Kimi K3
Moonshot · released 2026-03-15
Quality (AA Index)80
Input price$0.30
Output price$1.20
Context200K
Throughput150 tok/s
P50 latency0.8s
Side-by-side pricing, capabilities, real-world cost across common scenarios, and our editorial pick.
Moonshot · released 2026-03-15
Anthropic · released 2026-04-08
Links open in a new tab via our OpenRouter referral. Affiliate disclosure
| Metric | Kimi K3 | Claude 4.6 Sonnet | Verdict |
|---|---|---|---|
Input price /1M tokens | $0.30 | $3.00 | Kimi K3 −90% |
Output price /1M tokens | $1.20 | $15.00 | Kimi K3 −92% |
Context window max input length | 200K | 200K | Tied |
AA Quality AA Intelligence Index (0–100) | 80 | 89 | Claude 4.6 Sonnet +9pt |
Arena Elo LMArena human-pref Elo (800–2000) | — | — | Tied |
Throughput tokens per second | 150 | 85 | Kimi K3 +76% |
P50 latency first token | 0.8s | 1.1s | Kimi K3 −27% |
Vision multimodal | — | ||
Function calling tool use | Tied | ||
Reasoning mode chain-of-thought | — |
| Scenario | Kimi K3 | Claude 4.6 Sonnet |
|---|---|---|
customer support 1000K req · 600/180 tok | $396 | $4.5K |
chat with docs 300K req · 4000/300 tok | $468 | $5.0K |
code generation 500K req · 2000/500 tok | $600 | $6.8K |
voice assistant 600K req · 800/200 tok | $288 | $3.2K |
Set Kimi K3 as primary, Claude 4.6 Sonnet as fallback. One key, one bill, automatic failover when Kimi K3 errors.
$ curl https://api.aipricly.com/v1/chat/completions \
-H "Authorization: Bearer $AIPC_KEY" \
-d '{
"routing": {
"primary": "moonshot/kimi-k3",
"fallback": ["anthropic/claude-4-6-sonnet"]
},
"messages": [{"role": "user", "content": "..."}]
}'