Skip to content
ModelCap

Inference provider

Seed: AI models and API pricing

Every tracked model Seed serves through OpenRouter, with Seed's own input and output price per 1M tokens, the context window it serves, disclosed quantization and measured endpoint uptime. Rows link to the model page, where every provider's deployment is listed side by side.

Snapshot as of 11 August 2026

Seed serves 4 tracked models through 4 endpoints as of 11 August 2026; the highest-ranked is Seed 1.6 Flash (ModelCap Index #106); mean measured uptime is 100.0%.

Models served
4
On the ModelCap Index
4
Cheapest output price
$0.30/1M

Language models on Seed (4)

Ranked models first, in ModelCap Index order. Prices are the lowest Seed lists for the model; the endpoint count shows how many deployments carry it.

Language models served by Seed, with price, context, quantization and uptime
#ModelModelCap IndexInput $/1MOutput $/1MContextQuantizationUptime (30 min)Endpoints
1Seed 1.6 FlashByteDance Seed#10625.5$0.075$0.30262Kfp8100.0%1
2Seed 1.6ByteDance Seed#10725.5$0.25$2.00262Kfp8—1
3Seed-2.0-LiteByteDance Seed#10825.5$0.25$2.00262Kfp8100.0%1
4Seed-2.0-MiniByteDance Seed#10925.5$0.10$0.40262Kfp8100.0%1

Seed on ModelCap: common questions

How many AI models does Seed serve?

4 tracked models as of 11 August 2026: 4 language models (4 with a public ModelCap Index position), across 4 live endpoints observed through OpenRouter.

What is the best model available on Seed?

Seed 1.6 Flash from ByteDance Seed is the highest-ranked language model Seed serves, at ModelCap Index position #106 and $0.30 per 1M output tokens on Seed. The table lists every model in Index order.

What is the cheapest model on Seed?

Seed 1.6 Flash at $0.30 per 1M output tokens ($0.075 per 1M input), the lowest positive language-token price Seed lists. Free-tier endpoints, where present, show as $0 and are excluded from that comparison.

Which Seed model has the largest context window?

Seed 1.6 Flash, served with a 262K-token context window on Seed. Providers sometimes serve less than the model's published maximum, so the figure here is the provider's own.

How reliable is Seed?

Mean measured uptime across Seed endpoints is 100.0% over the last 30 minutes, as reported by OpenRouter at the time of the snapshot. Per-model uptime is in the table; it is a live operational signal, not a service-level guarantee.

Where do the Seed prices come from?

From the OpenRouter catalogue entry for each Seed endpoint, in USD per 1M tokens, re-observed on every ModelCap refresh. Where Seed exposes several deployments of one model at different prices, the table shows the lowest and notes the count; the model page lists each deployment.

How current is this page?

It re-renders within a minute of every dataset refresh; this snapshot was published 11 August 2026. Offers retained from a failed refresh are marked stale in the data and are not counted here.

Explore further