Model Comparison

Run the same prompt across multiple Fireworks models side-by-side.

Prompt

DeepSeek V4.1 Flash

deepseek-v4p1-flash

fast

Latency

—

Tokens

—

Cost

—

Click "Compare" to run

GLM 5.3

glm-5p3

instruct

Latency

—

Tokens

—

Cost

—

Click "Compare" to run

Kimi K2.7 Code

kimi-k2p7-code

coding

Latency

—

Tokens

—

Cost

—

Click "Compare" to run

DeepSeek V4 Pro

deepseek-v4-pro-0813

reasoning

Latency

—

Tokens

—

Cost

—

Click "Compare" to run