Kimi K3 (Low)
KimiKimi
Release Date
2026-07-16
Parameters
—
Context Length
1.0M
Modalities
image, text, video
Capability Radar
29
general
69
coding
84
reasoning
61
science
80
agents
90
multimodal
Rankings
No ranking data available
Benchmark Scores (LLM Stats)
(LLM Stats (zeroeval))No benchmark data available
AA Evaluation Indices
(Artificial Analysis)Gpqa(NYU + Cohere + Anthropic (2023))84.2
Terminalbench V2 182.4
Lcr(Artificial Analysis)79.3
Coding Index(Artificial Analysis)72.0
Scicode(UIUC + Argonne National Lab (2024))52.7
Tau Banking41.6
Intelligence Index(Artificial Analysis)30.1
Hle(Center for AI Safety + Scale AI (2025))25.0
Terminalbench V4 012.6
LLM Stats Category Scores
(LLM Stats (zeroeval))No category score data available
Pricing
Input Price$3 / 1M tokens
Output Price$15 / 1M tokens
Blended Price (3:1)$6 / 1M tokens
Cache Read Price$0.21 / 1M tokens
Speed
Tokens/sec36.6
Time to First Token2.74s
Time to Answer57.32s
Provider Price Ranking
Provider Price Ranking
19 providers
Cheapest: OpenRouterMost Expensive: Prime Inference
ProviderInputOutput
1OpenRouterCheapest
$0.239
$10.8
2NanoGPT
$1.2
$5.5
3IteraCompute
$2.35
$11.76
4Wallaby
$2.7
$13.5
5KimiPRIMARY
$3
$15
6ZenMux
$3
$15
7Novita AI
$3
$15
8Kilo Gateway
$3
$15
9Cloudflare AI Gateway
$3
$15
10Vercel AI Gateway
$3
$15
11Ofox
$3
$15
12ai&
$3
$12.5
13TensorX
$3
$15
14Impossibl
$3
$15
15Arcee
$3
$15
16Standard Compute
$3
$15
17TokenGo
$3
$15
18NEAR AI Cloud
$3.3
$16.5
19Prime Inference
$3.45
$17.25
Compare pricing across different API providers for this model.