Creator
Amazon
Released
2024-12-03
Intelligence
4.7
Artificial Analysis Index
Coding
—
Artificial Analysis Index
In $/1M
$0.04
input tokens
Out $/1M
$0.14
output tokens
Blended $/1M
$0.06
3:1 blended
Speed
268
tokens / sec
Profile
License, openness, and modality — the governance layer.
License
Proprietary
non-commercial
Weights
Closed
API only
Modalities
Text
Parameters
—
A text-only model that delivers lowest-latency responses at very low cost while maintaining strong performance on core language tasks. Optimized for speed and efficiency while preserving high accuracy on key benchmarks.
Capability profile
Category strength across 20 domains, via LLM Stats.
structured output
90instruction following
90code
80math
80legal
80healthcare
80general
70reasoning
70finance
60
language
60tool calling
60economics
50search
40biology
40physics
40chemistry
40long context
20summarization
20
Benchmark breakdown
Independent evaluation scores, normalized to 0–100.
GPQA Diamond
36
Humanity’s Last Exam
5
MMLU-Pro
53
SciCode
9
LiveCodeBench
14
MATH-500
70
AIME 2025
6
τ²-Bench (agentic)
14
Terminal-Bench Hard
2
IFBench
29