language
license
library_name
pipeline_tag
tags
metrics
model-index
en
zh
es
fr
de
ja
ko
ru
ar
pt
it
hi
proprietary
hanzo
feature-extraction
decision-intelligence
long-context
modernbert
structured-prediction
32k-context
api-only
needle_in_a_haystack
brier_score
expected_calibration_error
name
results
hanzoai/kai-1.4
task
metrics
type
name
long-context-retrieval
Needle in a Haystack (31K)
type
value
name
accuracy
0.733
Retrieval Accuracy
task
metrics
type
name
long-context-retrieval
Needle in a Haystack (8K)
type
value
name
accuracy
0.733
Retrieval Accuracy
Kai-1.4: Long-Context Decision Research Model
⚠️ API-only · Weights not distributed POST /v1/decisions with model: "kai-1.4".
1. Model Overview
Kai-1.4 extends Kai's decision encoder to a native 32,768-token reach , enabling structured decision-making over entire codebases, multi-turn agent conversation histories, legal contracts, and dense log traces without truncation.
Primary Endpoint : https://api.hanzo.ai/v1/decisionsIdentifier : kai-1.4Context Capacity : 32,768 tokens (stretched via YaRN 4x rotary scaling)Parameters : 382.3MServing Rate : Standard Kai rate ($0.021 / million input tokens)
2. Long-Context Benchmarks
Evaluated on long-context synthetic needles and document reasoning suites:
Benchmark
Context Length
Kai-1.4 Result
Qualification Bar
Status
Needle in a Haystack (31K) 31,000 tokens
0.733 0.700
MET
Needle in a Haystack (8K) 8,000 tokens
0.733 0.800
Research preview
32K CPU Inference Latency 31,800 tokens
65.0 s (24T)
—
CPU baseline
32K GPU Inference Latency 31,800 tokens
1.1 s (BF16)
—
Production GPU
3. Cryptographic Verification & Hashes
Weights SHA-256 : c1856a77730f33781dd4ca662a629051d445b50a52d3ea012c9492395461f52aRepresentation Hash : faeca4548fcabf3233832a6aa13dfd74f7dac4dd74650017fc6e753caa8ab1ddCalibration Digest : cal_68c2d5e983f2705dImage Digest : v0.4.8@sha256:e495dd5f98a1a5b93c26d278e3aa122417b3cbc4c4ea0d2ef4902dffa545825a
4. Related Resources
