Doubao-Lite-32k
Budget
Cheap, fast Doubao Lite. Bulk classification and routing for Chinese-first apps on Volcengine.
Doubao-Lite-32k is a efficient AI model from ByteDance. It costs $0.040 per million input tokens and $0.090 per million output tokens (blended $0.055/M), with a 32,000-token context window.
INPUT
$0.040/M
per million input tokens
OUTPUT
$0.090/M
per million output tokens
CONTEXT
32,000
tokens
What it is good at
- Cheapest Doubao tier
- Sub-second latency
- Chinese-tuned
Typical use cases
- Bulk Chinese classification
- Cheap routing layer
Benchmarks
No published benchmark scores tracked for this model yet. Frontier and reasoning models from major providers have scores; smaller models and inference-host variants typically inherit the underlying open-weights score.
More from ByteDance
See all 5 →Frequently asked questions
How much does Doubao-Lite-32k cost?
Doubao-Lite-32k costs $0.040 per million input tokens and $0.090 per million output tokens, for a blended reference rate of $0.055 per million tokens.
What is Doubao-Lite-32k's context window?
Doubao-Lite-32k supports up to 32,000 tokens of context in a single request.
What is Doubao-Lite-32k best for?
Doubao-Lite-32k is well suited to Cheapest Doubao tier, Sub-second latency and Chinese-tuned.
Who makes Doubao-Lite-32k?
Doubao-Lite-32k is developed and served by ByteDance.