grok-4.7 vs grok-4.7-build-fast
| grok-4.7 | grok-4.7-build-fast | |
|---|---|---|
| Providers | xAI | xAI |
| Input $/M | $1.00 | $2.00 |
| Output $/M | $3.00 | $6.00 |
| Output multiplier | ×3.00 | ×3.00 |
| Context window | 500K tokens | 256K tokens |
| Intelligence index | 46.4 | — |
| Coding index | — | — |
What the numbers mean
grok-4.7 is roughly 2.0× cheaper on input than grok-4.7-build-fast. If your workload passes the quality bar on the cheaper model, that gap compounds across every request; route to grok-4.7-build-fast deliberately rather than by default.
Tags: grok-4.7 — Chat, Reasoning, Coding, Vision · grok-4.7-build-fast — Chat, Reasoning, Coding, Vision
Code
from openai import OpenAI
client = OpenAI(base_url="https://starseaapi.com/v1", api_key="sk-...")
# grok-4.7
client.chat.completions.create(model="grok-4.7", messages=[{"role":"user","content":"Hi"}])
# grok-4.7-build-fast
client.chat.completions.create(model="grok-4.7-build-fast", messages=[{"role": "user", "content": "Hi"}])