
Gemini 4 Argon
Gemini 4 Hydrogen vs Argon: Which Model Should You Use?
Gemini 4 Hydrogen vs Argon: compare thinking defaults, context and output limits, current prices and three API checks before choosing a model for your own work.
01 · Image, video, language and audio · one key
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.
Model families available on SeedRouter
Generate and edit video from text or a first frame, at the resolutions and durations each model supports, with native audio where the model provides it. You get a task id you can poll or receive by webhook.

$ POST /v1/videos/generations… processing
"model": "dreamina-seedance-2-5"
Create images from text or edit them with natural-language instructions and reference images. Text rendering, consistent characters and product shots are all available on SeedRouter with one request shape.

$ POST /v1/images/generations✓ completed
"model": "gpt-image-2"
Build chat, reasoning, code generation and agent workflows with tool calls and structured output. Language models on SeedRouter are served through an OpenAI-compatible endpoint, so existing SDKs work by changing the base URL.
Write a product description for a small ceramic planter shaped like a split seed pod.
This hand-glazed ceramic planter mimics a seed pod split open, cradling your succulent in its organic curves. Perfect for windowsills, desks, or anywhere nature-inspired charm is welcome.
Make it shorter — one line for the product tag.
Ceramic seed pod planter — nature's cradle for your favorite succulent.
Now suggest three names for it.
1. Pod & Petal 2. The Sprout Cradle 3. Seedling Split
$ POST /v1/messages✓ 200 OK
"model": "claude-fable-5"
One endpoint, compatible with the OpenAI SDK and standard HTTP clients. Move an existing integration to SeedRouter without rewriting it.
$ curl https://api.seedrouter.ai/v1/images/generations \ -H "Authorization: Bearer $SEEDROUTER_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "model": "gpt-image-2", "prompt": "An amber glass bottle on a cream background, studio lighting", "size": "1024x1024", "quality": "low" }'{"id": "task_…", "status": "processing"}$ curl https://api.seedrouter.ai/v1/tasks/YOUR_TASK_ID \ -H "Authorization: Bearer $SEEDROUTER_API_KEY"Get your API key
Add the SeedRouter MCP server to Claude Code, Cursor or Codex, and your agent can find a model, read its parameters, check the price and generate images or video with your key. Failed tasks are not charged.
# Claude Code$ claude mcp add --transport http seedrouter https://api.seedrouter.ai/v1/mcp \ --header "Authorization: Bearer $SEEDROUTER_API_KEY"# Codex$ codex mcp add seedrouter --url https://api.seedrouter.ai/v1/mcp \ --bearer-token-env-var SEEDROUTER_API_KEY# toolslist_models · get_model_schema · get_pricing · submit_task · get_taskSet up MCP
Every card is a model live on the API, with its current starting price. Open one for parameters, a playground and docs.
VideoSeedance 2.5From $0.1026 per secondGenerate, 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.ByteDanceGet started
VideoKling 4.0From $0.1425 per secondKling 4.0 brings 30-second video, 10 keyframes and stereo sound. Explore its features, pricing and Flash differences. Now available on SeedRouter.KuaishouGet started
ImageGPT Image 2.5From $0.00448 per imageGenerate and edit images with GPT Image 2.5 Flare or Sunburst on SeedRouter. Six quality steps up to max, transparent backgrounds, a live playground and pay-as-you-go pricing.OpenAIGet started
ImageNano Banana 2.1From $0.021 per imageNano Banana 2.1, Google's update to Nano Banana 2: create and edit images with sharper text, 1K to 4K, 14 aspect ratios and 14 references, one price per image.GoogleGet started
VideoMiniMax H3From $0.015385 per secondMiniMax H3 makes 4–15 second clips at 768P or 2K with audio from text, frames or reference images, video and audio. Official request format, pay per second.MiniMaxGet started
ImageNano Banana ProFrom $0.01875 per imageCreate and edit images with Nano Banana Pro (Gemini 3 Pro Image): 1K to 4K output, built-in thinking, up to 14 references. Pay per image or per token.GoogleGet startedOne endpoint, compatible with the OpenAI SDK and standard HTTP clients. Move an existing integration to SeedRouter without rewriting it.
Create a SeedRouter account in under a minute. Look around before you load any balance.
One key works for every model on SeedRouter. Manage and revoke keys from the dashboard.
Use the OpenAI SDK for language models, or the SeedRouter task API for images, video and audio.
Change the base URL and the key. Your first request runs the same day.
curl https://api.seedrouter.ai/v1/responses \
-H "Authorization: Bearer $SEEDROUTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "gpt-6.1-sol",
"input": "Summarize the trade-offs of event sourcing in three bullet points."
}'Billed on delivery
SeedRouter bills you when the result is delivered. A failed request costs nothing, and you can retry or switch models with the same key.
SeedRouter gives you straightforward billing, a balance that never expires, OpenAI-compatible access and clear terms for your data. The essentials for bringing AI into a real product.
Failed requests on SeedRouter are not charged. Track the outcome and exact cost of each request in your dashboard.
See how billing worksTop up one USD balance and spend it on image, video, language and audio models at your own pace. No subscription, monthly minimum or deadline to use it.
Top up your balanceLanguage models on SeedRouter are served through an OpenAI-compatible endpoint. Point the SDK at SeedRouter, use your SeedRouter key and keep your existing code.
Get your API keySee live prices by model and available tier. Where a comparable official price is published, the pricing page shows both rates and the savings.
Compare model pricesSeedRouter does not use your prompts or outputs to train its own models. Request content is processed to deliver results and investigate failures; model vendors apply their own terms.
Read our privacy policyUse one SeedRouter API key across supported models. Track usage, balance and request costs in one dashboard, and follow image or video jobs from submission to result with one task ID.
Explore the modelsPrices are charged per request against your balance. A request that fails is not charged. A model priced in tiers is listed at its standard rate, and a longer request can settle at a higher tier.
Generate Seedance 2.5 Flash videos in 480p or 720p. Use text, first and last frames, multimodal references or video editing, with live per-second pricing.
ByteDanceFrom $0.1200 per secondUpdated Nov 14, 2026
Grok Imagine Video 1.5 turns a prompt or one image into a 6–15 second clip with sound at 480p or 720p. Pay per second, no plan, failed runs are free.
xAIFrom $0.04 per secondUpdated Nov 9, 2026
Kling 4.0 Flash offers 20-second, 720p video with text, images, videos and Omni Reference. See pricing, API details and limits. Now available on SeedRouter.
KuaishouFrom $0.085 per secondUpdated Nov 6, 2026
Gemini Omni 1.2 Flash makes 3–15 second videos with sound from text, images or frames, and edits or extends clips, at 360p to 4K. See pricing and the API.
GoogleFrom $0.021 per secondUpdated Nov 6, 2026
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.
ByteDanceFrom $0.0703 per secondUpdated Nov 3, 2026
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.
ByteDanceFrom $0.0561 per secondUpdated Nov 3, 2026
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.
ByteDanceFrom $0.0375 per secondUpdated Nov 3, 2026
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.
ByteDanceFrom $0.1026 per secondUpdated Nov 3, 2026
Muse Video is Meta's video model. Turn a prompt or up to 9 reference images into a 10-second 720p clip with sound. One price per clip, no subscription.
MetaFrom $0.024 / clipUpdated Oct 29, 2026
PixVerse V6 makes 1–15 second clips from text, a photo, two frames or reference images, up to 1080p with optional audio. Pay per second; failed runs are free.
PixVerseFrom $0.02 per secondUpdated Oct 24, 2026
PixVerse V6 Max turns a prompt or one photo into a 1–15 second clip at up to 1080p, with optional audio. Pay per second, no plan; failed runs are free.
PixVerseFrom $0.024 per secondUpdated Oct 24, 2026
Kling 4.0 brings 30-second video, 10 keyframes and stereo sound. Explore its features, pricing and Flash differences. Now available on SeedRouter.
KuaishouFrom $0.1425 per secondUpdated Oct 22, 2026
MiniMax H3 makes 4–15 second clips at 768P or 2K with audio from text, frames or reference images, video and audio. Official request format, pay per second.
MiniMaxFrom $0.015385 per secondUpdated Oct 20, 2026
Create MiniMax H3 Max videos from text, frames or reference media. Choose 480P or 768P, control prompt expansion, and see live prices before you generate.
MiniMaxFrom $0.045703125 per secondUpdated Oct 20, 2026
Create short videos with MiniMax H3 Max Turbo from text or first and last frames. Try 480P or 768P, compare live prices, and see a real generated sample.
MiniMaxFrom $0.0228515625 per secondUpdated Oct 20, 2026
Kling 3.0 makes 3–15 second clips from text or a first and last frame, with optional native sound, up to five shots and up to 4K. Pay per second, no plan.
KuaishouFrom $0.08064 per secondUpdated Oct 6, 2026
Kling 3.0 Turbo makes 3–15 second clips with sound from a prompt or a first frame, at 720p or 1080p. Pay per second, no plan, failed runs free.
KuaishouFrom $0.13728 per secondUpdated Oct 6, 2026
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.
GoogleFrom $0.0105 per secondUpdated Oct 4, 2026
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.
SeedRouterFrom $0.0200 per secondUpdated Oct 3, 2026
Use Gemini 4 Hydrogen for coding and agent workflows with native Gemini requests, four thinking levels, 1M-token context and live prices. Try the Playground.
GoogleInput $0.675Output $3.375 / 1M tokensUpdated Nov 13, 2026
Create and edit pictures with MiniMax H3 Image. Combine up to 16 references, choose exact dimensions or 1K–4K output, and check live token prices.
MiniMaxInput $2.25Output $3.75 / 1M tokensUpdated Nov 12, 2026
Create and edit pictures with MiniMax H3 Image Highspeed. Combine up to 16 references, choose exact dimensions or 1K–4K output, and check live token prices.
MiniMaxInput $2.25Output $7.50 / 1M tokensUpdated Nov 12, 2026
Call Gemini 4 Carbon with native Gemini requests: 1M-token context, long decode, three thinking levels and live per-token prices. Test it in the Playground.
GoogleInput $0.90Output $4.50 / 1M tokensUpdated Nov 11, 2026
Try Claude Fable 5.2 for coding and problem solving with a 1M-token context. Compare live token prices and model tiers, then test it in the playground.
AnthropicInput $2.80Output $14.00 / 1M tokensUpdated Nov 10, 2026
Try Claude Mythos 5 for complex reasoning and research with a 1M-token context. Compare live token prices and model tiers, then test it in the playground.
AnthropicInput $3.50Output $17.50 / 1M tokensUpdated Nov 10, 2026
Try Claude Mythos 5.1 for research and agent workflows with a 1M-token context. Compare live token prices and model tiers, then test it in the playground.
AnthropicInput $3.50Output $17.50 / 1M tokensUpdated Nov 10, 2026
Try GLM-5.3 for coding, long document review and tool workflows. Explore reasoning controls, live token pricing and complete developer examples.
Z.aiInput $1.12Output $3.52 / 1M tokensUpdated Oct 29, 2026
Try Kimi K3.1 Pro for coding, document review and tool workflows. Explore its million-token context, reasoning controls and live token prices.
Moonshot AIInput $1.60Output $8.00 / 1M tokensUpdated Oct 25, 2026
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.
MiniMaxInput $0.09Output $0.36 / 1M tokensUpdated Oct 20, 2026
Use Gemini 3.1 Pro for coding and multimodal analysis. Explore thinking levels, a 1M-token input window, native requests and live token prices.
GoogleInput $0.90Output $5.40 / 1M tokensUpdated Oct 17, 2026
Use Gemini 3.8 Flash for multimodal reasoning and structured text. Explore native requests, thinking levels, live group prices and the Playground.
GoogleInput $0.675Output $3.375 / 1M tokensUpdated Oct 17, 2026
Gemini 4 Argon is Google's frontier model for long-horizon coding, legal and finance work, and cyber defense, with 1M-token output. Release status, benchmarks.
GoogleInput $0.90Output $4.50 / 1M tokensUpdated Oct 14, 2026
Try Grok 4.7 for coding, image analysis and research. Compare live token prices, choose reasoning effort and test Chat, Responses or Messages with one key.
xAIInput $1.20Output $3.60 / 1M tokensUpdated Oct 10, 2026
Try Claude Haiku 5.5 for classification, extraction and summaries. See live token prices, test your prompts, and connect your app with the Messages API.
AnthropicInput $0.035Output $0.175 / 1M tokensUpdated Oct 9, 2026
Try Claude Sonnet 5.5 for code reviews and document questions. See live token prices, test a prompt, and check verified capabilities before connecting your app.
AnthropicInput $0.70Output $3.50 / 1M tokensUpdated Oct 8, 2026
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.
AnthropicInput $3.50Output $17.50 / 1M tokensUpdated Oct 8, 2026
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.
AnthropicInput $3.50Output $17.50 / 1M tokensUpdated Oct 8, 2026
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.
AnthropicInput $1.40Output $7.00 / 1M tokensUpdated Oct 8, 2026
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.
OpenAIInput $1.00Output $5.00 / 1M tokensUpdated Oct 8, 2026
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.
OpenAIInput $0.20Output $1.00 / 1M tokensUpdated Oct 8, 2026
Call GPT-6.1 Sol with the OpenAI SDK: near-Astra coding and agent work at a fifth of the price, 1.05M-token context, 95% off cached input. Try it now.
OpenAIInput $0.20Output $1.00 / 1M tokensUpdated Oct 8, 2026
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.
OpenAIInput $0.01Output $0.05 / 1M tokensUpdated Oct 8, 2026
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.
Moonshot AIInput $2.40Output $12.00 / 1M tokensUpdated Oct 8, 2026
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.
DeepSeekInput $0.24Output $0.96 / 1M tokensUpdated Oct 8, 2026
Make, edit and split images into layers with Seedream 5.5. Add up to 10 references, read the text in a poster back, and see the live per-image price first.
ByteDanceFrom $0.017 per imageUpdated Nov 10, 2026
Generate and edit images with GPT Image 2.6 on SeedRouter. Try Sunburst, animated GIF and SVG output, complexity controls and current model pricing.
OpenAIFrom $0.018574 per imageUpdated Nov 5, 2026
Create, edit and split images into layers with Seedream 5.0 Pro. Combine up to 10 references, set exact pixel sizes, and see the live per-image price first.
ByteDanceFrom $0.03375 per imageUpdated Nov 2, 2026
Muse Image is Meta's image model. Create pictures from text or up to 9 reference images in seven aspect ratios. One price per image, no subscription.
MetaFrom $0.0048 per imageUpdated Oct 29, 2026
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.
Black Forest LabsFrom $0.00753 per imageUpdated Oct 21, 2026
Explore Midjourney V8.2 for visual concepts, style references and HD images. Compare versions, check task prices and follow a documented image workflow.
MidjourneyFrom $0.08 / jobUpdated Oct 18, 2026
Create and edit images with GPT Image 2 on SeedRouter. Use text prompts, reference images and transparent backgrounds, with a live playground and usage-based pricing.
OpenAIFrom $0.00425 per imageUpdated Oct 10, 2026
Generate and edit images with GPT Image 2.5 Flare or Sunburst on SeedRouter. Six quality steps up to max, transparent backgrounds, a live playground and pay-as-you-go pricing.
OpenAIFrom $0.00448 per imageUpdated Oct 10, 2026
Nano Banana 2.1, Google's update to Nano Banana 2: create and edit images with sharper text, 1K to 4K, 14 aspect ratios and 14 references, one price per image.
GoogleFrom $0.021 per imageUpdated Oct 10, 2026
Create and edit images with Nano Banana 2 (Gemini 3.1 Flash Image): 512px to 4K, 14 aspect ratios, up to 14 references. Pay per image or per token.
GoogleFrom $0.01875 per imageUpdated Sep 25, 2026
Create and edit images with Nano Banana Pro (Gemini 3 Pro Image): 1K to 4K output, built-in thinking, up to 14 references. Pay per image or per token.
GoogleFrom $0.01875 per imageUpdated Sep 25, 2026
Create and edit images with Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image), Google's fastest and cheapest image model: 1K output, 14 aspect ratios.
GoogleFrom $0.02565 per imageUpdated Sep 25, 2026
Transcribe recordings with Whisper-1. Get readable text, word timestamps and subtitle files, check live pricing, and try your own audio online on SeedRouter.
OpenAIFrom $0.036 / minuteUpdated Oct 19, 2026
Top up a balance in USD and spend it across every model on SeedRouter. Every model lists its price, and a request that fails costs nothing.
One USD paid is one USD of balance. Pick an amount, pay by card, and start calling.
Everything you need to know before building on SeedRouter.
SeedRouter is one API in front of image, video, language and audio models. You create one key, load a balance and call any model with the same request shape and the same billing. It replaces separate accounts, keys and invoices for each model vendor with a single integration.
Every model on SeedRouter has a listed price: per request, per image, per second of video or per token. You are charged when the output is delivered and nothing for failed requests. There is no subscription and no monthly minimum.
The request returns an error instead of a result, and you are not charged for it. Retry when the model is back, or send the same request to another model on SeedRouter with the same key and the same request shape.
Yes. Language models are served through an OpenAI-compatible endpoint. Point the SDK at SeedRouter, use your SeedRouter key and keep your existing code.
Video and some image and audio models run as tasks. The request returns a task id; poll it or register a webhook, and the output arrives as a CDN link when it is ready.
Image, video, language and audio families, including GPT, Claude, Gemini and GPT Image, plus video and image families such as Seedance, Flux and Qwen Image. The full list with prices is on the models page, and it grows without changes on your side.
No. Top up a balance in USD and spend it across every model on SeedRouter. Unused balance stays in your account.
Yes. SeedRouter is built for products, not demos: per-request billing you can audit, webhooks for long jobs, and no charge for requests that fail.
Guides, comparisons, and deep dives on AI image, video, and model APIs.

Gemini 4 Argon
Gemini 4 Hydrogen vs Argon: compare thinking defaults, context and output limits, current prices and three API checks before choosing a model for your own work.

Image Editing
Write MiniMax H3 Image edit prompts that separate what stays from what changes, with reference numbering, a real jewelry edit and a practical review checklist.

Pricing
Seedance 2.5 Flash pricing explained: official BytePlus rates, 720p clip estimates, reference-video billing and why a lower token rate can mean a larger bill.

Release
Seedance 2.5 Flash is announced, with official API access scheduled for November 15. See the opening time, confirmed limits and current SeedRouter availability.
One key. Every model. Pay per request. Start building on SeedRouter today.