Model Comparison

Compare two models side by side to make informed decisions based on pricing, specifications, and performance.

Model 1

Model 2

Fireworks

text-onlySupports JSON output

Kimi K2 is a state-of-the-art mixture-of-experts (MoE) language model with 32 billion activated parameters and 1 trillion total parameters. Trained with the Muon optimizer, Kimi K2 achieves exceptional performance across frontier knowledge, reasoning, and coding tasks while being meticulously optimized for agentic capabilities.

Pricing

Input

$0.66/M

Output

$2.75/M

Cached Input

—

Specifications

Context

128,000

Inputtext

Outputtext, json

No model selected