# Kimi K3 (Moonshot) — API pricing and providers

> Long-context agents. Model id `moonshot/kimi-k3`. Text model by Moonshot.

- Page: https://infro.io/models/moonshot/kimi-k3
- Vendor: Moonshot (https://infro.io/models/moonshot)
- Modality: Text
- Endpoint through INFRO: `POST /v1/chat/completions` at https://api.infro.io/v1
- List rate: $3.00 per 1M input tokens and $15 per 1M output tokens, with cached input at $0.30 per 1M tokens
- Rates checked: 2026-10-05

Rates are Moonshot's published list price: what the customer's own provider account bills, not an INFRO charge. INFRO is a BYOK control plane; it charges a software subscription and adds 0% to model spend.

## Providers that serve it

| Provider | Model id sent |
| --- | --- |
| AWS Bedrock | `global.moonshotai.kimi-k3` |
| Together AI | `moonshotai/Kimi-K3` |
| Fireworks AI | `accounts/fireworks/models/kimi-k3` |
| OpenRouter | `moonshotai/kimi-k3` |
| KIE | `kimi-k3` |
| Moonshot AI (Kimi) | `kimi-k3` |

## Questions

### How much does the Kimi K3 API cost?

Moonshot's published list rate for Kimi K3 is $3.00 per 1M input tokens and $15 per 1M output tokens, with cached input at $0.30 per 1M tokens (checked 2026-10-05). The provider account you connect bills you at the rate on that account, so a negotiated rate replaces the list rate. INFRO adds 0% to model spend.

### Which providers serve Kimi K3?

In INFRO's provider registry, Kimi K3 can be served by AWS Bedrock, Together AI, Fireworks AI, OpenRouter, KIE and Moonshot AI (Kimi). You connect your own account with any of them, and INFRO routes and fails over between the ones you connect.

### What is the Kimi K3 model ID?

Request it from INFRO as "moonshot/kimi-k3". INFRO sends each provider its own id: AWS Bedrock "global.moonshotai.kimi-k3", Together AI "moonshotai/Kimi-K3", Fireworks AI "accounts/fireworks/models/kimi-k3", OpenRouter "moonshotai/kimi-k3", KIE "kimi-k3", and so on.

### How do I call Kimi K3 through an OpenAI-compatible API?

Point an OpenAI SDK, or any HTTP client, at https://api.infro.io/v1 with an INFRO gateway key and send model "moonshot/kimi-k3" to POST /v1/chat/completions. INFRO runs the request on a provider account you connected and returns the provider's response with an estimated cost.

### Does INFRO mark up Kimi K3 usage?

No. Moonshot or the provider you connect bills model usage to your own account. INFRO charges a software subscription for routing, failover, observability, budgets and policy, and takes 0% of model spend.