kimi-k3
Moonshot's flagship open model: frontier coding, agents, multimodal, 1M context.
Value rank
#17 of 17
intelligence per dollar in our catalogue
Context rank
#1 tied
1M token window
Benchmarks
Independent scores by Artificial Analysis, compared with the strongest models in our catalogue.
Intelligence index
Coding index
Best for
Where this model earns its keep.
The numbers
Pricing is live from our platform. Prices per 1M tokens, zero data retention on every request.
| Input price | $3.00 |
| Cache read price | $0.75 |
| Output price | $15.00 |
| Context window | 1M tokens |
| Intelligence / coding index | 59.7 / 76.2 |
| GPQA / MMLU-Pro | 94% / - |
Or consider
Close alternatives in the catalogue.
glm-5.3
Intelligence 59.5 · agentic -
qwen3.8-2.4t-a95b
Intelligence 58.1 · agentic -
qwen3.8-flash-next
Intelligence 55.8 · agentic -
Quick start
OpenAI-compatible. Switch in one line.
client = OpenAI(base_url="https://api.tensorx.ai/v1", api_key="tsx-...")
r = client.chat.completions.create(
model="moonshotai/kimi-k3",
messages=[{"role": "user", "content": "Hello"}],
)
Benchmark data from the Artificial Analysis Intelligence Index v4.1, measured independently. Pricing live from the TensorX platform. All inference on EU-sovereign infrastructure with zero data retention.