Sunburst through one asynchronous image endpoint, with six quality steps up to max. (HTML: https://seedrouter.ai/docs/gpt-image-2-5)
- Models and getting started > [Kimi K3](https://seedrouter.ai/docs/kimi-k3.md): Call Kimi K3 with the official Chat Completions, Responses or Anthropic Messages API: a 1M-token context window, always-on reasoning and effort you choose. (HTML: https://seedrouter.ai/docs/kimi-k3)
- Models and getting started > [Seedance 2.0](https://seedrouter.ai/docs/seedance-2-0.md): Generate video with Seedance 2.0 through the official ModelArk task API: text to video, first and last frames, and image, video and audio references, 480p to 4K. (HTML: https://seedrouter.ai/docs/seedance-2-0)
- Models and getting started > [Seedance 2.5](https://seedrouter.ai/docs/seedance-2-5.md): Generate, edit and extend video with Seedance 2.5 through the official ModelArk task API: up to 30 seconds at 1080p, with up to 30 image, 10 video and 10 audio references. (HTML: https://seedrouter.ai/docs/seedance-2-5)
- Models and getting started > [Welcome](https://seedrouter.ai/docs/welcome.md): Build with the SeedRouter API. (HTML: https://seedrouter.ai/docs/welcome)

## Practical guides

English articles on budgeting, prompts, batch requests, and integration. Markdown and HTML share the same authored content; the pricing guide includes current rates rather than fixed quotes.

- [Claude Fable 5.1 prompting guide: effort, system prompts and what changed](https://seedrouter.ai/blog/claude-fable-5-1-prompting-guide.md): How to prompt Claude Fable 5.1 and Claude Opus 5.5: effort, system prompt lines from Anthropic's own guides, what the models now reject, and worked examples. (HTML: https://seedrouter.ai/blog/claude-fable-5-1-prompting-guide)
- [Context window vs max output tokens: limits for GPT-6, Claude, DeepSeek and Kimi](https://seedrouter.ai/blog/context-window-vs-max-output-tokens.md): What context window and max output tokens mean, the limits for GPT-6, Claude, DeepSeek V4.1 Flash and Kimi K3, and how to fix replies that stop early. (HTML: https://seedrouter.ai/blog/context-window-vs-max-output-tokens)
- [DeepSeek V4.1 Flash specs: context window, max output, size and defaults](https://seedrouter.ai/blog/deepseek-v4-1-flash-specs.md): DeepSeek V4.1 Flash specs: 552B-parameter MoE, 1M-token context, 384K max output, image input, thinking modes and the defaults that cut replies short. (HTML: https://seedrouter.ai/blog/deepseek-v4-1-flash-specs)
- [fal.ai alternatives: free credits, credit expiry and pricing compared](https://seedrouter.ai/blog/fal-ai-alternatives.md): fal.ai credits expire after 365 days. Compare Replicate, WaveSpeedAI, Kie.ai, Runware, Higgsfield, OpenRouter, RunPod and SeedRouter on credits and APIs. (HTML: https://seedrouter.ai/blog/fal-ai-alternatives)
- [GPT-6 in Codex: setup, tested configs and common errors](https://seedrouter.ai/blog/gpt-6-codex.md): How to run GPT-6 Astra, Sol and Luna in OpenAI Codex CLI with a SeedRouter key: the config.toml, the context window setting, test results and common errors. (HTML: https://seedrouter.ai/blog/gpt-6-codex)
- [GPT-6 release date: when GPT-6 Astra, Sol and Luna came out](https://seedrouter.ai/blog/gpt-6-release-date.md): When was GPT-6 released? GPT-6 Astra launched on September 3, 2026, and GPT-6 Sol and Luna on September 22. How the rollout went and where to use GPT-6 today. (HTML: https://seedrouter.ai/blog/gpt-6-release-date)
- [GPT Image 2.5 vs GPT Image 2: release date, differences and when to upgrade](https://seedrouter.ai/blog/gpt-image-2-5-vs-gpt-image-2.md): GPT Image 2.5 vs GPT Image 2: release dates, the new xhigh and max quality steps, Flare and Sunburst, transparency, speed, and when GPT Image 2 still fits. (HTML: https://seedrouter.ai/blog/gpt-image-2-5-vs-gpt-image-2)
- [GPT Image 2.5 vs Nano Banana Pro: text, editing, references and sizes compared](https://seedrouter.ai/blog/gpt-image-2-5-vs-nano-banana-pro.md): GPT Image 2.5 vs Nano Banana Pro: how the two image models compare on text, editing, reference images, output sizes and request shape, and which to pick. (HTML: https://seedrouter.ai/blog/gpt-image-2-5-vs-nano-banana-pro)
- [Is GPT-6 free? What Free, Plus, Pro, students and API users get](https://seedrouter.ai/blog/is-gpt-6-free.md): Is GPT-6 free? Free and Go users get GPT-6 Luna in the ChatGPT desktop app. GPT-6 Astra needs a paid plan, and the API is paid per token. (HTML: https://seedrouter.ai/blog/is-gpt-6-free)
- [Is GPT Image 2 free? ChatGPT plans, the API and GPT Image 2.5](https://seedrouter.ai/blog/is-gpt-image-2-free.md): Is GPT Image 2 free? ChatGPT Images, now GPT Image 2.5, works on every plan within limits, but the OpenAI API has no free tier. What you can use without paying. (HTML: https://seedrouter.ai/blog/is-gpt-image-2-free)
- [Kimi K3 parameters, context window and max output tokens](https://seedrouter.ai/blog/kimi-k3-specs.md): Kimi K3 specs: 2.8 trillion parameters, 16 of 896 experts active per token, a 1M-token context window and up to 1,048,576 output tokens. (HTML: https://seedrouter.ai/blog/kimi-k3-specs)
- [Nano Banana Pro in Claude Code: a skill that generates and edits images](https://seedrouter.ai/blog/nano-banana-pro-claude-code.md): Give Claude Code a Nano Banana Pro skill: a small script that submits the request, polls the task and saves the image, plus a SKILL.md you invoke by name. (HTML: https://seedrouter.ai/blog/nano-banana-pro-claude-code)
- [Nano Banana Pro prompt guide: structure, text, references and edits](https://seedrouter.ai/blog/nano-banana-pro-prompt-guide.md): How to write Nano Banana Pro prompts: a five-part structure, exact text in images, roles for reference images, edits that keep the rest, and 2K or 4K output. (HTML: https://seedrouter.ai/blog/nano-banana-pro-prompt-guide)
- [Seedance 2.5 prompt guide: structure, camera, timing, audio and references](https://seedrouter.ai/blog/seedance-2-5-prompt-guide.md): How to write Seedance 2.5 prompts: the core formula, camera language, timestamps, dialogue and sound syntax, references, edits, and what differs for 2.0. (HTML: https://seedrouter.ai/blog/seedance-2-5-prompt-guide)
- [Seedance "may contain real person" error: why it happens and what is allowed](https://seedrouter.ai/blog/seedance-real-person-error.md): Why Seedance rejects images and videos with real human faces, what the "may contain real person" error means, and the options ByteDance officially allows. (HTML: https://seedrouter.ai/blog/seedance-real-person-error)
- [Together AI alternatives: free credits, pricing and which one fits](https://seedrouter.ai/blog/together-ai-alternatives.md): Together AI has no free trial. Compare OpenRouter, Fireworks, DeepInfra, Groq, Baseten, Hugging Face, Featherless, RunPod, Modal and SeedRouter. (HTML: https://seedrouter.ai/blog/together-ai-alternatives)
- [What is Ox Alpha? The stealth model revealed as Z.ai GLM-5.3-Flash](https://seedrouter.ai/blog/what-is-ox-alpha.md): Ox Alpha was the anonymous name of Z.ai GLM-5.3-Flash on OpenRouter and OpenCode. Who made it, specs, whether it is still free, and how to use it now. (HTML: https://seedrouter.ai/blog/what-is-ox-alpha)
- [Who makes Seedance? ByteDance Seed, the versions and where to use it](https://seedrouter.ai/blog/who-makes-seedance.md): Seedance is made by ByteDance Seed, ByteDance's AI research team. Who owns it, how Seed and Seedance differ, the versions, where to use it and the API. (HTML: https://seedrouter.ai/blog/who-makes-seedance)
- [DeepSeek V4.1 Flash API: get a key and make your first call](https://seedrouter.ai/blog/deepseek-v4-1-flash-api.md): How to use the DeepSeek V4.1 Flash API: get a key, call it with the OpenAI SDK, turn thinking on or off, stream, send images and fix the errors new users hit. (HTML: https://seedrouter.ai/blog/deepseek-v4-1-flash-api)
- [DeepSeek V4.1 Flash API pricing: peak, off-peak and cache hits](https://seedrouter.ai/blog/deepseek-v4-1-flash-api-pricing.md): DeepSeek V4.1 Flash API pricing per million tokens: peak and off-peak rates, cache hits, the hours each applies, the billing formula and what a request costs. (HTML: https://seedrouter.ai/blog/deepseek-v4-1-flash-api-pricing)
- [Use DeepSeek V4.1 Flash in Claude Code and Codex: tested setup](https://seedrouter.ai/blog/deepseek-v4-1-flash-claude-code-codex.md): How to run DeepSeek V4.1 Flash as the model in Claude Code and OpenAI Codex CLI through SeedRouter: environment variables, config.toml and our test results. (HTML: https://seedrouter.ai/blog/deepseek-v4-1-flash-claude-code-codex)
- [DeepSeek V4.1 Flash vs V4 Pro: price, vision and benchmarks](https://seedrouter.ai/blog/deepseek-v4-1-flash-vs-pro.md): DeepSeek V4.1 Flash vs DeepSeek V4 Pro compared on price per token, image input, concurrency and DeepSeek-reported benchmarks, with a clear pick for each job. (HTML: https://seedrouter.ai/blog/deepseek-v4-1-flash-vs-pro)
- [DeepSeek V4.1 Flash vs V4 Flash 0731: what changed and why it matters](https://seedrouter.ai/blog/deepseek-v4-1-flash-vs-v4-flash.md): What changed from DeepSeek V4 Flash 0731 to V4.1 Flash: a new architecture, native vision, a smaller cache, lower prices, benchmarks, and where old names go. (HTML: https://seedrouter.ai/blog/deepseek-v4-1-flash-vs-v4-flash)
- [GPT-6 API: how to get a key and call Astra, Sol and Luna](https://seedrouter.ai/blog/gpt-6-api.md): How to access the GPT-6 API: get a key, call GPT-6 Astra, Sol or Luna with the OpenAI SDK, set reasoning effort, stream, send images and avoid common errors. (HTML: https://seedrouter.ai/blog/gpt-6-api)
- [GPT-6 API pricing: Astra, Sol and Luna cost per million tokens](https://seedrouter.ai/blog/gpt-6-api-pricing.md): GPT-6 API pricing for Astra, Sol and Luna per million tokens: input, output, cached input, cache writes and the 272K long-context rate, with worked examples. (HTML: https://seedrouter.ai/blog/gpt-6-api-pricing)
- [GPT-6 Astra vs Sol vs Luna: which GPT-6 model to use](https://seedrouter.ai/blog/gpt-6-astra-vs-sol-vs-luna.md): GPT-6 Astra vs Sol vs Luna compared: specs, prices, OpenAI benchmark results, reasoning effort and a clear pick for coding, agents and high-volume work. (HTML: https://seedrouter.ai/blog/gpt-6-astra-vs-sol-vs-luna)
- [GPT-6 vs Claude Opus 5.5: benchmarks, prices and which to use](https://seedrouter.ai/blog/gpt-6-vs-claude-opus-5-5.md): GPT-6 Astra, Sol and Luna vs Claude Opus 5.5: specs, token prices, the benchmark results both labs published, and which model fits coding, agents and cost. (HTML: https://seedrouter.ai/blog/gpt-6-vs-claude-opus-5-5)
- [GPT-6 vs GPT-5.6: prices, specs and what changed](https://seedrouter.ai/blog/gpt-6-vs-gpt-5-6.md): GPT-6 vs GPT-5.6 compared: Sol and Luna at half the price, the same 1.05M context, newer knowledge, OpenAI benchmark gains and what to change when you migrate. (HTML: https://seedrouter.ai/blog/gpt-6-vs-gpt-5-6)
- [Is DeepSeek V4.1 Flash free? Open weights, API costs and credit](https://seedrouter.ai/blog/is-deepseek-v4-1-flash-free.md): Is DeepSeek V4.1 Flash free? The weights are free to download, the API is paid per token at low rates, and here is how to try it for next to nothing today. (HTML: https://seedrouter.ai/blog/is-deepseek-v4-1-flash-free)
- [Is Kimi K3 free? Open weights, API costs and free credit](https://seedrouter.ai/blog/is-kimi-k3-free.md): Is Kimi K3 free to use? The weights are free to download, but running them needs data-center hardware, and the API is paid per token. What you can try free. (HTML: https://seedrouter.ai/blog/is-kimi-k3-free)
- [Kimi K3 API: how to get a key and make your first call](https://seedrouter.ai/blog/kimi-k3-api.md): How to access the Kimi K3 API: get a key, call kimi-k3 with the OpenAI SDK, set reasoning effort, stream, send images and fix the errors new users hit first. (HTML: https://seedrouter.ai/blog/kimi-k3-api)
- [Kimi K3 API pricing: cost per million tokens, cache and a task](https://seedrouter.ai/blog/kimi-k3-api-pricing.md): Kimi K3 API pricing per million tokens: input, output, cached input and 5-minute or 1-hour cache writes, with the billing formula and what a task costs. (HTML: https://seedrouter.ai/blog/kimi-k3-api-pricing)
- [Use Kimi K3 in Claude Code and Codex: setup and tested configs](https://seedrouter.ai/blog/kimi-k3-claude-code-codex.md): How to run Kimi K3 as the model in Claude Code and OpenAI Codex CLI through SeedRouter: the environment variables, the config.toml and test results. (HTML: https://seedrouter.ai/blog/kimi-k3-claude-code-codex)
- [Kimi K3 vs Claude Fable 5 and Opus 5.5: price, context and access](https://seedrouter.ai/blog/kimi-k3-vs-claude.md): Kimi K3 vs Claude Fable 5 and Claude Opus 5.5 compared on list price, context, output limits, reasoning control, open weights and API formats, with a verdict. (HTML: https://seedrouter.ai/blog/kimi-k3-vs-claude)
- [Claude Fable 5, Fable 5.1 and Opus 5.5 API pricing: cost per million tokens](https://seedrouter.ai/blog/claude-api-pricing.md): Claude Fable 5.1, Fable 5 and Opus 5.5 API pricing per million tokens: input, output and prompt-cache rates, how a request is billed, and API vs Claude plans. (HTML: https://seedrouter.ai/blog/claude-api-pricing)
- [How to use the Claude Fable 5.1 API: model ID, API key and your first request](https://seedrouter.ai/blog/claude-fable-5-1-api.md): Call the Claude Fable 5.1 API: get an API key, use the claude-fable-5-1 model ID, send a first request in Python or Node.js, and switch to Opus 5.5. (HTML: https://seedrouter.ai/blog/claude-fable-5-1-api)
- [Use Claude Fable 5.1 and Opus 5.5 in Claude Code with an API key](https://seedrouter.ai/blog/claude-fable-5-1-claude-code.md): Run Claude Fable 5.1, Fable 5 or Opus 5.5 in Claude Code with a SeedRouter API key: the environment variables, model selection, and what each session costs. (HTML: https://seedrouter.ai/blog/claude-fable-5-1-claude-code)
- [Claude Fable 5.1 vs Fable 5 vs Opus 5.5: which Claude model to use](https://seedrouter.ai/blog/claude-fable-5-1-vs-fable-5-vs-opus-5-5.md): Claude Fable 5.1 vs Fable 5 vs Opus 5.5 compared: specs, prices, official benchmark scores, what changed from Fable 5 and Opus 5, and which model to pick. (HTML: https://seedrouter.ai/blog/claude-fable-5-1-vs-fable-5-vs-opus-5-5)
- [Is Claude Fable 5 still available? The suspension, the return, and what it means for API users](https://seedrouter.ai/blog/is-claude-fable-5-available.md): Is Claude Fable 5 still available? Why it was suspended on June 12, 2026, when it came back, its status today, and how to call it through the API right now. (HTML: https://seedrouter.ai/blog/is-claude-fable-5-available)
- [Is Claude Fable 5 free? Free plans, trial credit and paid API options](https://seedrouter.ai/blog/is-claude-fable-5-free.md): Is Claude Fable 5 free? What the Claude Free, Pro and Max plans include, whether a free Fable 5 API key exists, and how to test it with free sign-up credit. (HTML: https://seedrouter.ai/blog/is-claude-fable-5-free)
- [Is Nano Banana free? What you get without paying](https://seedrouter.ai/blog/is-nano-banana-free.md): Is Nano Banana free? What the Gemini app and the Gemini API include for Nano Banana 2 and Nano Banana Pro without paying, and when you start paying. (HTML: https://seedrouter.ai/blog/is-nano-banana-free)
- [Is Seedance free? What the free options include](https://seedrouter.ai/blog/is-seedance-free.md): Is Seedance free? Where ByteDance offers Seedance 2.0 and 2.5 with free credits, why the API is paid, and what free unlimited Seedance sites really are. (HTML: https://seedrouter.ai/blog/is-seedance-free)
- [How to use the Nano Banana 2 API: key, request and result](https://seedrouter.ai/blog/nano-banana-2-api.md): Use the Nano Banana 2 API step by step: create a key, send a generateContent request, poll the task, add reference images, and let a coding agent run it. (HTML: https://seedrouter.ai/blog/nano-banana-2-api)
- [Nano Banana 2 vs Nano Banana Pro vs Nano Banana 2 Lite: which one to use](https://seedrouter.ai/blog/nano-banana-2-vs-pro-vs-lite.md): Compare Nano Banana 2, Nano Banana Pro and Nano Banana 2 Lite on image size, aspect ratios, references, thinking and billing, and pick one per job. (HTML: https://seedrouter.ai/blog/nano-banana-2-vs-pro-vs-lite)
- [Nano Banana API pricing: cost per image by resolution](https://seedrouter.ai/blog/nano-banana-api-pricing.md): Current Nano Banana API pricing for Nano Banana 2, Pro and 2 Lite: flat per-image and token billing, cost by resolution, and when each billing fits. (HTML: https://seedrouter.ai/blog/nano-banana-api-pricing)
- [Seedance 2.0 vs Seedance 2.0 Fast vs Seedance 2.0 Mini: which one to use](https://seedrouter.ai/blog/seedance-2-0-vs-fast-vs-mini.md): Compare Seedance 2.0, Seedance 2.0 Fast and Seedance 2.0 Mini on resolution, price per second, render time and inputs, and pick the right one for each job. (HTML: https://seedrouter.ai/blog/seedance-2-0-vs-fast-vs-mini)
- [Seedance 2.5 vs Seedance 2.0: what changed and when to upgrade](https://seedrouter.ai/blog/seedance-2-5-vs-2-0.md): Seedance 2.5 vs Seedance 2.0 compared: clip length, references, editing, resolution, price and release dates, and when the upgrade is worth it. (HTML: https://seedrouter.ai/blog/seedance-2-5-vs-2-0)
- [How to use the Seedance API: key, request, polling and references](https://seedrouter.ai/blog/seedance-api.md): Use the Seedance API step by step: create a key, send a video task, poll it for the video URL, add image, video and audio references, and hand it to an agent. (HTML: https://seedrouter.ai/blog/seedance-api)
- [Seedance API pricing: cost per second for every model and resolution](https://seedrouter.ai/blog/seedance-api-pricing.md): Current Seedance API pricing for Seedance 2.0, 2.0 Fast, 2.0 Mini and 2.5: price per second at each resolution, how video tokens are counted, and what is free. (HTML: https://seedrouter.ai/blog/seedance-api-pricing)
- [GPT Image 2.5 API pricing: what one image costs](https://seedrouter.ai/blog/gpt-image-2-5-api-pricing.md): See current GPT Image 2.5 API pricing per image for Flare and Sunburst, compare flat and token billing, and estimate a monthly budget from real rates. (HTML: https://seedrouter.ai/blog/gpt-image-2-5-api-pricing)
- [GPT Image 2.5 API in Python: a working example](https://seedrouter.ai/blog/gpt-image-2-5-api-python.md): Call the GPT Image 2.5 API from Python and JavaScript, poll the task for image URLs, edit with references, and fix model ID and parameter errors. (HTML: https://seedrouter.ai/blog/gpt-image-2-5-api-python)
- [GPT Image 2.5 Flare vs Sunburst: which one should you use?](https://seedrouter.ai/blog/gpt-image-2-5-flare-vs-sunburst.md): Compare GPT Image 2.5 Flare and Sunburst on speed, edit control, parameters and cost, and pick the right model ID for each kind of image job. (HTML: https://seedrouter.ai/blog/gpt-image-2-5-flare-vs-sunburst)
- [GPT Image 2.5 prompting guide: prompts, edits and quality steps](https://seedrouter.ai/blog/gpt-image-2-5-prompting-guide.md): Write GPT Image 2.5 prompts that hold up across revisions, describe reference edits and masks clearly, and use the six quality steps without wasted renders. (HTML: https://seedrouter.ai/blog/gpt-image-2-5-prompting-guide)
- [GPT Image 2 API key: how to get access and make a first request](https://seedrouter.ai/blog/gpt-image-2-api-key.md): Get a GPT Image 2 API key, store it safely, add credits, and make a first request with curl, Python or JavaScript, plus the errors a new key most often hits. (HTML: https://seedrouter.ai/blog/gpt-image-2-api-key)
- [GPT Image 2 API parameters: size, resolution, aspect ratio and quality](https://seedrouter.ai/blog/gpt-image-2-api-parameters.md): The GPT Image 2 API parameters that shape the image: model name, size and resolution, aspect ratios, 4K limits, quality, formats and the errors they return. (HTML: https://seedrouter.ai/blog/gpt-image-2-api-parameters)
- [GPT Image 2 API in Python: a complete example](https://seedrouter.ai/blog/gpt-image-2-api-python.md): A complete GPT Image 2 API example in Python: submit a request, poll the task, download the images to disk, edit with references and handle errors safely. (HTML: https://seedrouter.ai/blog/gpt-image-2-api-python)
- [Use GPT Image 2 in Codex, Claude Code and other coding agents](https://seedrouter.ai/blog/gpt-image-2-codex-claude-code.md): Let Codex, Claude Code or another coding agent make images with GPT Image 2 through your API key, with a reusable prompt that asks before every paid request. (HTML: https://seedrouter.ai/blog/gpt-image-2-codex-claude-code)
- [Batch GPT Image 2 requests without losing track of tasks](https://seedrouter.ai/blog/gpt-image-2-batch-generation.md): Submit a set of GPT Image 2 prompts, save task IDs, resume polling after interruptions, and download completed images without resubmitting them. (HTML: https://seedrouter.ai/blog/gpt-image-2-batch-generation)
- [How much does GPT Image 2 cost?](https://seedrouter.ai/blog/gpt-image-2-pricing.md): Estimate GPT Image 2 costs from current SeedRouter rates, understand sample token usage, and budget for drafts, revisions, and final images. (HTML: https://seedrouter.ai/blog/gpt-image-2-pricing)
- [GPT Image 2 prompts that are easier to revise](https://seedrouter.ai/blog/gpt-image-2-prompting.md): Write clearer GPT Image 2 prompts, specify exact text, preserve details in reference edits, and revise one visual constraint at a time. (HTML: https://seedrouter.ai/blog/gpt-image-2-prompting)
- [Move an image integration to SeedRouter](https://seedrouter.ai/blog/migrate-image-api-to-seedrouter.md): Migrate a GPT Image 2 integration to SeedRouter by mapping request fields, handling asynchronous tasks, and validating URL-based image delivery. (HTML: https://seedrouter.ai/blog/migrate-image-api-to-seedrouter)

## Support and site information

- [Documentation index](https://seedrouter.ai/docs/llms.txt)
- [Pricing and balance](https://seedrouter.ai/pricing)
- [About SeedRouter](https://seedrouter.ai/about)
- [Contact](https://seedrouter.ai/contact): support@seedrouter.ai
- [Terms](https://seedrouter.ai/terms) and [Privacy](https://seedrouter.ai/privacy)

## Optional

- [Blog index](https://seedrouter.ai/blog/llms.txt): every English post with its Markdown URL
- [Full text](https://seedrouter.ai/llms-full.txt): every English documentation page and blog post inlined in one file, for bulk ingestion. Live prices are in each model's llms.txt, not here.