MODEL PROOF

Kimi K3

BETTER VALUE OPTION

A stored alternative has an equal-or-higher measured score and an equal-or-lower price.

$6.00 / 1M tokens Balanced · 3 tokens in per 1 out

Serving precision differs between offers.

Gemini 4 Neon · Δ score 48.9 points · same measured price · $6.00 / 1M tokens

Gemini 3.8 Flash is a further stored option with these losses: 944K → 66K max output

Independent LMArena score
1,474.7 ± 4.17 · 44,364 votes
Context window
1.05M
Maximum output
943.72K
Input modalities
text, image, video
Output modalities
text
Published input price
$3.00 / 1M tokens
Published output price
$15.00 / 1M tokens
Pricing kind
fixed

Inspect complete billing conditions and endpoint terms below.

Price from Moonshot AI: the cheapest offer that is serving, at standard delivery, with at least 90% of the reference context and at the maker’s precision or better, at its standard rate.

Cheaper right now: $2.61/M at Wafer — 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$3.00/M
Output$15.00/M
Cached input$0.300/M
Cache writeUnknown/M
Cache write 1hUnknown/M
ReasoningUnknown/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 $3.00/M from BaseTen.

29 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.

SellerInputOutputPrecisionUptime (1d)
Waferwafer/fast
Endpoint terms
Cached input /M
$0.152
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%
$0.153 $16.00 mxfp4 100.00%
Relacerelace/fp4
Endpoint terms
Cached input /M
$0.180
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%
$0.182 $11.01 fp4 99.38%
Waferwafer
Endpoint terms
Cached input /M
$0.182
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%
$0.192 $16.00 mxfp4 100.00%
InferenceNetinference-net/us
Endpoint terms
Cached input /M
$0.214
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%
$0.245 $15.75 fp4 100.00%
InferenceNetinference-net/fp4
Endpoint terms
Cached input /M
$0.214
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%
$0.245 $15.75 fp4 100.00%
Waferwafer/us
Endpoint terms
Cached input /M
$0.130
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%
$0.276 $9.60 mxfp4 100.00%
Sail Researchsail-research/fp4
Endpoint terms
Cached input /M
$0.173
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
Unknown
$0.345 $16.58 fp4 —
InferenceNetinference-net/us/fast
Endpoint terms
Cached input /M
$0.363
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%
$0.450 $18.00 fp4 100.00%
InferenceNetinference-net/fast
Endpoint terms
Cached input /M
$0.363
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%
$0.450 $18.00 fp4 100.00%
KTkt
Endpoint terms
Cached input /M
$0.300
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%
$0.450 $15.00 undeclared 100.00%
Io Netio-net/fp4
Endpoint terms
Cached input /M
$0.120
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
100.00%
$0.600 $11.50 fp4 99.89%
Makoramakora/fp4
Endpoint terms
Cached input /M
$0.500
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%
$1.00 $18.00 fp4 100.00%
Chuteschutes/mxfp4
Endpoint terms
Cached input /M
$0.185
Context limit
1,048,576 tokens
Output limit
65,535 tokens
Tools
Not listed by endpoint
Reasoning
Listed by endpoint
Promotional discount
None reported
Uptime · last 30 minutes
Unknown
$1.85 $9.50 mxfp4 100.00%
DigitalOceandigitalocean
Endpoint terms
Cached input /M
$0.255
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%
$2.55 $12.95 undeclared 100.00%
DeepInfradeepinfra/mxfp4
Endpoint terms
Cached input /M
$0.285
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%
$2.85 $14.25 mxfp4 100.00%
BaseTenbaseten/fp8
Endpoint terms
Cached input /M
$0.300
Context limit
1,048,576 tokens
Output limit
262,144 tokens
Tools
Listed by endpoint
Reasoning
Listed by endpoint
Promotional discount
None reported
Uptime · last 30 minutes
100.00%
$3.00 $15.00 fp8 100.00%
Nebiusnebius/fp4
Endpoint terms
Cached input /M
$0.300
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%
$3.00 $15.00 fp4 100.00%
Parasailparasail/fp4
Endpoint terms
Cached input /M
$0.300
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%
$3.00 $15.00 fp4 100.00%
Riverriver
Endpoint terms
Cached input /M
$0.300
Context limit
1,048,576 tokens
Output limit
1,048,575 tokens
Tools
Not listed by endpoint
Reasoning
Listed by endpoint
Promotional discount
None reported
Uptime · last 30 minutes
100.00%
$3.00 $15.00 undeclared 99.70%
Amazon Bedrockamazon-bedrock/us-east-2
Endpoint terms
Cached input /M
$0.300
Context limit
1,048,576 tokens
Output limit
128,000 tokens
Tools
Listed by endpoint
Reasoning
Listed by endpoint
Promotional discount
None reported
Uptime · last 30 minutes
100.00%
$3.00 $15.00 undeclared 99.74%
Alibabaalibaba
Endpoint terms
Cached input /M
$0.300
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
100.00%
$3.00 $15.00 undeclared 100.00%
Modalmodal/mxfp4
Endpoint terms
Cached input /M
$0.300
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%
$3.00 $15.00 mxfp4 100.00%
Togethertogether
Endpoint terms
Cached input /M
$0.300
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%
$3.00 $15.00 undeclared 100.00%
Fireworksfireworks
Endpoint terms
Cached input /M
$0.300
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
75.00%
$3.00 $15.00 undeclared 99.88%
Moonshot AImoonshotai
Endpoint terms
Cached input /M
$0.300
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%
$3.00 $15.00 undeclared 99.86%
Amazon Bedrockamazon-bedrock/us-east-1
Endpoint terms
Cached input /M
$0.330
Context limit
1,048,576 tokens
Output limit
128,000 tokens
Tools
Listed by endpoint
Reasoning
Listed by endpoint
Promotional discount
None reported
Uptime · last 30 minutes
100.00%
$3.30 $16.50 undeclared 100.00%
Parasailparasail/fast
Endpoint terms
Cached input /M
$0.450
Context limit
1,048,576 tokens
Output limit
943,718 tokens
Tools
Not listed by endpoint
Reasoning
Listed by endpoint
Promotional discount
None reported
Uptime · last 30 minutes
100.00%
$4.50 $22.50 fp4 100.00%
Fireworksfireworks/us
Endpoint terms
Cached input /M
$0.450
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%
$4.50 $22.50 undeclared 100.00%
Fireworksfireworks/fast
Endpoint terms
Cached input /M
$0.450
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%
$4.50 $22.50 undeclared 100.00%

Independent scores

LMArena Elo1474.7max
LMArena rowkimi-k3-max

LMArena Elo under CC BY 4.0. Absence of another board is not a score of zero.

Best rankings by task

  • ASCII art #3 1352
  • Data visualisation #4 1348
  • Agenticgamedev #4 1202
  • Websites #5 1334
  • Htmlslides #5 1157
  • Full-stack apps #7 1287
  • Native Android apps #7 1253
  • Code categories #8 1345

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.

Capability

Context window1M
Max output943K
Input modestext, image, video
Tool useyes
Reasoningoptional
Open weightsyes

Provenance

Price sourceopenrouter.ai
Fetched2026-11-22
Quality dataverified
Cross-checkedvendor page

Our take

editorial — not a measurement

Kimi is a candidate for teams comparing hosted multimodal use with self-hosting. The accepted record lists open weights, but hardware and licence requirements still need review. Use the current proof and benchmark evidence for measured standing. Other models’ withheld latency figures cannot establish a speed comparison; measure responsiveness on your intended deployment.

Strengths

  • Open weights are recorded
  • Text, image and video input are listed

Weaknesses

  • Measure first-token latency and sustained generation separately on your deployment
  • The context window and output ceiling are different limits

Reach for it when

  • Hosted-versus-self-hosted evaluations
  • Multimodal workflows with an explicit latency test

Avoid it if

  • The decision depends on a latency advantage you have not measured
  • You have not checked serving capacity and licence terms

Sources: openrouter.ai

Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI. It is suited for complex coding, knowledge work, and long-horizon agentic workflows, and is particularly strong at...

Questions this page answers

What does Kimi K3 cost?

$3.00/M in, $15.00/M out in this catalogue, as of the fetch date on this page. That is the API row, not a subscription.

Does Kimi K3 have an independent quality score?

Kimi K3 has an LMArena score in this catalogue.

What beats Kimi K3?

Gemini 4 Neon has an equal-or-higher measured score and an equal-or-lower price.

Does this page use Artificial Analysis scores for Kimi K3?

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 K3 endpoint the same product?

Headline cheapest is a lower precision. Like-for-like at the best declared precision is $3.00/M from BaseTen.

MODEL MONUMENT

Save or share this proof

Badge

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.

Kimi K3 — Undominated.ai dominance verdict

Markdown
[![Kimi K3 — Undominated.ai dominance verdict](https://undominated.ai/badge/moonshotai__kimi-k3.svg)](https://undominated.ai/models/moonshotai__kimi-k3/)
HTML
<a href="https://undominated.ai/models/moonshotai__kimi-k3/"><img src="https://undominated.ai/badge/moonshotai__kimi-k3.svg" alt="Kimi K3 — Undominated.ai dominance verdict" height="36"></a>

Direct file: https://undominated.ai/badge/moonshotai__kimi-k3.svg — a static SVG, written by scripts/build-badges.mjs on every build, so the copy you embed is never older than the last deploy.

Evidence & Ask