per 1M tokens
moonshotai/Kimi-K3
deepinfra/moonshotai/Kimi-K3
Kimi K3 is Moonshot AI's 2.8T-parameter open-weight multimodal reasoning model. Built for complex coding, knowledge work, and long-horizon agentic workflows, it excels at navigating large repositories, calling tools, debugging, and iterating on images, logs, tests, and runtime feedback. Its architecture relies on KDA and Attention Residuals for computational efficiency.
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.
$17.10 at list price for this workload
Cache
per 1M tokens
Every rate
| Unit | Input | Output | Flat | Confidence |
|---|---|---|---|---|
| token | $2.85/1M | $14.25/1M | Not published— | official |
Price history
input or flat output
Daily snapshots
| UTC date | Unit | Input | Output | Flat |
|---|---|---|---|---|
| 2026-10-08 | token | $2.85 | $14.25 | Not published— |
| 2026-10-09 | token | $2.85 | $14.25 | Not published— |
| 2026-10-10 | token | $2.85 | $14.25 | Not published— |
| 2026-10-11 | token | $2.85 | $14.25 | Not published— |
| 2026-10-12 | token | $2.85 | $14.25 | Not published— |
| 2026-10-13 | token | $2.85 | $14.25 | Not published— |
| 2026-10-14 | token | $2.85 | $14.25 | Not published— |
| 2026-10-15 | token | $2.85 | $14.25 | Not published— |
| 2026-10-16 | token | $2.85 | $14.25 | Not published— |
| 2026-10-17 | token | $2.85 | $14.25 | Not published— |
| 2026-10-18 | token | $2.85 | $14.25 | Not published— |
| 2026-10-19 | token | $2.85 | $14.25 | Not published— |
| 2026-10-20 | token | $2.85 | $14.25 | Not published— |
| 2026-10-21 | token | $2.85 | $14.25 | Not published— |
| 2026-10-22 | token | $2.85 | $14.25 | Not published— |
| 2026-10-23 | token | $2.85 | $14.25 | Not published— |
| 2026-10-24 | token | $2.85 | $14.25 | Not published— |
| 2026-10-25 | token | $2.85 | $14.25 | Not published— |
| 2026-10-26 | token | $2.85 | $14.25 | Not published— |
| 2026-10-27 | token | $2.85 | $14.25 | Not published— |
| 2026-10-28 | token | $2.85 | $14.25 | Not published— |
| 2026-10-29 | token | $2.85 | $14.25 | Not published— |
| 2026-10-30 | token | $2.85 | $14.25 | Not published— |
Alternatives
- Kimi K3 ()$2.834/1M · Compare
- Qwen3.7 Max$2.8/1M · Compare
- Z.ai: GLM 5.3 Prime$2.8/1M · Compare
- abliteration-abliterated-model-large-v2$3/1M · Compare
- AionLabs: Aion 3.5$3/1M · Compare
- AionLabs: Aion-3.0$3/1M · Compare
Parameters (5)
chatvlmvisionprompt_cachereasoning
Call this model
OpenRouter id deepinfra/moonshotai/Kimi-K3. 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":"deepinfra/moonshotai/Kimi-K3","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: "deepinfra/moonshotai/Kimi-K3",
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": "deepinfra/moonshotai/Kimi-K3", "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())