per 1M tokens
Kimi K2 Instruct 0905
novita/moonshotai/kimi-k2-0905
Kimi K2 0905 is the September update of Kimi K2 0711. It is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters with 32 billion active per forward pass. It supports long-context inference up to 256k tokens, extended from the previous 128k. This update improves agentic coding with higher accuracy and better generalization across scaffolds, and enhances frontend coding with more aesthetic and functional outputs for web, 3D, and related tasks. Kimi K2 is optimized for agentic capabilities, including advanced tool use, reasoning, and code synthesis. It excels across coding (LiveCodeBench, SWE-bench), reasoning (ZebraLogic, GPQA), and tool-use (Tau2, AceBench) benchmarks. The model is trained with a novel stack incorporating the MuonClip optimizer for stable large-scale MoE training.
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.
No provider prices yet.
Monthly bill
Token models use the token counts. Image, video, and audio models use units times the flat rate.
$3.10 at list price for this workload
Every rate
| Unit | Input | Output | Flat | Confidence |
|---|---|---|---|---|
| token | $0.6/1M | $2.5/1M | Not published— | official |
Price history
input or flat output
Daily snapshots
| UTC date | Unit | Input | Output | Flat |
|---|---|---|---|---|
| 2026-10-08 | token | $0.6 | $2.5 | Not published— |
| 2026-10-09 | token | $0.6 | $2.5 | Not published— |
| 2026-10-10 | token | $0.6 | $2.5 | Not published— |
| 2026-10-11 | token | $0.6 | $2.5 | Not published— |
| 2026-10-12 | token | $0.6 | $2.5 | Not published— |
| 2026-10-13 | token | $0.6 | $2.5 | Not published— |
| 2026-10-14 | token | $0.6 | $2.5 | Not published— |
| 2026-10-15 | token | $0.6 | $2.5 | Not published— |
| 2026-10-16 | token | $0.6 | $2.5 | Not published— |
| 2026-10-17 | token | $0.6 | $2.5 | Not published— |
| 2026-10-18 | token | $0.6 | $2.5 | Not published— |
| 2026-10-19 | token | $0.6 | $2.5 | Not published— |
| 2026-10-20 | token | $0.6 | $2.5 | Not published— |
| 2026-10-21 | token | $0.6 | $2.5 | Not published— |
| 2026-10-22 | token | $0.6 | $2.5 | Not published— |
| 2026-10-23 | token | $0.6 | $2.5 | Not published— |
| 2026-10-24 | token | $0.6 | $2.5 | Not published— |
| 2026-10-25 | token | $0.6 | $2.5 | Not published— |
| 2026-10-26 | token | $0.6 | $2.5 | Not published— |
| 2026-10-27 | token | $0.6 | $2.5 | Not published— |
| 2026-10-28 | token | $0.6 | $2.5 | Not published— |
| 2026-10-29 | token | $0.6 | $2.5 | Not published— |
| 2026-10-30 | token | $0.6 | $2.5 | Not published— |
Alternatives
- @cf/moonshotai/kimi-k2.5$0.6/1M · Compare
- Deepseek V3.1 NVFP4$0.6/1M · Compare
- Elorian: Glimpse$0.6/1M · Compare
- GLM 4.5V$0.6/1M · Compare
- GLM 4.6 Fp8$0.6/1M · Compare
- GLM 4.7$0.6/1M · Compare
Call this model
OpenRouter id novita/moonshotai/kimi-k2-0905. 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-k2-0905","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-k2-0905",
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-k2-0905", "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())