Kimi K3
Moonshot AI • codigo#6 of 579 in intelligence
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...
Specifications
Context Window
1.0M tokens
Input Price/1M
$3.00
#644 of 714
Output Price/1M
$15.00
Parameters
—
Speed
36 tok/s
#263 of 537
Latency (TTFT)
2.8s
Cost per Task
10.0
AA Score / US$ · higher = better
Benchmarks
Kimi K3 results on the main AI model evaluation benchmarks. Higher scores indicate better performance.
Coding
| Benchmark | Score | Maximum | Methodology |
|---|---|---|---|
| AA Coding Index | 76.2 | 100.0 | Artificial Analysis official API |
| SciCode | 59.0 | 100.0 | — |
Long Context
| Benchmark | Score | Maximum | Methodology |
|---|---|---|---|
| AA-LCR | 75.0 | 100.0 | — |
overall
| Benchmark | Score | Maximum | Methodology |
|---|---|---|---|
| AA Intelligence Index | 59.7 | 100.0 | Artificial Analysis official API |
Reasoning
| Benchmark | Score | Maximum | Methodology |
|---|---|---|---|
| GPQA Diamond | 84.2 | 100.0 | Artificial Analysis official API |
| HLE | 44.0 | 100.0 | — |
Information
- Release date
- July 16, 2026
- Tool Calling
- ✅ Supported
- Vision
- ✅ Supported
- Audio
- ❌ Not supported
Full Analysis: Kimi K3
What is Kimi K3?
Kimi K3 is an AI model developed by Moonshot AI, classified as a codigo model. It focuses on text processing and natural language generation. As a proprietary model, it is available via Moonshot AI's cloud API. With a context window of 1.0M tokens, it is suitable for processing long documents such as contracts, books, and complete codebases.
Pricing & Costs in 2026
Kimi K3 is usage-based, priced at $3/1M input tokens and $15/1M output tokens. For context: 1 million tokens is approximately 750,000 words, or about 10 average-length books. The mid-range pricing balances quality and cost for most professional applications.
Benchmarks & Performance
Kimi K3 was evaluated on 6 different benchmarks, covering categories like Coding, Long Context, overall, Reasoning. Results show solid performance across available evaluations.
It's important to note that benchmarks measure specific aspects and don't capture the full user experience. Factors like instruction adherence, behavior in long conversations, and real-world task quality vary significantly between models and aren't always reflected in standard scores.
Recommended Use Cases
Kimi K3 specializes in codigo, offering advanced capabilities for creating and processing codigo content.
Comparison with Alternatives
In the 2026 AI model ecosystem, Kimi K3 competes directly with similarly capable models. Moonshot AI competes in this segment against OpenAI, Anthropic, Google, and Meta. The choice between models depends on the specific use case, budget, latency requirements, and need for features like multimodality and tool calling.
For a detailed side-by-side comparison, use our comparison tool or check the overall model ranking.
Frequently Asked Questions
What is Kimi K3?
Kimi K3 is an AI model developed by Moonshot AI. It is a codigo model.
How much does Kimi K3 cost?
Kimi K3 costs $3/1M input tokens and $15/1M output tokens. For heavy usage (e.g., a chatbot handling 100k messages/month), costs can range from $10 to $1,000 depending on volume.
How does Kimi K3 compare with other models?
In available benchmarks, Kimi K3 scored: AA Coding Index: 76.2/100, SciCode: 59/100, AA-LCR: 75/100. See the full table above for a detailed comparison.
Is Kimi K3 open source?
No, Kimi K3 is a proprietary model from Moonshot AI. It is available via cloud API. For open source alternatives, check our open source model ranking.
What is Kimi K3 best for?
Kimi K3 excels at multimodal tasks including text and vision. With its large context window, it handles long documents, codebases, and extended conversations. It supports tool calling for API integrations and automation.
Last updated: August 12, 2026 • View methodology →