Context
1.0M tokens (~524 books)
Input $/1M
$3.00
Output $/1M
$15.00
Type
multimodal
License
Proprietary
Benchmarks
0 tested
Data as of
About
Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI. It is suited for complex coding, knowledge work, and long-horizon agentic workflows, and is particularly strong at...
No benchmark data available yet.
Recently Happened
Kimi K3 (batch) added
Aug 29, 2026
Links
Research
Documentation
Community
BenchGecko API
kimi-k3-batch
Specifications
- Typemultimodal
- Context1.0M tokens (~524 books)
- ReleasedJul 2026
- LicenseProprietary
- StatusActive
- Cost / Message~$0.021
Available On
Learn More
Share & Export
Frequently Asked Questions
Kimi K3 (batch) is a proprietary multimodal AI model by moonshotai, released in July 2026. Context window: 1M tokens.
Related Models
Qwen3 Coder Next FP8 · AlibabaQwen2.5 Coder 32B Instruct AWQ · AlibabaSpeaker Diarization Community 1 · PyannoteGemma 3 12B (free) · Google DeepMindQwen3 Next 80B A3B Instruct (free) · Alibaba QwenBenchmarks
Key facts · as of 2026-10-05
- Kimi K3 (batch) by moonshotai. Not enough public benchmark scores to rank yet.
- List price $3.00 input · $15.00 output per 1M tokens (as of 2026-10-05).
- Sold by 1 provider (as of 2026-10-05): DeepInfra (bf16) $2.28 in / $11.40 out.
How to cite · data as of 2026-10-05
Kimi K3 (batch) · benchmarks, pricing and providers. BenchGecko, data as of 2026-10-05. https://benchgecko.ai/model/kimi-k3-batch
Credit "Source: BenchGecko" with a link. Prices per provider and Gecko Tests are BenchGecko data (CC BY 4.0); benchmark scores keep their original source, listed in the JSON. JSON · llms.txt · MCP