Grok 4.7 API
Model ID: grok-4.7 · Developer: xAI · Available on 7API: yes, as of 2026-11-20
Call Grok 4.7 with any OpenAI- or Anthropic-compatible client. Use base URL https://7api.st/v1 (OpenAI) or https://7api.st (Anthropic) and send "model": "grok-4.7".
Specifications
| Model ID | grok-4.7 |
| Context window | 500,000 tokens |
| Max output | 65,536 tokens |
| Input | Text |
| Tool calling | Yes |
| Streaming | Yes |
| Reasoning effort | Model default |
| API formats | Chat Completions, Responses, Anthropic Messages |
Pricing
| USD per 1M tokens | |
|---|---|
| Input | $0.10 |
| Output | $0.10 |
| Cached input | $0.02 |
For example, an agent turn with 150,000 cached input tokens, 2,000 new input tokens and 800 output tokens costs about $0.0033 on Grok 4.7. Billing is pay per token from a prepaid balance. See Pricing and billing.
Benchmarks
Independent scores for Grok 4.7, as published by third parties (retrieved 2026-10-24). 7API serves the same model, so these scores apply to it here.
| Benchmark | Result |
|---|---|
Artificial Analysis Intelligence Index, xhigh effort | 46 |
Artificial Analysis Intelligence Index, high effort | 46 |
Artificial Analysis Intelligence Index, low effort | 42 |
Example
from openai import OpenAI
client = OpenAI(base_url="https://7api.st/v1", api_key="YOUR_7API_KEY")
r = client.chat.completions.create(
model="grok-4.7",
messages=[{"role": "user", "content": "Write a haiku about caching."}],
)
print(r.choices[0].message.content)In Claude Code: /model claude-grok-4.7. Setup guides: Claude Code, OpenCode, Codex, Cursor.
