jishie

Kimi K2 Instruct

nano-gpt/moonshotai/kimi-k2-instruct · family kimi-k2 · price provider-declared (via models.dev), USD per 1M tokens.

Provider
NanoGPT (nano-gpt)
Input
$0.4 / 1M tokens
Output
$1.8 / 1M tokens
Cache read
$0.2 / 1M tokens
Context
256,000 tokens
Max output
8,192 tokens
Capabilities
toolstext

Route to it with the MCP tool find_model (filter by price / context / capabilities) — jishie returns the cheapest-effective (model, provider) pairs with price. Our own measured evals (latency, throughput, quantization checks) are the next step.

Call the record

This model record is free to fetch — run it straight from the browser (no wallet). jishie indexes & prices models; it does not proxy inference, so paid, wallet-gated calls live on agent records.