# Grok 4.7 API

Grok 4.7 is xAI's frontier Grok model for coding, agentic tasks and knowledge work, with text and image input and a 500K-token context window; list price $2.00 in / $6.00 out per 1M tokens, provider list as at 1 November 2026.

- Provider: xAI
- Model ID: grok-4.7
- Type: Chat
- Region: Global (provider global routing)
- Context window: 500,000 tokens
- Max output: not listed
- Modalities: text, vision, tools, reasoning
- Endpoints: OpenAI Chat Completions https://api.seedrise.ai/v1
- Prices checked: 1 November 2026

## Provider list price

Provider list price as at 1 November 2026, per 1M tokens. AUD at a reference rate of 1 USD = 1.53 AUD; invoices use the rate on the day.

| Token type | USD | AUD |
|---|---:|---:|
| Input | 2.00 | 3.06 |
| Output | 6.00 | 9.18 |
| Cached input | 0.50 | 0.77 |

Your Seedrise rate is quoted per account against this list price. Request a rate card: https://seedrise.ai/contact?model=grok-4.7

Requests whose prompt reaches 200K tokens are billed by xAI at $4.00 in / $12.00 out and $1.00 cached for every token in the request. Global: runs on the provider's global routing; no Australian-region option as at 1 November 2026.

## Strengths

- Reasoning effort low, medium, high or xhigh, with high as the default
- Function calling and structured outputs
- 500K-token context window for large codebases and document sets
- Cached input lists at $0.50 per 1M tokens

## Typical use cases

- Coding agents and code review
- Knowledge work such as research and report drafting
- Agentic tasks with tool calls
- Analysis that combines images and text

## Quickstart

A first request with curl. Replace sk-... with your Seedrise key.

```bash
curl https://api.seedrise.ai/v1/chat/completions \
  -H "Authorization: Bearer sk-..." \
  -H "Content-Type: application/json" \
  -d '{"model":"grok-4.7","messages":[{"role":"user","content":"Hello"}]}'
```

OpenAI SDK, Python:

```python
from openai import OpenAI

client = OpenAI(base_url="https://api.seedrise.ai/v1", api_key="sk-...")

r = client.chat.completions.create(
    model="grok-4.7",
    messages=[{"role": "user", "content": "Summarise this contract in three bullets."}],
)
print(r.choices[0].message.content)
```

## Where it runs

Global: Served on the provider's global routing.

## Related models

- [Grok 4.3](https://seedrise.ai/models/grok-4.3): US$1.25 input · US$2.50 output per 1M tokens, Global
- [Claude Sonnet 5.5](https://seedrise.ai/models/claude-sonnet-5-5): US$2.00 input · US$10.00 output per 1M tokens, AU
- [GPT-6.1 Sol](https://seedrise.ai/models/gpt-6.1-sol): US$2.00 input · US$10.00 output per 1M tokens, Global
- [Gemini 4 Argon](https://seedrise.ai/models/gemini-4-argon): US$2.00 input · US$10.00 output per 1M tokens, Global

## FAQ

### What is the model ID for Grok 4.7?

Use grok-4.7 as the model field, with no vendor prefix, on the OpenAI-compatible endpoint at https://api.seedrise.ai/v1. GET /v1/models returns the IDs your key can call.

### How does the Seedrise rate for Grok 4.7 compare to the list price?

xAI's list price as at 1 November 2026 is US$2.00 per 1M input tokens and US$6.00 per 1M output tokens. Seedrise quotes rates per account against the provider's published list price for the same routing. Volume and committed tiers sit below list.

### What is the context window and max output of Grok 4.7?

Grok 4.7 has a context window of 500,000 tokens, per the provider documentation checked on 1 November 2026. Maximum output is not listed on our rate card; ask us for the current limit.

### Can Grok 4.7 run in Australia?

Not at present. Grok 4.7 is served on the provider's global routing. Models marked AU in the model library can be pinned to Sydney or Melbourne on request.

### What happens to Grok 4.7 pricing above 200K tokens?

Once a prompt reaches 200K tokens, xAI bills every token in that request at the higher tier: $4.00 in / $12.00 out and $1.00 cached per 1M tokens, as at 1 November 2026.

### Can I turn reasoning off on Grok 4.7?

No. xAI lists low, medium, high and xhigh effort levels, with high as the default. For calls without reasoning, Grok 4.3 accepts an effort of none.

Model names are trademarks of their respective providers.

Source: https://seedrise.ai/models/grok-4.7