KAT-Coder-Pro V2
KAT-Coder-Pro V2 is the latest high-performance model in KwaiKAT’s KAT-Coder series, designed for complex enterprise-grade software engineering and SaaS integration. It builds on the agentic coding strengths of earlier versions,...
Updated 20 min ago · first seen 11 Sept 2026
model_01M294WW2FKK355C156ZDT1X3K
- Context
- 256K tokens
- T2 · 20 min ago
- Released
- 27 Mar 2026
- T2 · 2 h ago
Specification
- Release date
- 27 Mar 2026
Source:OpenRouter public model & pricing listingT2observed 2 h agomedium
- Openness
- proprietary
Source:Artificial AnalysisT2observed 20 min agomedium
- Context window
- 256K tokens
Source:Artificial AnalysisT2observed 20 min agomedium
- Max output
- 144K tokens
Source:OpenRouter public model & pricing listingT2observed 2 h agomedium
- Modalities
- text
Source:OpenRouter public model & pricing listingT2observed 2 h agomedium
- Input modalities
- text
Source:OpenRouter public model & pricing listingT2observed 2 h agomedium
- Output modalities
- text
Source:OpenRouter public model & pricing listingT2observed 2 h agomedium
- Openrouter id
- kwaipilot/kat-coder-pro-v2
Source:OpenRouter public model & pricing listingT2observed 2 h agomedium
- Supported parameters
- frequency_penalty, logit_bias, max_tokens, min_p, presence_penalty, repetition_penalty, response_format, seed, stop, structured_outputs, temperature, tool_choice, tools, top_k, top_p
Source:OpenRouter public model & pricing listingT2observed 2 h agomedium
Each value shows its source, tier and observation time. Conflicting claims are kept side by side and flagged — never averaged. How AI Atlas records facts →
Provenance
Attributed facts
13
Source tiers
T213
Freshest observation
20 min ago
Conflicts
None
Modalities
- Modalities
- text
- Input
- text
- Output
- text
Capabilities
Tool calling
Yes
OpenRouter public model & pricing listing · T2
Structured output
Yes
OpenRouter public model & pricing listing · T2
Reasoning
No
Artificial Analysis · T2
Vision
Unavailable
Audio
Unavailable
Fine-tuning available
Unavailable
- Context window
- 256K tokens
Source:Artificial AnalysisT2observed 20 min agomedium
- Max output
- 144K tokens
Source:OpenRouter public model & pricing listingT2observed 2 h agomedium
| Benchmark | Score | Metric | Config | Evaluated | Source |
|---|---|---|---|---|---|
| τ²-bench | 89.47% | pass^1 | aa_slug=kat-coder-pro-v2 · evaluator=Artificial Analysis · index_version=4.3 | — | artificialanalysis.aiT2 |
| Artificial Analysis Intelligence Index | 21.7 | index | aa_slug=kat-coder-pro-v2 · version=4.3 · estimated=true | — | artificialanalysis.aiT2 |
| GPQA | 85.45% | accuracy | aa_slug=kat-coder-pro-v2 · variant=GPQA Diamond · evaluator=Artificial Analysis · index_version=4.3 | — | artificialanalysis.aiT2 |
| Humanity's Last Exam | 16.13% | accuracy | aa_slug=kat-coder-pro-v2 · evaluator=Artificial Analysis · index_version=4.3 | — | artificialanalysis.aiT2 |
| IFBench | 66.67% | accuracy | aa_slug=kat-coder-pro-v2 · evaluator=Artificial Analysis · index_version=4.3 | — | artificialanalysis.aiT2 |
| Terminal-Bench | 49.24% | accuracy | aa_slug=kat-coder-pro-v2 · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — | artificialanalysis.aiT2 |
| Terminal-Bench | 70.04% | accuracy | aa_slug=kat-coder-pro-v2 · variant=v2.1 · evaluator=Artificial Analysis · index_version=4.3 | — | artificialanalysis.aiT2 |
Scores are reported as published, with their evaluation configuration (harness, prompting, judge). Results with different configs are not directly comparable — see methodology.
Current prices
| Provider | Input / 1M | Output / 1M | Cached in | Batch in / out | Context | Observed | Source |
|---|---|---|---|---|---|---|---|
| OpenRouterkwaipilot/kat-coder-pro-v2 | $0.30 | $1.2 | $0.06 | — | 262.1K | 25 min ago | openrouter.aiT2 |
USD per 1M tokens as published by each provider (USD). Rows are append-only: every change is kept in the history below.
Available through 1
Price history
Input price · USD / 1M tokens
Output price · USD / 1M tokens
- OpenRouter
No hardware estimate available
No lineage recorded
Papers 0
No papers linked yet.
Repositories 0
No repositories linked yet.
As of
Rewind the record: see this entity's attributes exactly as AI Atlas knew them on a given day.
Claim history · Description
Descriptiondescription1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| KAT-Coder-Pro V2 is the latest high-performance model in KwaiKAT’s KAT-Coder series, designed for complex enterprise-grade software engineering and SaaS integration. It builds on the agentic coding strengths of earlier versions,... | → current | current | OpenRouter public model & pricing listingT2 | medium | deterministic |
Claims are temporal and append-only: a new observation closes the previous claim (valid_to) instead of overwriting it. Conflicting claims from different sources are kept side by side and flagged — never averaged. Methodology →
KAT-Coder-Pro V2 scores 49.24% on Terminal-Bench
artificial_analysisKAT-Coder-Pro V2 scores 70.04% on Terminal-Bench
artificial_analysisKAT-Coder-Pro V2 scores 89.47% on τ²-bench
artificial_analysisKAT-Coder-Pro V2 scores 66.67% on IFBench
artificial_analysisKAT-Coder-Pro V2 scores 16.13% on Humanity's Last Exam
artificial_analysisKAT-Coder-Pro V2 scores 85.45% on GPQA
artificial_analysisKAT-Coder-Pro V2 scores 21.7 on Artificial Analysis Intelligence Index
artificial_analysisKAT-Coder-Pro V2: context length changed from 262144 to 256000
Context window262.1K tokens→256K tokensartificial_analysisOpenRouter lists KAT-Coder-Pro V2 at $0.3 in / $1.2 out per 1M tokens
openrouter
| Source | Document | Type | Tier | Last observed | Snapshots |
|---|---|---|---|---|---|
| Artificial Analysis | artificialanalysis.ai/leaderboards/models | leaderboard | T2· Quality secondary | 20 min ago | 1 |
| OpenRouter public model & pricing listing | openrouter.ai/api/v1/models | catalogue | T2· Quality secondary | 25 min ago | 2 |
Tier 1 = official/primary, 2 = quality secondary, 3 = community, 4 = unverified. Every snapshot is archived; see all sources and the methodology.