Price from Xiaomi: the cheapest offer that is serving, at standard delivery and at the maker’s precision or better, at its standard rate.
Cheaper right now: $0.145/M at Darkbloom — 4-bit It does not pass the like-for-like test, so it never sets a rank.
Every price dimension · USD per million tokens
Input
$0.140/M
Output
$0.280/M
Cached input
$0.0028/M
Cache write
Unknown/M
Cache write 1h
Unknown/M
Reasoning
Unknown/M
Who sells it
The same weights, different shops. Cheapest is not like-for-like when serving precision differs.
Headline cheapest is a lower precision. Like-for-like at the best declared precision is $0.140/M from GMICloud.
7 provider offers · rates, limits and conditions
Rates are USD per million tokens. Endpoint terms can differ even when the quoted price and precision match. A listed parameter is a provider declaration, not a task-success test.
Seller
Input
Output
Precision
Uptime (1d)
Seller
Darkbloomdarkbloom/fp4 Endpoint terms
Cached input /M
$0.050
Context limit
1,048,576 tokens
Output limit
131,072 tokens
Tools
Listed by endpoint
Reasoning
Listed by endpoint
Promotional discount
None reported
Uptime · last 30 minutes
96.91%
Input$0.100
Output$0.280
Precisionfp4
Uptime (1d)98.81%
Seller
GMICloudgmicloud/bf16 Endpoint terms
Cached input /M
$0.0030
Context limit
1,050,000 tokens
Output limit
945,000 tokens
Tools
Listed by endpoint
Reasoning
Listed by endpoint
Promotional discount
None reported
Uptime · last 30 minutes
97.10%
Input$0.140
Output$0.280
Precisionbf16
Uptime (1d)94.64%
Seller
Novitanovita/fp8 Endpoint terms
Cached input /M
$0.0028
Context limit
1,048,576 tokens
Output limit
131,072 tokens
Tools
Listed by endpoint
Reasoning
Listed by endpoint
Promotional discount
None reported
Uptime · last 30 minutes
96.80%
Input$0.140
Output$0.280
Precisionfp8
Uptime (1d)94.87%
Seller
DeepInfradeepinfra/fp8 Endpoint terms
Cached input /M
$0.0028
Context limit
1,048,576 tokens
Output limit
943,718 tokens
Tools
Listed by endpoint
Reasoning
Listed by endpoint
Promotional discount
None reported
Uptime · last 30 minutes
99.43%
Input$0.140
Output$0.280
Precisionfp8
Uptime (1d)97.79%
Seller
Xiaomixiaomi/fp8 Endpoint terms
Cached input /M
$0.0028
Context limit
1,048,576 tokens
Output limit
131,072 tokens
Tools
Listed by endpoint
Reasoning
Listed by endpoint
Promotional discount
None reported
Uptime · last 30 minutes
98.82%
Input$0.140
Output$0.280
Precisionfp8
Uptime (1d)97.51%
Seller
Io Netio-net/fp8 Endpoint terms
Cached input /M
$0.0040
Context limit
1,048,320 tokens
Output limit
131,072 tokens
Tools
Listed by endpoint
Reasoning
Listed by endpoint
Promotional discount
None reported
Uptime · last 30 minutes
99.81%
Input$0.159
Output$0.300
Precisionfp8
Uptime (1d)98.93%
Seller
Venicevenice/fp8 Endpoint terms
Cached input /M
$0.0038
Context limit
1,000,000 tokens
Output limit
131,072 tokens
Tools
Listed by endpoint
Reasoning
Listed by endpoint
Promotional discount
None reported
Uptime · last 30 minutes
98.95%
Input$0.175
Output$0.350
Precisionfp8
Uptime (1d)91.85%
Independent scores
LMArena Elo
1456.4default
LMArena Elo under CC BY 4.0. Absence of another board is not a score of zero.
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...
Questions this page answers
What does MiMo-V2.6-Flash cost?
$0.140/M in, $0.280/M out in this catalogue, as of the fetch date on this page. That is the API row, not a subscription.
Does MiMo-V2.6-Flash have an independent quality score?
MiMo-V2.6-Flash has an LMArena score in this catalogue.
What beats MiMo-V2.6-Flash?
Nothing is both better and cheaper than MiMo-V2.6-Flash.
Does this page use Artificial Analysis scores for MiMo-V2.6-Flash?
No. Artificial Analysis figures are not published here. Quality on this page is LMArena Elo where a score exists; otherwise the row is unrated.
Is the cheapest MiMo-V2.6-Flash endpoint the same product?
Headline cheapest is a lower precision. Like-for-like at the best declared precision is $0.140/M from GMICloud.
MODEL MONUMENT
Save or share this proof
Preview and more sharing options
Xiaomi: MiMo-V2.6-Flash. Balanced workload. Frontier. Evidence as of 06 Oct 2026.
The verdict as one SVG, for a README or a docs page. It states this model's dominance
status at the balanced workload on the LMArena lens, with the date it was computed, and
it is rebuilt with the catalogue — so it changes when the verdict changes, including to
one you would rather it did not.