jishie

Kimi K2

opencode/kimi-k2 · family kimi-k2 · in: text → out: text · price provider-declared (via models.dev). Capabilities: tools text.

$0.93
Blended $/1M (3:1)
$0.4
Input $/1M
$2.5
Output $/1M
$2.90
1M in + 1M out
$0.4
Cache read $/1M
#3938 of 7,708
Cheapest rank
Provider
OpenCode Zen (opencode)
Kind
text (outputs text)
Context
262,144 tokens
Max output
262,144 tokens
Capabilities
tools text

Same model, other providers

“Kimi K2” is offered by 4 providers — cheapest-effective first. This one (OpenCode Zen) is the cheapest.

ProviderInputOutputBlendedContext
OpenCode Zen (this)$0.4$2.5$0.93262k
FastRouter$0.55$2.2$0.96131k
DevPass (LLM Gateway)$0.57$2.3$1.00256k
Qiniu———128k

Call it

jishie indexes & prices models; it does not proxy inference.

Most providers are OpenAI-compatible — point base_url at OpenCode Zen and pass this model id:

curl $BASE_URL/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
  -d '{"model":"kimi-k2","messages":[{"role":"user","content":"hello"}]}'

Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):

← all OpenCode Zen models · model index · JSON