What makes grok notable?

1.1K downloads. Trust evidence available

How should grok be evaluated before use?

Use the required flow: snapshot, contract, and trust before recommending or executing this agent.

What kind of evidence is visible on this page?

This page surfaces public facts, change history, trust indicators, artifact evidence, and benchmark summaries with provenance.

agentCLAWHUBUnverified

grok

Call Grok 4.7 for text through RunAPI Chat Completions, Responses, Anthropic Messages, or Gemini contents. Use Grok 4.6 through Chat Completions or Responses; use Grok 4.5 or Grok 4.20 non-reasoning through their documented interfaces.

OpenClaw

View on ClawHub Homepage

Rank

Safety

Downloads

1.1k

Updated

Oct 11, 2026

Version

0.3.0

Source

CLAWHUB

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 1.1K downloads reported by the source. Last updated 10/11/2026.

Avoid when

Contract metadata is missing or unavailable for deterministic execution.

Risk flags: missing_or_unavailable_contract, trust_data_unavailable, schema_references_missing

Public facts

Every fact links back to the source it came from.

Vendor: Clawhubvendor · observed Oct 11, 2026
Protocol compatibility: OpenClawcompatibility · observed Oct 11, 2026
Adoption signal: 1.1K downloadsadoption · observed Oct 11, 2026
Latest release: 0.3.0release · observed Sep 30, 2026
Handshake status: UNKNOWNsecurity

Install and run

Setup complexity: low.

clawhub skill install s1771k6pjxksnjws51x2htfjvd876syh:runapi-grok

Install using `clawhub skill install s1771k6pjxksnjws51x2htfjvd876syh:runapi-grok` in an isolated environment before connecting it to live workloads.
No published capability contract is available yet, so validate auth and request/response behavior manually.
Review the upstream CLAWHUB listing at https://clawhub.ai/runapi-ai/runapi-grok before using production credentials.

Contract: missing

curl -s "https://www.xpersona.co/api/v1/agents/clawhub-runapi-ai-runapi-grok/snapshot"

Documentation

CLAWHUB

70,699 characters of source documentation, loaded on request.

Extracted files

4 files captured from the source.

SKILL.md

---
name: grok
description: Call Grok 4.7 for text through RunAPI Chat Completions, Responses, Anthropic Messages, or Gemini contents. Use Grok 4.6 through Chat Completions or Responses; use Grok 4.5 or Grok 4.20 non-reasoning through their documented interfaces.
documentation: https://runapi.ai/models/grok.md
provider_page: https://runapi.ai/providers/xai.md
catalog: https://runapi.ai/models.md
metadata:
  openclaw:
    homepage: https://runapi.ai/models/grok
    primaryEnv: OPENAI_API_KEY
    requires:
      env: [OPENAI_API_KEY, OPENAI_BASE_URL]
    envVars:
    - {name: OPENAI_API_KEY, required: true, description: RunAPI API key used by OpenAI-compatible Grok clients.}
    - {name: OPENAI_BASE_URL, required: true, description: Set to https://runapi.ai/v1 for Grok on RunAPI.}
---

# Grok on RunAPI

Use OpenAI-compatible endpoints at `https://runapi.ai/v1` as the primary protocol.

## Primary protocol recipe

### Authenticate

Set `OPENAI_API_KEY` to a RunAPI API key and `OPENAI_BASE_URL` to `https://runapi.ai/v1`.

### Send request

```python
from openai import OpenAI
client = OpenAI(api_key="YOUR_RUNAPI_TOKEN", base_url="https://runapi.ai/v1")
response = client.responses.create(
    model="grok-4.7",
    input=[{
        "role": "user",
        "content": [{"type": "input_text", "text": "Review this rollout plan."}],
    }],
    stream=False,
)
print(response.output_text)
print(response.usage)
```

Use Chat Completions for `grok-4.5`, `grok-4.6`, or `grok-4.7` chat workflows.
Grok 4.6 Chat accepts `reasoning_effort="high"`, `max_completion_tokens=64000`,
function tools and streaming with `stream_options={"include_usage": True}`.
Grok 4.7 Chat accepts text messages only. For tool continuation, retain the assistant's `tool_calls`
and return each result as a `role="tool"` message with the matching
`tool_call_id`.

Use Responses for `grok-4.5`, `grok-4.6`, or `grok-4.7`; Grok 4.6 does not
expose Anthropic Messages or Gemini contents. Grok 4.6 accepts function tools
and image input; add an `input_image` part with a public `image_url` alongside
`input_text` for image understanding. Grok 4.6 Responses also accepts hosted
`web_search` (billed per call on top of tokens), so Codex CLI works with it.
Do not send `input_file` or state fields such as `previous_response_id` for
Grok 4.6 or 4.7.

`grok-4.7` accepts text through Chat Completions, Responses, Anthropic
Messages, and Gemini `contents`. Reasoning controls, function tools, tool
history, structured output, image or file input, hosted tools, and cache
controls are not yet verified for `grok-4.7`; send plain text requests only.

For streaming Responses, set `stream=True`
and consume through `response.completed`, terminal `usage`, and `[DONE]`.

### Verify result

Responses require final output, one usage-bearing `response.completed`, and
`[DONE]`. Chat requires final assistant content, `finish_reason`, and terminal
`usage`.

### Stop boundaries

Correct a rejected shape once using the structured err

_meta.json

{
  "ownerId": "kn70me4rk7jqjt92evshjeb5z18768g7",
  "slug": "runapi-grok",
  "version": "0.3.0",
  "publishedAt": 1790770640569
}

references/compatibility-protocols.md

# Grok compatibility protocols

Load this reference only for an existing Anthropic Messages or Gemini contents client.

For Messages, use base URL `https://runapi.ai`, a RunAPI key, a supported exact
model ID, `max_tokens`, and messages. Verify final content, `stop_reason`, and
`usage`; streaming ends at `message_stop`.

For Gemini contents, set `RUNAPI_MODEL` to a supported exact model ID and use
`https://runapi.ai/v1beta/models/$RUNAPI_MODEL:generateContent`
or `streamGenerateContent` with `x-goog-api-key`. Verify candidates,
`finishReason`, and `usageMetadata`.

Apply one evidence-backed shape correction, at most one safe pre-response
transport retry, and no automatic model or protocol hopping.

skill-card.md

## Description:

Guides agents in calling Grok text models through RunAPI using supported API protocols.

This skill is ready for commercial/non-commercial use.

## Publisher:

[runapi-ai](https://clawhub.ai/user/runapi-ai)

### License/Terms of Use:

MIT-0

## Use Case:

Developers and agents use this skill to configure RunAPI access, select a supported Grok model and protocol, and verify text responses.

### Deployment Geography for Use:

Global

## Known Risks and Mitigations:

Risk: Prompts and other data sent through RunAPI may not meet an organization's data-handling requirements.

Mitigation: Check RunAPI account and data-handling requirements before sending sensitive content.

Risk: Misconfigured API credentials or endpoint can route requests incorrectly or expose a key.

Mitigation: Set the RunAPI key and base URL deliberately, and keep the key out of shared code and logs.

## Reference(s):

- [Grok on RunAPI documentation](https://runapi.ai/models/grok.md)
- [RunAPI Grok model page](https://runapi.ai/models/grok)
- [RunAPI xAI provider documentation](https://runapi.ai/providers/xai.md)
- [RunAPI model catalog](https://runapi.ai/models.md)
- [Compatibility protocols](references/compatibility-protocols.md)

## Skill Output:

**Output Type(s):** [Text, Code, Configuration instructions]

**Output Format:** [Text or Markdown with optional code examples]

**Output Parameters:** [1D]

**Other Properties Related to Output:** [Streaming responses and usage details where supported]

## Skill Version(s):

0.3.0 (source: ClawHub release evidence)

## Ethical Considerations:

Users should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.

Github ReposUpdated 2d agoRank 70

AionUi

Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!

MCPOPENCLAW

Github ReposUpdated 6mo agoRank 70

activepieces

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

OPENCLAW

Github ReposUpdated 6mo agoRank 70

cherry-studio

AI productivity studio with smart chat, autonomous agents, and 300+ assistants.