per 1M tokens
Kimi K2 Instruct
novita/moonshotai/kimi-k2-instruct
Kimi K2 is a state-of-the-art mixture-of-experts (MoE) language model with 32 billion activated parameters and 1 trillion total parameters. Trained with the Muon optimizer, Kimi K2 achieves exceptional performance across frontier knowledge, reasoning, and coding tasks while being meticulously optimized for agentic capabilities.Specifically designed for tool use, reasoning, and autonomous problem-solving.
Price
per 1M tokens
Providers
Each row is one seller. Prices are the published rate from that source. A dash means that source did not publish the amount. Sorted by a 3:1 blend of input and output.
| Provider | Tag | Quant | Input | Output | Context | Uptime | Status | Source |
|---|---|---|---|---|---|---|---|---|
| Novita | — | — | $0.57/1M | $2.3/1M | 131K | — | Listed | novita |
Monthly bill
Token models use the token counts. Image, video, and audio models use units times the flat rate.
$2.87 at list price for this workload
Every rate
| Unit | Input | Output | Flat | Confidence |
|---|---|---|---|---|
| token | $0.57/1M | $2.3/1M | Not published— | official |
Price history
input or flat output
Daily snapshots
| UTC date | Unit | Input | Output | Flat |
|---|---|---|---|---|
| 2026-10-08 | token | $0.57 | $2.3 | Not published— |
| 2026-10-09 | token | $0.57 | $2.3 | Not published— |
| 2026-10-10 | token | $0.57 | $2.3 | Not published— |
| 2026-10-11 | token | $0.57 | $2.3 | Not published— |
| 2026-10-12 | token | $0.57 | $2.3 | Not published— |
| 2026-10-13 | token | $0.57 | $2.3 | Not published— |
| 2026-10-14 | token | $0.57 | $2.3 | Not published— |
| 2026-10-15 | token | $0.57 | $2.3 | Not published— |
| 2026-10-16 | token | $0.57 | $2.3 | Not published— |
| 2026-10-17 | token | $0.57 | $2.3 | Not published— |
| 2026-10-18 | token | $0.57 | $2.3 | Not published— |
| 2026-10-19 | token | $0.57 | $2.3 | Not published— |
| 2026-10-20 | token | $0.57 | $2.3 | Not published— |
| 2026-10-21 | token | $0.57 | $2.3 | Not published— |
| 2026-10-22 | token | $0.57 | $2.3 | Not published— |
| 2026-10-23 | token | $0.57 | $2.3 | Not published— |
| 2026-10-24 | token | $0.57 | $2.3 | Not published— |
| 2026-10-25 | token | $0.57 | $2.3 | Not published— |
| 2026-10-26 | token | $0.57 | $2.3 | Not published— |
| 2026-10-27 | token | $0.57 | $2.3 | Not published— |
| 2026-10-28 | token | $0.57 | $2.3 | Not published— |
| 2026-10-29 | token | $0.57 | $2.3 | Not published— |
| 2026-10-30 | token | $0.57 | $2.3 | Not published— |
Alternatives
- MoonshotAI: Kimi K2 0711$0.57/1M · Compare
- MoonshotAI: Kimi K2 Instruct 0905$0.57/1M · Compare
- kimi-k2-5$0.56/1M · Compare
- MoonshotAI: Kimi K2.7 Code$0.56/1M · Compare
- DeepSeek V3.1$0.58/1M · Compare
- @cf/meta/llama-2-7b-chat-fp16$0.556/1M · Compare
Call this model
OpenRouter id novita/moonshotai/kimi-k2-instruct. InferenceList does not send the request.
curl
curl https://openrouter.ai/api/v1/chat/completions \
-H "Authorization: Bearer $OPENROUTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"novita/moonshotai/kimi-k2-instruct","messages":[{"role":"user","content":"Hello"}]}'
JavaScript
await fetch("https://openrouter.ai/api/v1/chat/completions", {
method: "POST",
headers: {
Authorization: "Bearer " + process.env.OPENROUTER_API_KEY,
"Content-Type": "application/json",
},
body: JSON.stringify({
model: "novita/moonshotai/kimi-k2-instruct",
messages: [{ role: "user", content: "Hello" }],
}),
});
Python
import os, json, urllib.request
req = urllib.request.Request(
"https://openrouter.ai/api/v1/chat/completions",
data=json.dumps({"model": "novita/moonshotai/kimi-k2-instruct", "messages": [{"role": "user", "content": "Hello"}]}).encode(),
headers={"Authorization": "Bearer " + os.environ["OPENROUTER_API_KEY"], "Content-Type": "application/json"},
)
print(urllib.request.urlopen(req).read().decode())