Claude Fable 5$22.000/MClaude Opus 5$11.000/MClaude Opus 4.8$11.000/MClaude Opus 4.7$11.000/MClaude Opus 4.6$11.000/MClaude Opus 4.5$33.000/MClaude Sonnet 3.7$6.600/MClaude Opus 3$33.000/MClaude 2.1$12.800/MClaude 2$12.800/MGPT-5.6 Sol$12.500/MGPT-5.6 Terra$5.000/MGPT-5.5$12.500/MGPT-5.2$5.425/MGPT-5.2-Codex$5.425/MGPT-5$3.875/MGPT-4.5$97.500/MGPT-4 Turbo Preview$16.000/MGPT-4$39.000/MGPT-4-32k$78.000/Mo3$19.000/Mo3-mini$2.090/Mo4-mini$2.090/Mo1$28.500/Mo1-mini$5.700/Mo1-preview$28.500/MGemini 3.5 Pro$5.000/MGemini 3.1 Pro$5.000/MGemini 3 Pro$5.000/MGemini 2.5 Pro$3.875/MClaude Fable 5$22.000/MClaude Opus 5$11.000/MClaude Opus 4.8$11.000/MClaude Opus 4.7$11.000/MClaude Opus 4.6$11.000/MClaude Opus 4.5$33.000/MClaude Sonnet 3.7$6.600/MClaude Opus 3$33.000/MClaude 2.1$12.800/MClaude 2$12.800/MGPT-5.6 Sol$12.500/MGPT-5.6 Terra$5.000/MGPT-5.5$12.500/MGPT-5.2$5.425/MGPT-5.2-Codex$5.425/MGPT-5$3.875/MGPT-4.5$97.500/MGPT-4 Turbo Preview$16.000/MGPT-4$39.000/MGPT-4-32k$78.000/Mo3$19.000/Mo3-mini$2.090/Mo4-mini$2.090/Mo1$28.500/Mo1-mini$5.700/Mo1-preview$28.500/MGemini 3.5 Pro$5.000/MGemini 3.1 Pro$5.000/MGemini 3 Pro$5.000/MGemini 2.5 Pro$3.875/M
Tokenando
BETA
Subscribe
← Back to Index
kwaipilot
kwaipilot
EfficientAUTO PROFILELIVE INDEX

KAT-Coder-Air V2.5

text->text

KAT-Coder-Air V2.5 is a code-specialist variant tuned for completion, refactoring, and test generation across major programming languages. Available via kwaipilot. 256,000-token context. Efficient pricing.

KAT-Coder-Air V2.5 is a efficient AI model from kwaipilot. It costs $0.150 per million input tokens and $0.600 per million output tokens (blended $0.285/M), with a 256,000-token context window.

Modalities textPricing source ↗Compare with another model →Estimate monthly cost →
INPUT
$0.150/M
per million input tokens
OUTPUT
$0.600/M
per million output tokens
BLENDED 70/30
$0.285/M
default reference rate · how it is calculated →
CONTEXT
256,000
tokens
What it is good at
  • Code completion across languages
  • Multi-file refactoring
  • Test generation
  • Debugging from stack traces
Typical use cases
  • Pair-programming copilots
  • Codebase refactors
  • Code review automation
  • Repo-scale agents

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 kwaipilot

See all 2 →
KAT-Coder-Pro V2.5
text->text · 256,000 ctx
in $0.740/Mout $2.960/M
KAT-Coder-Pro V2
text->text · 262,144 ctx
in $0.300/Mout $1.200/M

Frequently asked questions

How much does KAT-Coder-Air V2.5 cost?

KAT-Coder-Air V2.5 costs $0.150 per million input tokens and $0.600 per million output tokens, for a blended reference rate of $0.285 per million tokens.

What is KAT-Coder-Air V2.5's context window?

KAT-Coder-Air V2.5 supports up to 256,000 tokens of context in a single request.

What is KAT-Coder-Air V2.5 best for?

KAT-Coder-Air V2.5 is well suited to Code completion across languages, Multi-file refactoring and Test generation.

Who makes KAT-Coder-Air V2.5?

KAT-Coder-Air V2.5 is developed and served by kwaipilot.

Terms used on this page

Full glossary →
TokenInput tokensOutput tokensPrice per million tokensContext windowPrompt cachingBatch APIBlended cost