MoonshotAI

Kimi K3 API pricing.

Kimi K3 is MoonshotAI’s model on the API market, released 16 Jul 2026. Prices are per million tokens in USD, as last read from the price list.

$0.19Input / 1M
$15Output / 1M
1.0MContext
944KMax output
Capability scores
Epoch AI
Maths3 of 4 benchmarks69
Science and knowledge2 of 2 benchmarks71
CodingNot tested by Epoch
Reasoning and puzzles2 of 2 benchmarks26
Agents and long tasks1 of 3 benchmarks6

Each bar is this model's score in that area. The white tick marks the best score any model Epoch has tested reaches there.

Epoch Capabilities Index
158
Range 156 to 161 · #20 of 271 models Epoch has scored
Maths
69average of 3 of 4 Epoch results
FrontierMath (tiers 1 to 3) (max)72%
FrontierMath (tier 4) (max)39%
OTIS Mock AIME (max)97%
Science and knowledge
71average of 2 of 2 Epoch results
GPQA Diamond (max)93%
SimpleQA Verified (max)51%
Reasoning and puzzles
26average of 2 of 2 Epoch results
Chess puzzles (high)37%
Mystery game puzzles (max)26%
Agents and long tasks
6average of 1 of 3 Epoch results
Furniture assembly (max)34%

The index combines many benchmarks into one general-capability score; the range is how sure Epoch is of the number. Each area score is this site's average of the model's Epoch results in that area, where 0 is what guessing would score and 100 is perfect. Compare every model, and value for money →

Source: Epoch AI, Capabilities & benchmarking (licensed CC BY 4.0). Data refreshed 2 November 2026. These are Epoch's own tests; other benchmark sites can rank models differently.

Cheaper models that come close
Our working on Epoch's index
  1. DeepSeek V4 Flash 0731 · DeepSeekindex 154.94 (3 below) · 96% cheaper
  2. DeepSeek V4.1 Flash · DeepSeekindex 156.11 (2 below) · 96% cheaper
  3. Claude Haiku 5.5 · Anthropicindex 160.37 · 95% cheaper
  4. GPT-6 Luna · OpenAIindex 156.75 (2 below) · 95% cheaper

Models within 5 points of Kimi K3 on Epoch's Capabilities Index that cost less, comparing a typical chat mix (three parts input to one part output). A few points of index is a small difference and says nothing about your task: a place to start testing, not a verdict. Capability against price for every model.

Specification
USD per million tokens
Provider
MoonshotAI
Model id
moonshotai/kimi-k3
Input
$0.19
Output
$15
Cached input
$0.18
Context window
1.0M tokens
Maximum output
944K tokens
Takes
text, image, video
Returns
text
Tool use
Yes
Reasoning
Yes
Released
16 Jul 2026
First tracked
17 Sept 2026

At $0.19 per million input tokens, Kimi K3 is dearer than 106 of the 340 models on the price list.

Price changes
Tracked since 17 Sept 2026

No price change has been recorded since tracking began on 17 Sept 2026. Prices are checked every six hours, and any change is listed here and on model changes.

Want an email when this model's price changes? Tell us →

Coverage
1 story
  1. AWS Machine Learning Blog ·
    Introducing Kimi K3 on Amazon Bedrock
Other entries for this model
More from MoonshotAI
Cheapest input first
  1. Kimi K2.5$0.50 in · $2.50 out
  2. Kimi K2 0711$0.57 in · $2.30 out
  3. Kimi K2.7 Code$0.60 in · $3.50 out
  4. Kimi K2 Thinking$0.60 in · $2.50 out
  5. Kimi K2 0905$0.60 in · $2.50 out
  6. Kimi K2.6$0.65 in · $3.41 out
  7. Kimi K3.1 Pro$2.00 in · $10 out

Prices and specifications come from OpenRouter’s catalogue, last read 2 Nov 2026. A provider’s own price may differ; how this is collected.