Kimi K3
by Moonshot AI · moonshotai/kimi-k3 · #288 cheapest of 325 paid models
Prices updated Jul 22, 2026, 1:31 AM UTC · refreshed hourly
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...
Compare vs:Claude Sonnet 5Claude Opus 4.6Claude Haiku 4.5GPT-5.6 Sol
Pricing
Input
$3.00
per 1M tokens
Output
$15.00
per 1M tokens
Blended (3:1)
$6.00
3 input : 1 output
Cache read
$0.30
per 1M cached tokens
Cache write
—
per 1M tokens
Cache & batch economics
Effective prices for Kimi K3 with prompt caching.
| Cache hit rate | Effective blended $/1M | Example request* | vs no cache |
|---|---|---|---|
| 0% | $6.00 | $0.321 | — |
| 50% | $4.99 | $0.186 | −42% |
| 90% | $4.18 | $0.078 | −76% |
*Example: 100K sticky context + 2K new input + 1K output. Batch discount is an approximate 50% off list rates (available for OpenAI / Anthropic / Google — not flagged for this creator). Confirm on the vendor’s pricing page.
What a request costs
| Workload | Input tokens | Output tokens | Cost / request | Cost / 1K requests |
|---|---|---|---|---|
| Short chat message | 500 | 300 | $0.006 | $6.00 |
| Document summary | 8,000 | 1,000 | $0.039 | $39.00 |
| Codebase question (RAG) | 30,000 | 2,000 | $0.12 | $120.00 |
| Long-context analysis | 150,000 | 5,000 | $0.525 | $525.00 |
Performance
Intelligence Index
57.1
AA composite quality
Coding Index
76.2
Math Index
—
Agentic Index
50.1
Output speed
—
median
Time to first token
—
median
Time to first answer
—
after reasoning tokens
Design Arena Elo
| Category | Elo |
|---|---|
| Website | 1,382 |
| Web apps | 1,314 |
| UI components | 1,448 |
| Data viz | 1,356 |
| 3D | 1,448 |
| Godot game dev | 1,161 |
| Python→PPTX slides | 1,282 |
Specs
Context window
1.05M
tokens
Max output
—
tokens
Input modalities
text, image
Tokenizer
Other