Skip to the content
Rhumb
Menu

Kimi K3

moonshotai/kimi-k3

Maker
Moonshot AI, China
Released
2026-07-16
Family
kimi-k3
Weights
open
Tasks
text.chat, text.reasoning, code, vision.understand, vision.extract
Cheapest offering
OpenRouter, about $0.004959 for a typical text.chat call
Try it in the sandboxUse it from the API

Offerings

ProviderModel id at the providerStatusPrice per 1M tokensPer-unit pricesLimitsCapabilities (level)
Amazon Bedrockglobal.moonshotai.kimi-k3ga
  • Input: $3
  • Output: $15
  • Cache read: $0.3
  • Cache write (5 min): $3.75
Since 2026-11-03 · models.dev, MIT		none
  • Context: 1,048,576 tokens
  • Max output: 128,000 tokens
  • input.text claimed
  • input.image claimed
  • input.pdf claimed
  • output.text claimed
  • tools claimed
  • structured_output claimed
  • reasoning claimed
  • tool_choice claimed
  • prompt_caching claimed
Amazon Bedrockus.moonshotai.kimi-k3ga
  • Input: $3.3
  • Output: $16.5
  • Cache read: $0.33
  • Cache write (5 min): $4.125
Since 2026-11-03 · models.dev, MIT		none
  • Context: 1,048,576 tokens
  • Max output: 128,000 tokens
  • input.text claimed
  • input.image claimed
  • input.pdf claimed
  • output.text claimed
  • tools claimed
  • structured_output claimed
  • reasoning claimed
  • tool_choice claimed
  • prompt_caching claimed
Alibaba Cloud Model Studio (DashScope)kimi-k3ga
  • Input: $3
  • Output: $15
  • Cache read: $0.3
Since 2026-11-04 · models.dev, MIT		none
  • Context: 1,048,576 tokens
  • Max output: 1,048,576 tokens
  • input.text claimed
  • input.image claimed
  • input.pdf claimed
  • output.text claimed
  • tools claimed
  • structured_output claimed
  • reasoning claimed
DeepInframoonshotai/Kimi-K3ga
  • Input: $2.85
  • Output: $14.25
  • Cache read: $0.285
  • Cache write (5 min): $3.5625
Since 2026-11-03 · models.dev, MIT		none
  • Context: 1,048,576 tokens
  • Max output: 131,072 tokens
  • input.text claimed
  • input.image claimed
  • input.pdf claimed
  • output.text claimed
  • tools claimed
  • structured_output claimed
  • reasoning claimed
  • tool_choice claimed
  • prompt_caching claimed
Fireworks AIaccounts/fireworks/models/kimi-k3ga
  • Input: $3
  • Output: $15
  • Cache read: $0.3
  • Input, priority tier: $3.75
  • Output, priority tier: $18.75
  • Cache read, priority tier: $0.375
Since 2026-11-03 · models.dev, MIT		none
  • Context: 1,048,576 tokens
  • Max output: 131,072 tokens
  • input.text claimed
  • input.image claimed
  • input.pdf claimed
  • output.text claimed
  • tools claimed
  • structured_output claimed
  • reasoning claimed
  • tool_choice claimed
Fireworks AIaccounts/fireworks/routers/kimi-fast-latestga
  • Input: $4.5
  • Output: $22.5
  • Cache read: $0.45
Since 2026-11-03 · models.dev, MIT		none
  • Context: 1,048,576 tokens
  • Max output: 131,072 tokens
  • input.text claimed
  • input.image claimed
  • input.pdf claimed
  • output.text claimed
  • tools claimed
  • structured_output claimed
  • reasoning claimed
Fireworks AIaccounts/fireworks/routers/kimi-k3-fastga
  • Input: $4.5
  • Output: $22.5
  • Cache read: $0.45
Since 2026-11-03 · models.dev, MIT		none
  • Context: 1,048,576 tokens
  • Max output: 131,072 tokens
  • input.text claimed
  • input.image claimed
  • input.pdf claimed
  • output.text claimed
  • tools claimed
  • structured_output claimed
  • reasoning claimed
  • tool_choice claimed
Fireworks AIaccounts/fireworks/routers/kimi-k3-spotga
  • Input: $2.1
  • Output: $10.5
  • Cache read: $0.21
Since 2026-11-03 · models.dev, MIT		none
  • Context: 1,048,576 tokens
  • Max output: 131,072 tokens
  • input.text claimed
  • input.image claimed
  • input.pdf claimed
  • output.text claimed
  • tools claimed
  • structured_output claimed
  • reasoning claimed
  • tool_choice claimed
  • prompt_caching claimed
Fireworks AIaccounts/fireworks/routers/kimi-latestga
  • Input: $3
  • Output: $15
  • Cache read: $0.3
  • Input, priority tier: $3.75
  • Output, priority tier: $18.75
  • Cache read, priority tier: $0.375
Since 2026-11-03 · models.dev, MIT		none
  • Context: 1,048,576 tokens
  • Max output: 131,072 tokens
  • input.text claimed
  • input.image claimed
  • input.pdf claimed
  • output.text claimed
  • tools claimed
  • structured_output claimed
  • reasoning claimed
Moonshot AI (Kimi)kimi-k3ga
  • Input: $2.9879
  • Output: $14.9395
  • Cache read: $0.2988
  • Cache write (5 min): $2.9879
Since 2026-11-04 · models.dev, MIT		none
  • Context: 1,048,576 tokens
  • Max output: 1,048,576 tokens
  • input.text claimed
  • input.image claimed
  • input.video claimed
  • input.pdf claimed
  • output.text claimed
  • tools claimed
  • structured_output claimed
  • reasoning claimed
  • tool_choice claimed
  • prompt_caching claimed
OpenRoutermoonshotai/kimi-k3ga
  • Input: $0.2
  • Output: $15
  • Cache read: $0.19
Unverified: sources disagree by more than 5%Since 2026-11-04 · models.dev, MIT		none
  • Context: 1,048,576 tokens
  • Max output: 943,718 tokens
  • input.text claimed
  • input.image claimed
  • input.video claimed
  • input.pdf claimed
  • output.text claimed
  • tools claimed
  • structured_output claimed
  • reasoning claimed
Together AImoonshotai/Kimi-K3ga
  • Input: $3
  • Output: $15
  • Cache read: $0.3
Since 2026-11-03 · models.dev, MIT		none
  • Context: 1,048,576 tokens
  • Max output: 131,072 tokens
  • input.text claimed
  • input.image claimed
  • input.pdf claimed
  • output.text claimed
  • tools claimed
  • structured_output claimed
  • reasoning claimed
  • parallel_tools claimed
  • tool_choice claimed
  • prompt_caching claimed

Quality scores

BasisScore (0–1)RawMeasuredSource
epoch:gpqa_diamond0.9660.93122026-07-16Epoch AI, CC-BY-4.0, normalized by Nanner Tech
curated0.950 (estimated)0.95002026-11-02Curated tier (estimated), Nanner Tech
epoch:frontiermath0.7700.72182026-07-17Epoch AI, CC-BY-4.0, normalized by Nanner Tech
lmarena:webdev0.5851656.39092026-10-28LMArena, CC-BY-4.0, normalized by Nanner Tech
lmarena:agent0.0430.00862026-11-02LMArena, CC-BY-4.0, normalized by Nanner Tech

Aliases

Other names the API accepts for this model.

  • accounts/fireworks/models/kimi-k3
  • accounts/fireworks/routers/kimi-fast-latest
  • accounts/fireworks/routers/kimi-k3-fast
  • accounts/fireworks/routers/kimi-k3-spot
  • accounts/fireworks/routers/kimi-latest
  • global.moonshotai.kimi-k3
  • kimi k3 (max)
  • kimi-k3
  • moonshot/kimi-k3
  • us.moonshotai.kimi-k3

Use it from the API

Look this model up, or ask for the best model for its task on the providers that offer it. See the quickstart and the API reference.

Look up this model
curl 'https://rhumbdata.com/v1/models/moonshotai/kimi-k3' \
  -H "Authorization: Bearer $RHUMB_KEY"
Resolve text.chat on its providers
curl 'https://rhumbdata.com/v1/resolve?task=text.chat&providers=bedrock,dashscope,deepinfra,fireworks,moonshot,openrouter,together' \
  -H "Authorization: Bearer $RHUMB_KEY"

Built from catalog version 2026-11-04.3 of . Prices are list prices per 1M tokens unless marked otherwise; every score shows its source's notice (see Attributions).