What is Kimi K3 Fast?

Kimi K3 Fast is a model from Moonshot, released on Jul 16, 2026. Kimi K3 Fast is available on the Respan AI Gateway for production LLM workloads. Up to 1.0M context window.

How much does Kimi K3 Fast cost?

On the Respan gateway, input starts at $4.50 per 1M tokens on Inference.net, and output starts at $22.50 per 1M tokens on Inference.net, after gateway discounts.

Which providers serve Kimi K3 Fast on Respan?

2 providers serve Kimi K3 Fast: Inference.net.

What is Kimi K3 Fast's context window?

Kimi K3 Fast accepts up to 1.0M tokens of context on its largest provider route.

How do I use Kimi K3 Fast with the Respan gateway?

Point any OpenAI-compatible SDK at https://api.respan.ai/api/ with your Respan API key and set the model to "kimi-k3-fast". To set it up with a coding agent, copy the agent setup prompt at the top of this page.

How fast is Kimi K3 Fast?

Over the last 30 days of requests through the Respan gateway, the fastest provider was Inference.net at 20 tokens per second, and the lowest response latency was 1.7 seconds on Inference.net. Speed varies with request size and provider.