Question 1

What is Kimi K2 Instruct?

Accepted Answer

Kimi K2 Instruct is a model from Moonshot, released on Jul 11, 2025. Kimi-K2-Instruct has strong tool-calling capabilities. To enable them, you need to pass the list of available tools in each request, then the model will autonomously decide when and how to invoke them.

Question 2

How much does Kimi K2 Instruct cost?

Accepted Answer

On the Respan gateway, input starts at $0.51 per 1M tokens on Novita, and output starts at $2.07 per 1M tokens on Novita, after gateway discounts. Averaged across 4 providers, it costs $0.57 per 1M input tokens and $2.34 per 1M output tokens.

Question 3

Which providers serve Kimi K2 Instruct on Respan?

Accepted Answer

4 providers serve Kimi K2 Instruct: Novita, IO.net, and Featherless.

Question 4

What is Kimi K2 Instruct's context window?

Accepted Answer

Kimi K2 Instruct accepts up to 262K tokens of context on its largest provider route.

Question 5

How do I use Kimi K2 Instruct with the Respan gateway?

Accepted Answer

Point any OpenAI-compatible SDK at https://api.respan.ai/api/ with your Respan API key and set the model to "kimi-k2-instruct". To set it up with a coding agent, copy the agent setup prompt at the top of this page.

Question 6

How fast is Kimi K2 Instruct?

Accepted Answer

Over the last 30 days of requests through the Respan gateway, the fastest provider was Novita at 11 tokens per second, and the lowest response latency was 1.2 seconds on IO.net. Speed varies with request size and provider.

Provider	Context	Input	Output
NovitaSave 10%`novita/moonshotai/kimi-k2-instruct`	131K	$0.51/M	$2.07/M
IO.net`ionet/moonshotai/Kimi-K2-Instruct-0905`	262K	$0.57/M	$2.30/M
Featherless`featherless_ai/moonshotai/Kimi-K2-Instruct`	33K	$0.60/M	$2.50/M
Featherless`featherless_ai/moonshotai/Kimi-K2-Instruct-0905`	33K	$0.60/M	$2.50/M

Kimi K2 Instruct

Providers

Certified where it counts.

Pricing

Cost by volume

Throughput and latency

Output speed

Response latency

Apps

Kimi K2 Instruct FAQ

Works with your entire stack

Built for AI agents.
Break less.
Ship more.