Pricing, context window, capabilities, and release date — pulled from each provider's public docs. Both are available via the same AIgateway OpenAI-compatible endpoint; flip the model string to switch.
Both models stream in parallel through your own AIgateway key. Tokens, latency, and cost update as they arrive.
| Grok 4 Fast xai/grok-4-fast | Grok 4.20 Reasoning xai/grok-4.20-0309-reasoning | |
|---|---|---|
| Provider | xAI | xAI |
| Family | Grok 4 | Grok 4 |
| Modality | text | text |
| Context window | 256,000 tok | 2,000,000 tok |
| Max output | 16,384 tok | 4,096 tok |
| Released | 2025-09-19 | 2026-05-22 |
| Input price | $0.500 /1M | $2.00 /1M |
| Output price | $2.00 /1M | $6.00 /1M |
| Cache read | — | — |
| Tools | yes | — |
| Streaming | yes | yes |
| Vision | — | — |
| JSON mode | yes | — |
| Reasoning | — | — |
| Prompt caching | — | — |
xAI Grok 4 Fast — low-latency variant.
xAI's Grok 4.20 reasoning model. Uses extended thinking to work through complex problems, returning a reasoning trace alongside the final answer.
# pip install aigateway-py openai
# aigateway-py: sub-accounts, evals, replays, jobs, webhook verify.
# openai SDK: chat/embeddings/images/audio — drop-in compat per our SDK's own guidance.
from openai import OpenAI
client = OpenAI(
base_url="https://api.aigateway.sh/v1",
api_key="sk-aig-...",
)
# Try Grok 4 Fast
client.chat.completions.create(
model="xai/grok-4-fast",
messages=[{"role":"user","content":"hello"}],
)
# Try Grok 4.20 Reasoning — same client, same key
client.chat.completions.create(
model="xai/grok-4.20-0309-reasoning",
messages=[{"role":"user","content":"hello"}],
)