Price from Crusoe: 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 (bf16), at its standard rate. The maker’s own precision is not known.
Cheaper right now: $0.702/M at Baidu — promotion 59% · 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
$0.700/M
Output
$3.50/M
Cached input
$0.350/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 $0.700/M from Crusoe.
15 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
Baidubaidu/fp4 Endpoint terms
Cached input /M
$0.066
Context limit
262,144 tokens
Output limit
235,929 tokens
Tools
Listed by endpoint
Reasoning
Listed by endpoint
Promotional discount
59% · already included in these rates
Uptime · last 30 minutes
100.00%
Input$0.390
Output$1.64
Precisionfp4
Uptime (1d)100.00%
Seller
Chuteschutes/int4 Endpoint terms
Cached input /M
$0.039
Context limit
262,144 tokens
Output limit
65,535 tokens
Tools
Listed by endpoint
Reasoning
Listed by endpoint
Promotional discount
None reported
Uptime · last 30 minutes
100.00%
Input$0.390
Output$1.80
Precisionint4
Uptime (1d)100.00%
Seller
Inceptroninceptron/int4 Endpoint terms
Cached input /M
$0.190
Context limit
262,144 tokens
Output limit
235,929 tokens
Tools
Listed by endpoint
Reasoning
Listed by endpoint
Promotional discount
None reported
Uptime · last 30 minutes
100.00%
Input$0.565
Output$2.79
Precisionint4
Uptime (1d)99.64%
Seller
DigitalOceandigitalocean Endpoint terms
Cached input /M
$0.114
Context limit
262,144 tokens
Output limit
235,929 tokens
Tools
Listed by endpoint
Reasoning
Listed by endpoint
Promotional discount
None reported
Uptime · last 30 minutes
100.00%
Input$0.570
Output$2.40
Precisionundeclared
Uptime (1d)100.00%
Seller
StreamLakestreamlake/fp8 Endpoint terms
Cached input /M
$0.101
Context limit
256,000 tokens
Output limit
230,400 tokens
Tools
Listed by endpoint
Reasoning
Listed by endpoint
Promotional discount
37% · already included in these rates
Uptime · last 30 minutes
Unknown
Input$0.599
Output$2.52
Precisionfp8
Uptime (1d)98.43%
Seller
DeepInfradeepinfra/fp4/flex Endpoint terms
Cached input /M
$0.120
Context limit
262,144 tokens
Output limit
235,929 tokens
Tools
Not listed by endpoint
Reasoning
Listed by endpoint
Promotional discount
None reported
Uptime · last 30 minutes
Unknown
Input$0.600
Output$2.80
Precisionfp4
Uptime (1d)—
Seller
CoreWeavecoreweave/fp4 Endpoint terms
Cached input /M
$0.150
Context limit
262,144 tokens
Output limit
235,929 tokens
Tools
Listed by endpoint
Reasoning
Listed by endpoint
Promotional discount
None reported
Uptime · last 30 minutes
100.00%
Input$0.650
Output$3.41
Precisionfp4
Uptime (1d)99.86%
Seller
Crusoecrusoe/bf16 Endpoint terms
Cached input /M
$0.350
Context limit
262,144 tokens
Output limit
235,929 tokens
Tools
Listed by endpoint
Reasoning
Listed by endpoint
Promotional discount
None reported
Uptime · last 30 minutes
100.00%
Input$0.700
Output$3.50
Precisionbf16
Uptime (1d)99.79%
Seller
DeepInfradeepinfra/fp4 Endpoint terms
Cached input /M
$0.150
Context limit
262,144 tokens
Output limit
16,384 tokens
Tools
Listed by endpoint
Reasoning
Listed by endpoint
Promotional discount
None reported
Uptime · last 30 minutes
100.00%
Input$0.750
Output$3.50
Precisionfp4
Uptime (1d)99.84%
Seller
Venicevenice/int4 Endpoint terms
Cached input /M
$0.160
Context limit
256,000 tokens
Output limit
65,536 tokens
Tools
Listed by endpoint
Reasoning
Listed by endpoint
Promotional discount
None reported
Uptime · last 30 minutes
Unknown
Input$0.750
Output$3.50
Precisionint4
Uptime (1d)96.55%
Seller
Parasailparasail/int4 Endpoint terms
Cached input /M
$0.160
Context limit
262,144 tokens
Output limit
235,929 tokens
Tools
Listed by endpoint
Reasoning
Listed by endpoint
Promotional discount
None reported
Uptime · last 30 minutes
100.00%
Input$0.750
Output$3.50
Precisionint4
Uptime (1d)99.93%
Seller
SiliconFlowsiliconflow/fp8 Endpoint terms
Cached input /M
$0.140
Context limit
262,144 tokens
Output limit
235,929 tokens
Tools
Listed by endpoint
Reasoning
Listed by endpoint
Promotional discount
None reported
Uptime · last 30 minutes
Unknown
Input$0.770
Output$3.40
Precisionfp8
Uptime (1d)100.00%
Seller
Novitanovita Endpoint terms
Cached input /M
$0.160
Context limit
262,144 tokens
Output limit
235,929 tokens
Tools
Listed by endpoint
Reasoning
Listed by endpoint
Promotional discount
None reported
Uptime · last 30 minutes
100.00%
Input$0.800
Output$3.40
Precisionundeclared
Uptime (1d)100.00%
Seller
Moonshot AImoonshotai Endpoint terms
Cached input /M
$0.160
Context limit
262,144 tokens
Output limit
235,929 tokens
Tools
Listed by endpoint
Reasoning
Listed by endpoint
Promotional discount
None reported
Uptime · last 30 minutes
100.00%
Input$0.950
Output$4.00
Precisionundeclared
Uptime (1d)99.43%
Seller
DeepInfradeepinfra/fp4/priority Endpoint terms
Cached input /M
$0.225
Context limit
262,144 tokens
Output limit
235,929 tokens
Tools
Listed by endpoint
Reasoning
Listed by endpoint
Promotional discount
None reported
Uptime · last 30 minutes
Unknown
Input$1.13
Output$5.25
Precisionfp4
Uptime (1d)98.92%
Independent scores
LMArena Elo
1455.4default
LMArena row
kimi-k2.6
LMArena Elo under CC BY 4.0. Absence of another board is not a score of zero.
Best rankings by task
Agentichtmlslides#21248
Agenticslides(html)#21252
Agenticslides#41187
Agenticslides(python pptx)#41186
Pptxslides#41181
Spreadsheet#81276
Web apps#101268
Htmlslides#131086
Per-task Elo and rank from Design Arena, via OpenRouter’s model feed. The rank is the feed’s, and it counts models OpenRouter does not list.
Kimi K2.6 is Moonshot AI's next-generation multimodal model, designed for long-horizon coding, coding-driven UI/UX generation, and multi-agent orchestration. It handles complex end-to-end coding tasks across Python, Rust, and Go, and...
Questions this page answers
What does Kimi K2.6 cost?
$0.700/M in, $3.50/M out in this catalogue, as of the fetch date on this page. That is the API row, not a subscription.
Does Kimi K2.6 have an independent quality score?
Kimi K2.6 has an LMArena score in this catalogue.
What beats Kimi K2.6?
DeepSeek V4.1 Flash has an equal-or-higher measured score and an equal-or-lower price.
Does this page use Artificial Analysis scores for Kimi K2.6?
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 Kimi K2.6 endpoint the same product?
Headline cheapest is a lower precision. Like-for-like at the best declared precision is $0.700/M from Crusoe.
MODEL MONUMENT
Save or share this proof
Preview and more sharing options
MoonshotAI: Kimi K2.6. Balanced workload. Better value option available. Evidence as of 22 Nov 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.