Moonshot

Kimi K3

Launched 2026-07-16 · Listed on OpenRouter 2026-07-16

Prices updated . Benchmarks updated .

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...

You send / 1M

$0.192

tokens in

It replies / 1M

$16.00

tokens out

Context

1M

tokens it can read at once

Typical request

$0.0082

1,000 words in, 400 out

Benchmarks

BenchmarkScoreKindDateSource
Epoch Capabilities Index158.3Independent2026-07-16Epoch AI
GPQA DiamondMax effort93.1%Independent2026-07-16Epoch AI
OTIS Mock AIMEMax effort97.2%Independent2026-07-16Epoch AI
SimpleQA VerifiedMax effort50.6%Independent2026-08-27Epoch AI
ARC-AGI-2Max effort60.4%Independent2026-07-16ARC Prize, republished by Epoch AI
GDP.pdfMax effort19.0%Independent2026-07-16Surge AI GDP.pdf, republished by Epoch AI
CritPtMax effort23.4%Independent2026-07-16CritPt, republished by Epoch AI
Arena Elo (text)Max effort1,476Independent2026-10-28LMArena
Arena Elo (webdev)Max effort1,656Independent2026-10-28LMArena

Rankings on this site use the Epoch Capabilities Index, an independent composite. Lab-reported rows are the lab's own figures and are kept separate.

Data privacy

No training or retention: Yes. At least one provider serves it with zero data retention.

ProviderYou send / 1MIt replies / 1MUptimePrivacy policy
Wafer · mxfp4$0.276$9.60100%Read
Relace · fp4$0.182$11.01100%Read
DigitalOcean$2.55$12.95100%Read
Io Net · fp4$2.10$14.00100%Read
DeepInfra · mxfp4$2.85$14.25100%Read
Nebius · fp4$3.00$15.00100%Read
River$3.00$15.00100%Read
InferenceNet · fp4$0.234$15.00100%Read
Amazon Bedrock$3.00$15.00100%Read
InferenceNet · fp4$0.234$15.00100%Read
Parasail · fp4$3.00$15.00100%Read
Together$3.00$15.0099%Read
Fireworks$3.00$15.0098%Read
BaseTen · fp8$3.00$15.00100%Read
Moonshot AI$3.00$15.00100%Read
Wafer · mxfp4$0.153$16.00100%Read
Wafer · mxfp4$0.192$16.00100%Read
InferenceNet · fp4$0.450$18.00100%Read
InferenceNet · fp4$0.450$18.00100%Read
Makora · fp4$1.00$18.0098%n/a
Parasail · fp4$4.50$22.50100%Read
Fireworks$4.50$22.5088%Read
Fireworks$4.50$22.5094%Read

Based on OpenRouter and Vercel AI Gateway data. Confirm terms with the provider before sending sensitive data.

What it can do

  • Reads: text, image, video, pdf
  • Writes: text
  • Weights: Open weights, restricted
  • Reasoning: Yes
  • Tool calling: Yes
  • Longest reply: 128K tokens
  • Repeated text is billed at $0.182 per 1M (prompt caching)

Compare with

Appears in

Estimate your monthly cost with Kimi K3

Sources and licenses

  • OpenRouter: Prices, context windows, modalities and the model list come from the OpenRouter public API. Data: OpenRouter.
  • Vercel AI Gateway: The no-training flag comes from the Vercel AI Gateway model list.
  • models.dev: Lab launch dates, open-weights flags and knowledge cutoffs come from models.dev. Copyright (c) 2025 models.dev, MIT License.
  • Epoch AI: Independent benchmark scores and the Epoch Capabilities Index (ECI) come from Epoch AI's Benchmarking Hub, used under CC BY 4.0. Epoch AI, Capabilities & benchmarking, epoch.ai/benchmarks. Scores Epoch marks as external keep their original license, and the source is named on each score.
  • LMArena: Arena Elo (text, webdev and vision) comes from the LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset), CC BY 4.0, leaderboard date 2026-10-28.
  • Lab-reported scores, when an editor has added them, are the lab's own numbers. Each one links to the source and is labeled lab-reported. They are not used to rank the lists.
  • What a score measures: the benchmark guide.