venice/kimi-k3 · family kimi-k3 · price provider-declared (via models.dev), USD per 1M tokens. Capabilities: toolsreasoningtextimage.
venice)“Kimi K3” is offered by 9 providers — cheapest-effective first. Kenari is the cheapest at $0.00 blended.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| Kenari | free | free | $0.00 | 1049k |
| Umans AI Coding Plan | free | free | $0.00 | 1049k |
| Kimi For Coding | free | free | $0.00 | 1049k |
| Tinfoil | $2 | $6 | $3.00 | 256k |
| CrofAI | $2 | $8 | $3.50 | 1000k |
| Requesty | $2.25 | $11.25 | $4.50 | 1049k |
| NanoGPT | $2.5 | $13.5 | $5.25 | 1049k |
| ai& | $3 | $12.5 | $5.38 | 1049k |
| Venice AI (this) | $3.75 | $18.75 | $7.50 | 1000k |
jishie indexes & prices models; it does not proxy inference. Most providers are OpenAI-compatible — point base_url at Venice AI and pass this model id:
curl $BASE_URL/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
-d '{"model":"kimi-k3","messages":[{"role":"user","content":"hello"}]}'
Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):