MiniMax
MiniMax
Efficient

ABAB 6.5t

Turbo

Cheap ABAB 6.5 tier. Bulk Chinese chat and routing at the low-end of the MiniMax lineup.

ABAB 6.5t is a efficient AI model from MiniMax. It costs $0.450 per million input tokens and $0.450 per million output tokens (blended $0.450/M), with a 8,000-token context window.

INPUT
$0.450/M
per million input tokens
OUTPUT
$0.450/M
per million output tokens
BLENDED 70/30
$0.450/M
unchanged since 3 May
CONTEXT
8,000
tokens
What it is good at
  • Cheap
  • Fast
  • Chinese-tuned
Typical use cases
  • Bulk Chinese classification
  • Cheap chat

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 6.5t cost?

ABAB 6.5t costs $0.450 per million input tokens and $0.450 per million output tokens, for a blended reference rate of $0.450 per million tokens.

What is ABAB 6.5t's context window?

ABAB 6.5t supports up to 8,000 tokens of context in a single request.

What is ABAB 6.5t best for?

ABAB 6.5t is well suited to Cheap, Fast and Chinese-tuned.

Who makes ABAB 6.5t?

ABAB 6.5t is developed and served by MiniMax.

Terms used on this page