Moonshot AI's K2 — strong coding and long-context model.
| Provider | Context | Price · in / out |
|---|---|---|
| 128K | $0.53 / $2.29/MTok |
routing.strategyproviders.onlyproviders.excludeproviders.ordermax_cost_usddata_policydocs →Collecting — charts appear after two days.
curl https://www.ninjachat.ai/api/v1/chat/completions \
-H "Authorization: Bearer $NINJACHAT_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "kimi-k2.5",
"messages": [{ "role": "user", "content": "Hello!" }],
"stream": true
}'Moonshot AI's upgraded K2.5 — enhanced reasoning over K2.
Kimi K2.5 costs $0.53/M input tokens and $2.29/M output tokens.
Kimi K2.5 accepts text and returns text.
POST /api/v1/chat/completions with `"model": "kimi-k2.5"`.
Kimi K2, Kimi K2.6, Kimi K2.7 Code, Kimi K3.
Moonshot's coding-specialized Kimi with faster, more token-efficient long-horizon execution.
Moonshot's Kimi K3 frontier model on Fireworks with native vision and 1M context.
Anthropic's highest-capability generally available model for long-running agents.