per 1M tokens
Xiaomi: MiMo-V2.6-Flash
xiaomi/mimo-v2.6-flash
MiMo-V2.6-Flash is an open-source foundation model developed by Xiaomi. Built on a Mixture-of-Experts architecture with 309B total parameters and 15B activated per token, it employs a hybrid attention mechanism for...
Price
per 1M tokens
Cheaper on Relace (−36%) versus the lab 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 |
|---|---|---|---|---|---|---|---|---|
| Relace | relace/mxfp4 | mxfp4 | $0.087/1M | $0.187/1M | 1.0M | 100% | Live | openrouter-endpoints |
| Darkbloom | darkbloom/fp4 | fp4 | $0.1/1M | $0.28/1M | 1.0M | 100% | Live | openrouter-endpoints |
| Io Net Price differs from the host list |
io-net/fp8 | fp8 | $0.1/1M | $0.28/1M | 1.0M | 100% | Live | openrouter-endpoints |
| GMICloud | gmicloud/bf16 | bf16 | $0.119/1M | $0.238/1M | 1.1M | 100% | Live | openrouter-endpoints |
| Makora | makora/fp8 | fp8 | $0.11/1M | $0.28/1M | 1.0M | 100% | Live | openrouter-endpoints |
| Sarvam | — | — | $0.1312/1M | $0.2624/1M | — | — | Listed | sarvam-docs |
| Cohere | cohere | — | $0.14/1M | $0.28/1M | 1.0M | 100% | Live | openrouter-endpoints |
| DeepInfra | — | — | $0.14/1M | $0.28/1M | 1.0M | — | Listed | deepinfra |
| DeepInfra | deepinfra/fp8 | fp8 | $0.14/1M | $0.28/1M | 1.0M | 100% | Live | openrouter-endpoints |
| Novita | — | — | $0.14/1M | $0.28/1M | 1.0M | — | Listed | novita |
| Novita | novita/fp8 | fp8 | $0.14/1M | $0.28/1M | 1.0M | 100% | Live | openrouter-endpoints |
| Xiaomi | xiaomi/fp8 | fp8 | $0.14/1M | $0.28/1M | 1.0M | 100% | Live | openrouter-endpoints |
| Io Net Price differs from OpenRouter |
— | fp8 | $0.143/1M | $0.294/1M | 1.0M | — | Listed | ionet |
| Venice | venice/fp8 | fp8 | $0.175/1M | $0.35/1M | 1M | 100% | Live | openrouter-endpoints |
Monthly bill
Token models use the token counts. Image, video, and audio models use units times the flat rate.
$0.42 at list price for this workload
Cache
per 1M tokens
Every rate
| Unit | Input | Output | Flat | Confidence |
|---|---|---|---|---|
| token | $0.14/1M | $0.28/1M | Not published— | official |
Price history
input or flat output
Daily snapshots
| UTC date | Unit | Input | Output | Flat |
|---|---|---|---|---|
| 2026-09-22 | token | $0.14 | $0.28 | Not published— |
| 2026-09-23 | token | $0.14 | $0.28 | Not published— |
| 2026-09-24 | token | $0.14 | $0.28 | Not published— |
| 2026-09-25 | token | $0.14 | $0.28 | Not published— |
| 2026-09-26 | token | $0.14 | $0.28 | Not published— |
| 2026-09-27 | token | $0.14 | $0.28 | Not published— |
| 2026-09-28 | token | $0.14 | $0.28 | Not published— |
| 2026-09-29 | token | $0.14 | $0.28 | Not published— |
| 2026-09-30 | token | $0.14 | $0.28 | Not published— |
| 2026-10-01 | token | $0.14 | $0.28 | Not published— |
| 2026-10-02 | token | $0.14 | $0.28 | Not published— |
| 2026-10-03 | token | $0.14 | $0.28 | Not published— |
| 2026-10-04 | token | $0.14 | $0.28 | Not published— |
| 2026-10-05 | token | $0.14 | $0.28 | Not published— |
| 2026-10-06 | token | $0.14 | $0.28 | Not published— |
| 2026-10-07 | token | $0.14 | $0.28 | Not published— |
| 2026-10-08 | token | $0.14 | $0.28 | Not published— |
| 2026-10-09 | token | $0.14 | $0.28 | Not published— |
| 2026-10-10 | token | $0.14 | $0.28 | Not published— |
| 2026-10-11 | token | $0.14 | $0.28 | Not published— |
| 2026-10-12 | token | $0.14 | $0.28 | Not published— |
| 2026-10-13 | token | $0.14 | $0.28 | Not published— |
| 2026-10-14 | token | $0.14 | $0.28 | Not published— |
| 2026-10-15 | token | $0.14 | $0.28 | Not published— |
| 2026-10-16 | token | $0.14 | $0.28 | Not published— |
| 2026-10-17 | token | $0.14 | $0.28 | Not published— |
| 2026-10-18 | token | $0.14 | $0.28 | Not published— |
| 2026-10-19 | token | $0.14 | $0.28 | Not published— |
| 2026-10-20 | token | $0.14 | $0.28 | Not published— |
| 2026-10-21 | token | $0.14 | $0.28 | Not published— |
| 2026-10-22 | token | $0.14 | $0.28 | Not published— |
| 2026-10-23 | token | $0.14 | $0.28 | Not published— |
| 2026-10-24 | token | $0.14 | $0.28 | Not published— |
| 2026-10-25 | token | $0.14 | $0.28 | Not published— |
| 2026-10-26 | token | $0.14 | $0.28 | Not published— |
| 2026-10-27 | token | $0.14 | $0.28 | Not published— |
| 2026-10-28 | token | $0.14 | $0.28 | Not published— |
| 2026-10-29 | token | $0.14 | $0.28 | Not published— |
| 2026-10-30 | token | $0.14 | $0.28 | Not published— |
Alternatives
- DeepSeek V4 Flash$0.14/1M · Compare
- Gemma 4 31B$0.14/1M · Compare
- google.gemma-4-31b$0.14/1M · Compare
- google/gemma-4-31B-it$0.14/1M · Compare
- Hermes 2 Pro Llama 3 8B$0.14/1M · Compare
- Hy3$0.14/1M · Compare
Parameters (20)
Call this model
OpenRouter id xiaomi/mimo-v2.6-flash. 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":"xiaomi/mimo-v2.6-flash","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: "xiaomi/mimo-v2.6-flash",
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": "xiaomi/mimo-v2.6-flash", "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())