No LMArena general score is attached to this listing.
$0.088/ 1M tokensBalanced · 3 tokens in per 1 out
Price under confirmation since 2026-11-05. Upstream lists another price for this model now, or other prices from its sellers. What is shown is the last we published; the new figures are published once a second day shows the same values. · Serving precision differs between offers.
Price from Tenstorrent: the cheapest offer that is serving, at standard delivery, with at least 90% of the reference context and at a declared precision that is not 4-bit (fp8), at its standard rate. The maker’s own precision is not known.
Price under confirmation since 2026-11-05 Upstream lists another price for this model now, or other prices from its sellers. What is shown is the last we published; the new figures are published once a second day shows the same values.
Every price dimension · USD per million tokens
Input
$0.050/M
Output
$0.200/M
Cached input
$0.0050/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 $0.150/M from Novita.
13 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
Tenstorrenttenstorrent/fp8 Endpoint terms
Cached input /M
$0.0050
Context limit
1,000,000 tokens
Output limit
900,000 tokens
Tools
Listed by endpoint
Reasoning
Listed by endpoint
Promotional discount
None reported
Uptime · last 30 minutes
96.67%
Input$0.050
Output$0.200
Precisionfp8
Uptime (1d)99.65%
Seller
GMICloudgmicloud/fp8 Endpoint terms
Cached input /M
$0.011
Context limit
1,048,576 tokens
Output limit
943,718 tokens
Tools
Listed by endpoint
Reasoning
Listed by endpoint
Promotional discount
25% · already included in these rates
Uptime · last 30 minutes
100.00%
Input$0.113
Output$0.450
Precisionfp8
Uptime (1d)99.79%
Seller
StreamLakestreamlake/fp8 Endpoint terms
Cached input /M
$0.014
Context limit
1,000,000 tokens
Output limit
512,000 tokens
Tools
Listed by endpoint
Reasoning
Listed by endpoint
Promotional discount
10% · already included in these rates
Uptime · last 30 minutes
100.00%
Input$0.135
Output$0.540
Precisionfp8
Uptime (1d)100.00%
Seller
Novitanovita/fp16 Endpoint terms
Cached input /M
$0.015
Context limit
1,000,000 tokens
Output limit
524,288 tokens
Tools
Listed by endpoint
Reasoning
Listed by endpoint
Promotional discount
None reported
Uptime · last 30 minutes
100.00%
Input$0.150
Output$0.600
Precisionfp16
Uptime (1d)100.00%
Seller
Parasailparasail/fp8 Endpoint terms
Cached input /M
$0.015
Context limit
1,048,576 tokens
Output limit
524,288 tokens
Tools
Listed by endpoint
Reasoning
Listed by endpoint
Promotional discount
None reported
Uptime · last 30 minutes
100.00%
Input$0.150
Output$0.600
Precisionfp8
Uptime (1d)100.00%
Seller
InferenceNetinference-net/fp4 Endpoint terms
Cached input /M
$0.015
Context limit
1,000,000 tokens
Output limit
524,288 tokens
Tools
Listed by endpoint
Reasoning
Listed by endpoint
Promotional discount
None reported
Uptime · last 30 minutes
100.00%
Input$0.150
Output$0.600
Precisionfp4
Uptime (1d)99.08%
Seller
ModelRunmodelrun/fp4 Endpoint terms
Cached input /M
$0.015
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
100.00%
Input$0.150
Output$0.600
Precisionfp4
Uptime (1d)100.00%
Seller
InferenceNetinference-net/fp4/us Endpoint terms
Cached input /M
$0.015
Context limit
1,000,000 tokens
Output limit
524,288 tokens
Tools
Listed by endpoint
Reasoning
Listed by endpoint
Promotional discount
None reported
Uptime · last 30 minutes
100.00%
Input$0.150
Output$0.600
Precisionfp4
Uptime (1d)98.80%
Seller
Fireworksfireworks Endpoint terms
Cached input /M
$0.015
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
100.00%
Input$0.150
Output$0.600
Precisionundeclared
Uptime (1d)99.86%
Seller
DigitalOceandigitalocean Endpoint terms
Cached input /M
$0.015
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
100.00%
Input$0.150
Output$0.600
Precisionundeclared
Uptime (1d)100.00%
Seller
SambaNovasambanova Endpoint terms
Cached input /M
$0.015
Context limit
1,048,576 tokens
Output limit
943,718 tokens
Tools
Listed by endpoint
Reasoning
Listed by endpoint
Promotional discount
50% · already included in these rates
Uptime · last 30 minutes
Unknown
Input$0.150
Output$0.600
Precisionundeclared
Uptime (1d)96.67%
Seller
Togethertogether Endpoint terms
Cached input /M
$0.015
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
100.00%
Input$0.150
Output$0.600
Precisionundeclared
Uptime (1d)99.93%
Seller
Minimaxminimax Endpoint terms
Cached input /M
$0.015
Context limit
1,048,576 tokens
Output limit
524,288 tokens
Tools
Listed by endpoint
Reasoning
Listed by endpoint
Time windows
Standard-window rate shown. Discount 15:00–01:00 UTC every day: $0.075 in · $0.300 out.
Promotional discount
None reported
Uptime · last 30 minutes
100.00%
Input$0.150
Output$0.600
Precisionundeclared
Uptime (1d)100.00%
Independent scores
No independent benchmark has measured this model. Unrated is not a score of zero.
Price and provider offers kept at the published record of 2026-11-04 until a second day confirms the newer upstream value, or after 3 days until one day’s two readings agree.
Quality data
unrated
MiniMax-M3.1-Flash is a multimodal model from MiniMax. Compared with M3, it delivers significant improvements across multiple benchmarks, particularly in complex agentic tasks, coding, and cybersecurity. It is built for complex,...
Questions this page answers
What does MiniMax M3.1 Flash cost?
$0.050/M in, $0.200/M out: the published record of 2026-11-04, under confirmation since 2026-11-05. That is the API row, not a subscription.
Does MiniMax M3.1 Flash have an independent quality score?
MiniMax M3.1 Flash has no LMArena general score in this catalogue. Unrated is not a score of zero.
What beats MiniMax M3.1 Flash?
MiniMax M3.1 Flash has no LMArena general score. Unrated is not a score of zero.
Does this page use Artificial Analysis scores for MiniMax M3.1 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.
Does a missing score mean MiniMax M3.1 Flash scored zero?
Unrated is not a score of zero.
Is the cheapest MiniMax M3.1 Flash endpoint the same product?
Headline cheapest is a lower precision. Like-for-like at the best declared precision is $0.150/M from Novita.
MODEL MONUMENT
Save or share this proof
Preview and more sharing options
MiniMax: MiniMax M3.1 Flash. Balanced workload. Not rated on the LMArena general board. Evidence as of 05 Nov 2026. Price under confirmation since 05 Nov 2026.
Related
No LMArena general score, so there is no dominator to name. Unrated is not a clean bill of health.
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.