ABAB 6.5s
Balanced
MiniMax's ABAB 6.5s, speed-tuned chat model. Common backend for the MiniMax assistant apps.
ABAB 6.5s is a frontier AI model from MiniMax. It costs $1.000 per million input tokens and $5.000 per million output tokens (blended $2.200/M), with a 8,000-token context window.
INPUT
$1.000/M
per million input tokens
OUTPUT
$5.000/M
per million output tokens
CONTEXT
8,000
tokens
What it is good at
- Fast Chinese chat
- Tool use
- Multilingual
Typical use cases
- Production Chinese chat
- Assistant backends
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 MiniMax
See all 5 →Frequently asked questions
How much does ABAB 6.5s cost?
ABAB 6.5s costs $1.000 per million input tokens and $5.000 per million output tokens, for a blended reference rate of $2.200 per million tokens.
What is ABAB 6.5s's context window?
ABAB 6.5s supports up to 8,000 tokens of context in a single request.
What is ABAB 6.5s best for?
ABAB 6.5s is well suited to Fast Chinese chat, Tool use and Multilingual.
Who makes ABAB 6.5s?
ABAB 6.5s is developed and served by MiniMax.