mimo-v2.6-flashDeepInfra
- api
- chat
- hosting
- US
- model lab
- Xiaomi
- weights
- open
- added
- September 2026
- model id
- deepinfra/mimo-v2.6-flash
capabilities 5/8
3 providers serve mimo-v2.6-flash. This page is one of them. Compare all endpoints
- input
- $0.14
- output
- $0.28
- cache write
- -
- cache read
- $0.0027
worked cost
| volume | cost |
|---|---|
| 100K in + 10K out | $0.0168 |
| 1M in + 100K out | $0.17 |
| 10M in + 1M out | $1.68 |
Requesty charges what the upstream provider charges, with no markup and no per-request fee. Prompt caching and smart routing cut the effective cost further on repeated context. Gateway pricing
no measured traffic for this endpoint yet. pricing above is the provider's own
| eval | Score as a share of 100 | /100 |
|---|---|---|
| SciCode | 51.3 | |
| Humanity's Last Exam | 35.1 | |
| Intelligence Index | 26.7 | |
| 3 evals | mean | 37.7 |
Scores from Artificial Analysis and public leaderboards, normalised to 100. Bar colour is the band, not the rank: green 80 and up, blue 55 and up, amber 30 and up. Benchmarks measure narrow skills, so test on your own workload before committing. Released 2026-09-21.
- retention
- none
- trains on prompts
- no
- hosted in
- US
Terms are the provider's, not Requesty's: routing a request here puts it under them. DeepInfra Privacy Policy
Need every request to stay in one jurisdiction? EU hosting routes only through EU-hosted providers.
deepinfra/mimo-v2.6-flashthis id pins the deepinfra deployment, with no routing and no failover. the managed id on the canonical page routes across all 3 providers instead
from openai import OpenAI client = OpenAI( api_key="YOUR_REQUESTY_API_KEY", base_url="https://router.requesty.ai/v1",) response = client.chat.completions.create( model="deepinfra/mimo-v2.6-flash", messages=[ {"role": "user", "content": "Explain quantum computing in one paragraph."}, ],) print(response.choices[0].message.content)
Change the base url to https://router.requesty.ai/v1, use your Requesty key, set the model to the id above. Existing OpenAI SDK code needs no other edit, and the same key reaches every other model in the catalog. Browse all models
MiMo-V2.6-Flash is the efficiency-balanced model in Xiaomi's MiMo-V2.6 series: a sparse Mixture-of-Experts model with 309B total and 15B activated parameters, natively omnimodal across text, image, video and audio, with a 1M-token context window. Trained with large-scale mixed reinforcement learning across coding, general agents, visual and cybersecurity tasks, it is built for agentic workloads such as long-horizon coding, tool use and computer use.
questions 6
How much does mimo-v2.6-flash cost?
What is the context window of mimo-v2.6-flash?
How does mimo-v2.6-flash perform on benchmarks?
What can mimo-v2.6-flash do?
How do I use mimo-v2.6-flash with the OpenAI SDK?
Can I run mimo-v2.6-flash through Requesty?
more from deepinfra 8
| endpoint | ctx | in /M |
|---|---|---|
| deepseek-v4.1-flash-1017 | 1.0M | $0.10 |
| deepseek-v4.1-flash-1017:priority | 1.0M | $0.15 |
| step-5-preview | 1.0M | $1.00 |
| mimo-v2.6-pro | 1.0M | $0.43 |
| deepseek-v4.1-flash | 1.0M | $0.20 |
| deepseek-v4.1-flash:flex | 1.0M | $0.16 |
| glm-5.3-flash | 1.0M | $0.15 |
| glm-5.3 | 1.0M | $1.20 |
call mimo-v2.6-flash through one endpoint
One key for this endpoint and 600+ other models. No markup on provider prices, automatic failover when a provider degrades, and prompt caching built in. Methodology