One agent session
1M input tokens and 100K output tokens, no caching.
- Input1M x $0.50 = $0.50
- Output0.1M x $2.50 = $0.25
$0.75per session
ByteDance Seed - Closed weights
Dola Seed 2.1 Turbo pricing and specs
Dola Seed 2.1 Turbo is a closed-weights model from ByteDance Seed that costs $0.50 per 1M input tokens and $2.50 per 1M output tokens on the first-party API, with a 256K-token context window.
Last verified from docs.byteplus.com. All sources
- Input / 1M
- $0.50
- Output / 1M
- $2.50
- Context
- 256K tokens
- Weights
- Closed
Pricing per 1M tokens
| Item | Price / 1M tokens |
|---|---|
| Input | $0.50 |
| Output | $2.50 |
| Cache read | $0.10 |
| Batch inputBatch requests | $0.25 |
| Batch outputBatch requests | $1.25 |
Note: BytePlus ModelArk online inference (standard) prices, single tier for prompts [0, 256K]. Cache-hit input is 0.1. ModelArk bills cache storage at 0.0083 USD per M tokens per hour instead of a cache write fee, so cache write is not stated. Online inference (Flex) is 0.25 input / 1.25 output / 0.10 cache-hit, with implicit caching only and no storage fee. Batch inference is 0.25 input / 0.10 cache-hit / 1.25 output. The pricing page lists the unversioned id dola-seed-2-1-turbo; the model list gives the version dola-seed-2-1-turbo-260628. The model list states context length 256K, max input 256K and max output 256K including chain of thought (default 4K); BytePlus writes K as 1,000 (its own config examples render 256K as 256000 and 1024K as 1024000). The release date is left blank because the release notes list it only under month 202607, with no day. Text, image and video input. Gateway price matched first-party on 2026-10-17.
Specs
- Context window
- 256,000 tokens
- Max output
- 256,000 tokens
- Provider
- ByteDance Seed
- API model id
dola-seed-2-1-turbo-260628- Vercel AI Gateway id
bytedance/seed-2.1-turbo- Weights
- Closed weights
What Dola Seed 2.1 Turbo costs in practice
Worked from the standard list rates above, with the math shown so you can swap in your own token counts.
A chat app
10,000 requests a day at 2K input and 500 output tokens each.
- Input20M x $0.50 = $10.00
- Output5M x $2.50 = $12.50
$22.50per day
$675.00 per 30-day month
The same session at a 90% cache hit
90% of the input is read from the prompt cache. The one-time cache write premium is not included.
- Cached input0.9M x $0.10 = $0.09
- Uncached input0.1M x $0.50 = $0.05
- Output0.1M x $2.50 = $0.25
$0.39per session
Compare with
| Model | Input / 1M | Output / 1M |
|---|---|---|
| Dola Seed 2.1 Turbo (this page) | $0.50 | $2.50 |
| Amazon Nova 2 LiteAmazon | $0.30 | $2.50 |
| Gemini 2.5 FlashGoogle | $0.30 | $2.50 |
| Gemini 3.5 Flash-LiteGoogle | $0.30 | $2.50 |
| Grok 4.20xAI | $1.25 | $2.50 |
| Seed 2.0 LiteByteDance Seed | $0.25 | $2 |
| Seed 2.0 ProByteDance Seed | $0.50 | $3 |
| Seed 2.0 MiniByteDance Seed | $0.10 | $0.40 |
FAQ
How much does Dola Seed 2.1 Turbo cost per million tokens?
Dola Seed 2.1 Turbo costs $0.50 per 1M input tokens and $2.50 per 1M output tokens on ByteDance Seed's first-party API, per docs.byteplus.com on October 17, 2026. Per 1M tokens, cache reads cost $0.10, and the batch rate is $0.25 input and $1.25 output.
What is Dola Seed 2.1 Turbo's context window?
Dola Seed 2.1 Turbo has a 256,000-token context window and returns up to 256,000 output tokens per response.
Are Dola Seed 2.1 Turbo's weights open?
No. Dola Seed 2.1 Turbo is a closed-weights model. You call it through ByteDance Seed's API as dola-seed-2-1-turbo-260628 or through Vercel AI Gateway as bytedance/seed-2.1-turbo.
Sources
Last verified from docs.byteplus.com.
Newsletter
Get model price changes as they ship
One email per week. New model releases, price cuts and what they mean for your bill.