per 1M tokens
MoonshotAI: Kimi K2.5
moonshotai/kimi-k2.5
Kimi K2.5 is Moonshot AI's native multimodal model, delivering state-of-the-art visual coding capability and a self-directed agent swarm paradigm. Built on Kimi K2 with continued pretraining over approximately 15T mixed...
Price
per 1M tokens
Cheaper on Amazon Bedrock (−40%) versus the OpenRouter list price
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 |
|---|---|---|---|---|---|---|---|---|
| Amazon Bedrock Price differs from OpenRouter |
batch | — | $0.3/1M | $1.5/1M | — | — | Listed | amazon-bedrock |
| Amazon Bedrock Price differs from OpenRouter |
flex | — | $0.3/1M | $1.5/1M | — | — | Listed | amazon-bedrock |
| AtlasCloud | — | int4 | $0.49/1M | $2.5/1M | 262K | — | Listed | atlascloud |
| SiliconFlow | siliconflow/int4 | int4 | $0.5/1M | $2.5/1M | 262K | 100% | Live | openrouter-endpoints |
| Io Net | — | int4 | $0.5384/1M | $2.835/1M | 262K | — | Listed | ionet |
| Novita Price differs from the host list |
novita | — | $0.57/1M | $2.85/1M | 262K | 100% | Live | openrouter-endpoints |
| Amazon Bedrock | amazon-bedrock/us-east-2 | — | $0.6/1M | $3/1M | 262K | 100% | Live | openrouter-endpoints |
| Amazon Bedrock | standard | — | $0.6/1M | $3/1M | — | — | Listed | amazon-bedrock |
| Cloudflare | — | — | $0.6/1M | $3/1M | — | — | Listed | cloudflare-pricing |
| Novita Price differs from OpenRouter |
— | — | $0.6/1M | $3/1M | 262K | — | Listed | novita |
| Venice | venice | — | $0.532/1M | $3.325/1M | 256K | 100% | Live | openrouter-endpoints |
| Inference.net | — | — | $0.8/1M | $3.95/1M | 262K | — | Listed | inferencenet |
| Amazon Bedrock Price differs from OpenRouter |
priority | — | $1.05/1M | $5.25/1M | — | — | Listed | amazon-bedrock |
| AtlasCloud | atlas-cloud/int4 | int4 | $0.49/1M | $2.5/1M | 262K | 100% | Down | openrouter-endpoints |
Monthly bill
Token models use the token counts. Image, video, and audio models use units times the flat rate.
$3.00 at list price for this workload
Cache
per 1M tokens
Every rate
| Unit | Input | Output | Flat | Confidence |
|---|---|---|---|---|
| token | $0.5/1M | $2.5/1M | Not published— | official |
Price history
input or flat output
Daily snapshots
| UTC date | Unit | Input | Output | Flat |
|---|---|---|---|---|
| 2026-09-15 | token | $0.45 | $2.25 | Not published— |
| 2026-09-16 | token | $0.45 | $2.25 | Not published— |
| 2026-09-17 | token | $0.45 | $2.25 | Not published— |
| 2026-09-18 | token | $0.45 | $2.25 | Not published— |
| 2026-09-19 | token | $0.45 | $2.25 | Not published— |
| 2026-09-20 | token | $0.45 | $2.25 | Not published— |
| 2026-09-21 | token | $0.45 | $2.25 | Not published— |
| 2026-09-22 | token | $0.45 | $2.25 | Not published— |
| 2026-09-23 | token | $0.45 | $2.25 | Not published— |
| 2026-09-24 | token | $0.45 | $2.25 | Not published— |
| 2026-09-25 | token | $0.45 | $2.25 | Not published— |
| 2026-09-26 | token | $0.45 | $2.25 | Not published— |
| 2026-09-27 | token | $0.45 | $2.25 | Not published— |
| 2026-09-28 | token | $0.45 | $2.25 | Not published— |
| 2026-09-29 | token | $0.45 | $2.25 | Not published— |
| 2026-09-30 | token | $0.45 | $2.25 | Not published— |
| 2026-10-01 | token | $0.45 | $2.25 | Not published— |
| 2026-10-02 | token | $0.45 | $2.25 | Not published— |
| 2026-10-03 | token | $0.45 | $2.25 | Not published— |
| 2026-10-04 | token | $0.45 | $2.25 | Not published— |
| 2026-10-05 | token | $0.45 | $2.25 | Not published— |
| 2026-10-06 | token | $0.45 | $2.25 | Not published— |
| 2026-10-07 | token | $0.45 | $2.25 | Not published— |
| 2026-10-08 | token | $0.45 | $2.25 | Not published— |
| 2026-10-09 | token | $0.45 | $2.25 | Not published— |
| 2026-10-10 | token | $0.5 | $2.5 | Not published— |
| 2026-10-11 | token | $0.5 | $2.5 | Not published— |
| 2026-10-12 | token | $0.5 | $2.5 | Not published— |
| 2026-10-13 | token | $0.5 | $2.5 | Not published— |
| 2026-10-14 | token | $0.5 | $2.5 | Not published— |
| 2026-10-15 | token | $0.5 | $2.5 | Not published— |
| 2026-10-16 | token | $0.5 | $2.5 | Not published— |
| 2026-10-17 | token | $0.5 | $2.5 | Not published— |
| 2026-10-18 | token | $0.5 | $2.5 | Not published— |
| 2026-10-19 | token | $0.5 | $2.5 | Not published— |
| 2026-10-20 | token | $0.5 | $2.5 | Not published— |
| 2026-10-21 | token | $0.5 | $2.5 | Not published— |
| 2026-10-22 | token | $0.5 | $2.5 | Not published— |
| 2026-10-23 | token | $0.5 | $2.5 | Not published— |
| 2026-10-24 | token | $0.5 | $2.5 | Not published— |
| 2026-10-25 | token | $0.5 | $2.5 | Not published— |
| 2026-10-26 | token | $0.5 | $2.5 | Not published— |
| 2026-10-27 | token | $0.5 | $2.5 | Not published— |
| 2026-10-28 | token | $0.5 | $2.5 | Not published— |
| 2026-10-29 | token | $0.5 | $2.5 | Not published— |
| 2026-10-30 | token | $0.5 | $2.5 | Not published— |
Alternatives
- @cf/nvidia/nemotron-3-120b-a12b$0.5/1M · Compare
- Anthropic: Claude Haiku 4.5 (batch)$0.5/1M · Compare
- ByteDance Seed: Seed 2.1 Turbo$0.5/1M · Compare
- ByteDance Seed: Seed-2.0-Code$0.5/1M · Compare
- ByteDance/Seed-2.0-code$0.5/1M · Compare
- ByteDance/Seed-2.0-pro$0.5/1M · Compare
Parameters (19)
Call this model
OpenRouter id moonshotai/kimi-k2.5. 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":"moonshotai/kimi-k2.5","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: "moonshotai/kimi-k2.5",
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": "moonshotai/kimi-k2.5", "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())