Add to ChromeCompare models
Put models side by side on price, context, capabilities, and benchmarks.
KAT-Coder-Air V2.5 is a lighter, faster member of Kwaipilot's KAT-Coder agentic coding model family, trained on large numbers of verifiable repository environments. It is designed for autonomous software engineering tasks like issue resolution and repo-level code changes, optimized for lower cost and latency than the Pro variant.
Cost rate
0.1x
Context
256K
Input
Output
Reasoning
Tool calling
Structured outputs
Pricing/M tokens
Input$0.15
Cached input$0.03
Output$0.60
Context
Context length256,000
Max output tokens80,000
Knowledge cutoff-
Performance
Throughput-
Latency-
Claude Haiku 4.5 is Anthropic's fast, affordable small model in the Claude 4 generation, balancing strong instruction-following and coding ability with low latency. It is designed for high-throughput agentic and chat applications where speed and cost efficiency are priorities.
Document analysis#31Software & IT Services#100Mathematical#101Writing, Literature, & Language#109
Cost rate
1x
Context
200K
Input
Output
Reasoning
Tool calling
Structured outputs
Pricing/M tokens
Input$1.00
Cached input$0.10
Output$5.00
Context
Context length200,000
Max output tokens64,000
Knowledge cutoff-
Performance
Throughput90 tok/s
Latency1.04s
