Seed — pricing & performance
Models served
4
of 947 tracked models
Mean output speed
59
tokens per second, averaged over
4 measured endpoints
4 measured endpoints
Mean latency
1.1s
time to first token, averaged over
4 measured endpoints
4 measured endpoints
Cheapest blended
$0.13
per 1M tokens at a 3:1
input:output blend
input:output blend
Output speed on Seed
Median output tokens per second for all 4 models on Seed with published throughput telemetry from OpenRouter. Higher is better. We do not run these measurements ourselves.
All 4 of 4 models⇩
The Known Good
4 models on Seed
Full leaderboard →
| Model | Creator | Input $/M | Output $/M | Blended | Speed | TTFT | Context |
|---|---|---|---|---|---|---|---|
ByteDance Seed: Seed 1.6
|
ByteDance | $0.25 | $2.00 | $0.69 | 44 | 0.8s | 262k |
|
ByteDance Seed: Seed 1.6 Flash
|
ByteDance | $0.075 | $0.30 | $0.13 | 65 | 0.8s | 262k |
|
ByteDance Seed: Seed-2.0-Lite
|
ByteDance | $0.25 | $2.00 | $0.69 | 56 | 2.2s | 262k |
|
ByteDance Seed: Seed-2.0-Mini
|
ByteDance | $0.10 | $0.40 | $0.17 | 70 | 0.5s | 262k |
The Known Good
Source. Prices, endpoint availability and throughput for Seed are ingested from OpenRouter;
model metadata is enriched from models.dev. A blank cell means the figure was not published for that endpoint —
it never means zero. Blended price is (3 × input + output) ÷ 4, the same 3:1 blend used everywhere on this
site; see methodology. Quality scores are not provider-specific:
a model scores the same wherever it is hosted, so quality lives on the
model pages.