What makes deepseek notable?

1.2K downloads. Trust evidence available

How should deepseek 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

deepseek

Call the DeepSeek API (deepseek-flash, deepseek-v4-pro, deepseek-v4-flash, and deepseek-v4-flash-vision-exp) through RunAPI using OpenAI-compatible Chat Completions and Responses. Use deepseek-flash for the current V4.1 Flash model; the v4 names remain compatibility aliases.

OpenClaw

View on ClawHub Homepage

Rank

Safety

Downloads

1.2k

Updated

Oct 11, 2026

Version

0.1.6

Source

CLAWHUB

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 1.2K 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: 1.2K downloadsadoption · observed Oct 11, 2026
Latest release: 0.1.6release · observed Sep 16, 2026
Handshake status: UNKNOWNsecurity

Install and run

Setup complexity: low.

clawhub skill install s1771k6pjxksnjws51x2htfjvd876syh:runapi-deepseek

Install using `clawhub skill install s1771k6pjxksnjws51x2htfjvd876syh:runapi-deepseek` 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-deepseek before using production credentials.

Contract: missing

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

Documentation

CLAWHUB

56,898 characters of source documentation, loaded on request.

Extracted files

4 files captured from the source.

SKILL.md

---
name: deepseek
description: Call the DeepSeek API (deepseek-flash, deepseek-v4-pro, deepseek-v4-flash, and deepseek-v4-flash-vision-exp) through RunAPI using OpenAI-compatible Chat Completions and Responses. Use deepseek-flash for the current V4.1 Flash model; the v4 names remain compatibility aliases.
documentation: https://runapi.ai/models/deepseek.md
provider_page: https://runapi.ai/providers/deepseek.md
catalog: https://runapi.ai/models.md
metadata:
  openclaw:
    homepage: https://runapi.ai/models/deepseek
    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 DeepSeek clients.}
    - {name: OPENAI_BASE_URL, required: true, description: Set to https://runapi.ai/v1 for DeepSeek on RunAPI.}
---

# DeepSeek 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.chat.completions.create(
    model="deepseek-v4-pro",
    messages=[{"role": "user", "content": "Explain this decision."}],
)
print(response.choices[0].message.content)
print(response.usage)
```

For long output, set `stream=True` and
`stream_options={"include_usage": True}`; consume through `[DONE]`.
`deepseek-v4-flash` additionally supports one custom function on Responses;
keep automatic tool selection and one serial call/result lifecycle.

For image input, use `deepseek-v4-flash-vision-exp` with a Chat Completions
message content array containing a text part and an `image_url` part. The image
URL must be publicly reachable and use JPEG, PNG, GIF, or WebP.

### Verify result

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

### Stop boundaries

Correct a rejected shape once using the structured error. Retry transport once
only before any response or Usage and when replay is safe. Record a terminal
error and stop without changing model or protocol. Add tools, reasoning,
storage, cache controls, documents, or multimodal input only when the current
RunAPI contract verifies the exact model/protocol shape.

## Compatibility protocols

Load [compatibility protocols](references/compatibility-protocols.md) only when an existing client requires Anthropic Messages or Gemini contents.

## Supported models

| Model ID | Use when |
|---|---|
| `deepseek-flash` | Current V4.1 Flash model for fast text and reasoning |
| `deepseek-v4-flash-vision-exp` | Image input and vision tasks |
| `deepseek-v4-pro` | Higher-quality verified text workloads |
| `deepseek-v4-flash` | Compatibility alias for Flash |

_meta.json

{
  "ownerId": "kn70me4rk7jqjt92evshjeb5z18768g7",
  "slug": "runapi-deepseek",
  "version": "0.1.6",
  "publishedAt": 1789553445856
}

references/compatibility-protocols.md

# DeepSeek 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 text messages. `deepseek-v4-flash-vision-exp` is the
image-input variant; for vision requests use its Chat Completions shape with an
`image_url` content part. 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:

Call the DeepSeek API (deepseek-flash, deepseek-v4-pro, deepseek-v4-flash, and deepseek-v4-flash-vision-exp) through RunAPI using OpenAI-compatible Chat Completions and Responses.

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 and call DeepSeek models through RunAPI with OpenAI-compatible Chat Completions and Responses. It also provides compatibility guidance for existing Anthropic Messages or Gemini contents clients.

### Deployment Geography for Use:

Global

## Known Risks and Mitigations:

Risk: RunAPI API keys are required and could be exposed through insecure configuration or logging.

Mitigation: Store keys in environment variables or a secret manager, avoid hardcoding them in prompts or files, and prevent key values from appearing in logs.

Risk: Prompts, data, and image URLs are routed to a third-party service for processing.

Mitigation: Use the skill only when RunAPI processing is acceptable for the data classification, and avoid private prompts, sensitive data, or sensitive image URLs unless approved.

Risk: Unsupported model or protocol assumptions can produce rejected requests or misleading integration guidance.

Mitigation: Use exact supported model IDs, verify final content and usage fields, apply at most one evidence-backed shape correction, and avoid automatic model or protocol hopping.

## Reference(s):

- [DeepSeek model documentation](https://runapi.ai/models/deepseek.md)
- [DeepSeek provider documentation](https://runapi.ai/providers/deepseek.md)
- [RunAPI model catalog](https://runapi.ai/models.md)
- [DeepSeek on RunAPI homepage](https://runapi.ai/models/deepseek)
- [DeepSeek compatibility protocols](references/compatibility-protocols.md)

## Skill Output:

**Output Type(s):** [Guidance, Markdown, Code, Shell commands, Configuration]

**Output Format:** [Markdown with inline code blocks and environment variable settings]

**Output Parameters:** [1D]

**Other Properties Related to Output:** [Includes model selection, request validation, streaming, retry, and protocol compatibility guidance.]

## Skill Version(s):

0.1.6 (source: server 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 1d 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.