Moonshot v1 32k
Balanced
32K-context Moonshot v1. Mid-tier of the v1 line, cheaper than 128K when full long context isn't needed.
Moonshot v1 32k is a efficient AI model from Moonshot AI. It costs $0.400 per million input tokens and $0.400 per million output tokens (blended $0.400/M), with a 32,000-token context window.
INPUT
$0.400/M
per million input tokens
OUTPUT
$0.400/M
per million output tokens
CONTEXT
32,000
tokens
What it is good at
- 32K context
- Cheap Chinese chat
Typical use cases
- Chinese-first chat apps
- Mid-context RAG
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 Moonshot AI
See all 5 →Frequently asked questions
How much does Moonshot v1 32k cost?
Moonshot v1 32k costs $0.400 per million input tokens and $0.400 per million output tokens, for a blended reference rate of $0.400 per million tokens.
What is Moonshot v1 32k's context window?
Moonshot v1 32k supports up to 32,000 tokens of context in a single request.
What is Moonshot v1 32k best for?
Moonshot v1 32k is well suited to 32K context, Cheap Chinese chat and Chinese-first chat apps.
Who makes Moonshot v1 32k?
Moonshot v1 32k is developed and served by Moonshot AI.