MXiaomi: MiMo-V2.6-Flash
xiaomi/mimo-v2-6-flashMiMo-V2.6-Flash is an open-source foundation model developed by Xiaomi.
Modalities
In / out per 1M$0.14 / $0.28
Context1M
ReleasedSep 21, 2026
Providers
8 providers serve this model upstream.
| Provider | Input /M | Output /M | Cache read /M | Latency P50 | Throughput P50 | Uptime |
|---|---|---|---|---|---|---|
| $0.14 | $0.28 | $0.00 | 4.01s | 34 tps | 99.6% | |
| $0.15 | $0.29 | $0.03 | 1.25s | 86 tps | 99.39% | |
| $0.14 | $0.28 | $0.00 | 4.26s | 27 tps | 98.67% | |
 DeepInfraus · fp8 | $0.14 | $0.28 | $0.00 | 1.96s | 26 tps | 98.55% |
| $0.13 | $0.28 | $0.00 | 0.69s | 137 tps | 98.24% | |
 Darkbloomfp4 | $0.10 | $0.28 | $0.05 | 4.65s | 16 tps | 97.34% |
| $0.17 | $0.35 | $0.00 | 1.99s | 26 tps | 94.78% | |
| $0.14 | $0.28 | $0.00 | 4.90s | 15 tps | 51.49% |
Market-wide measurements, refreshed every 15 minutes. They describe who serves MiMo-V2.6-Flash in general, not how ProjectCOZY routes your requests.
Pricing
List rates per 1M tokens — what MiMo-V2.6-Flash costs pay-as-you-go elsewhere, not what you pay here.
Input
$0.14
per 1M tokens
Output
$0.28
per 1M tokens
Cache read
$0.00
per 1M cached tokens
Included in every pass
MiMo-V2.6-Flash is included in every ProjectCOZY pass at no extra cost — one flat rate, no per-token metering. The rates above are there for comparison.
Performance
Time to first token and output speed across every provider, over the last 3 days.
0.0s20.0s40.0s60.0s80.0s
Oct 11, 12 AMOct 11, 8 AMOct 11, 4 PMOct 12, 12 AMOct 12, 8 AMOct 12, 4 PMOct 13, 12 AMOct 13, 8 AMOct 13, 4 PMOct 14, 12 AMOct 14, 8 AM
DeepInfra (us) Xiaomi NovitaAI GMICloud Venice io.net Makora Darkbloom
0 tok/s200 tok/s400 tok/s600 tok/s800 tok/s
Oct 11, 12 AMOct 11, 8 AMOct 11, 4 PMOct 12, 12 AMOct 12, 8 AMOct 12, 4 PMOct 13, 12 AMOct 13, 8 AMOct 13, 4 PMOct 14, 12 AMOct 14, 8 AM
DeepInfra (us) Xiaomi NovitaAI GMICloud Venice io.net Makora Darkbloom
Uptime
100% of requests were served successfully over the last 3 days, across all providers.
Last 3 daysAvailability 99.55%
Oct 11, 2:00 PMNow
Availability over the last 24 hoursAvailability 99.77%
100% 98% 97% 95%
Oct 13, 2:40 PMNow
Apps
Tools that most often run MiMo-V2.6-Flash, by tokens this week.
Activity
30696.2B tokens processed market-wide in the last month.
0500.0B1000.0B1500.0B2000.0B
Sep 21Sep 26Oct 1Oct 6Oct 11
Tokens
FAQ
Which model id do I use for MiMo-V2.6-Flash?
xiaomi/mimo-v2.6-flash. Send it as the model field from any OpenAI-compatible client, against http://192.168.1.55/v1.
How much context does MiMo-V2.6-Flash hold?
1,050,000 tokens per request, of which up to 131,072 can be the response.
What can it accept and return?
Input: text, image, video, audio. Output: text.
What does MiMo-V2.6-Flash cost on a pass?
Nothing beyond the pass itself. Pay-as-you-go elsewhere it lists at $0.14 per 1M input tokens and $0.28 per 1M output tokens.
Who built MiMo-V2.6-Flash?
Xiaomi, in the MiMo family.
Explore
Other models your pass can call.
