How long does the integration take?

Change one base URL in an OpenAI-compatible client, or install the Python or TypeScript SDK; the quickstart routes a first request in a few minutes.

Will this lock us into another vendor?

No. The router is Apache-2.0 open source, your provider keys stay yours, and the API is OpenAI-compatible, so leaving is a change of base URL.

What happens when a provider fails?

The router falls back to the next model your policy allows and records the fallback in the trace, so an outage costs a retry, not an incident.

deepseek-reason - Skill - OpenSmartRoute

Name: deepseek-reason
Author: ruvnet

Imported from ruvnet/ruflo (plugins/ruflo-deepseek-harness/skills/deepseek-reason/SKILL.md). Install upstream with npx skills add ruvnet/ruflo --skill deepseek-reason. Copyright stays with the author.

Wraps DeepSeek's reasoning model so ruflo callers can get an explicit chain-of-thought back with the final answer, without having to parse it out of the message content. Same subprocess-invocation shape as the sibling deepseek-chat skill.

When to use

Multi-step reasoning tasks: proofs, plans, root-cause analysis, hard bug triage.
You want to see the model's thinking (for audit, for training data, or to sanity-check its final answer).
You can tolerate the higher latency and token cost of a reasoner vs deepseek-chat.

Data handling

The prompt and any --system text are sent over the network to api.deepseek.com, a third party. Do not put secrets, credentials, personal data or proprietary code you are not allowed to share into them. The API key is read from DEEPSEEK_API_KEY in your shell only; never paste it into a prompt, a file or a command line.

Algorithm

Implementation: scripts/reason.mjs.

Read DEEPSEEK_API_KEY from env. Degrade gracefully when missing.
POST to /v1/chat/completions with { model: 'deepseek-reasoner', messages, max_tokens? }. Per DeepSeek's docs, temperature/top_p are ignored for reasoner models — this script does not forward them.
Extract choices[0].message.content AND choices[0].message.reasoning_content.
JSON output always includes reasoning; table mode omits it unless --show-reasoning is passed.
reasoningTokens (from usage.completion_tokens_details.reasoning_tokens) is surfaced separately so callers can attribute cost.

Example

node plugins/ruflo-deepseek-harness/scripts/reason.mjs \
  --prompt "Prove that sqrt(2) is irrational." \
  --format table --show-reasoning

Table output shows the reasoning block, then the answer. JSON mode returns:

{
  "status": "ok",
  "model": "deepseek-reasoner",
  "content": "sqrt(2) is irrational because …",
  "reasoning": "Assume for contradiction that sqrt(2) = p/q in lowest terms …",
  "finishReason": "stop",
  "usage": {
    "promptTokens": 14,
    "completionTokens": 812,
    "reasoningTokens": 640,
    "totalTokens": 826
  }
}

Install deepseek-reason and it becomes one more candidate the router can pick - when it fits.

A listing is a routing target with a manifest: what it does, which domains it covers, what it costs and who publishes it. Once installed it sits beside your own models and tools, is scored like any other candidate for each request, and shows up in the trace when it wins. Ratings come from workspaces that installed it, one per account.

{ "ocm": "1", "id": "ruvnet-ruflo-deepseek-reason", "kind": "skill", "name": "deepseek-reason", "description": "Reasoning completion against DeepSeek's `deepseek-reasoner` (R1), returning the chain of thought apart from the answer. Use when a task needs step-by-step reasoning from DeepSeek. Reads DEEPSEEK_API_KEY; returns status:degraded when unset or unreachable.", "publisher": "ruvnet", "version": "1.0.0", "capabilities": { "domains": [ "coding", "data_analysis" ], "tags": [ "skill-md", "skills-sh" ], "languages": [ "en" ] }, "quality_prior": 0.6, "examples": [ "Reasoning completion against DeepSeek's `deepseek-reasoner` (R1), returning the chain of thought apart from the answer. Use when a task needs step-by-step reasoning from DeepSeek. Reads DEEPSEEK_API_KEY; returns status:degraded when unset or unreachable." ], "primary": false, "metadata": { "source": { "provider": "skills.sh", "repository": "https://github.com/ruvnet/ruflo", "path": "plugins/ruflo-deepseek-harness/skills/deepseek-reason/SKILL.md", "ref": "HEAD", "url": "https://github.com/ruvnet/ruflo/blob/HEAD/plugins/ruflo-deepseek-harness/skills/deepseek-reason/SKILL.md", "key": "ruvnet/ruflo/plugins/ruflo-deepseek-harness/skills/deepseek-reason/SKILL.md" }, "allowed_tools": [ "Bash" ] }, "instructions": "Wraps DeepSeek's reasoning model so ruflo callers can get an explicit\nchain-of-thought back with the final answer, without having to parse it\nout of the message content. Same subprocess-invocation shape as the sibling\n`deepseek-chat` skill.\n\n## When to use\n\n- Multi-step reasoning tasks: proofs, plans, root-cause analysis, hard\n bug triage.\n- You want to *see* the model's thinking (for audit, for training data,\n or to sanity-check its final answer).\n- You can tolerate the higher latency and token cost of a reasoner vs\n `deepseek-chat`.\n\n## Data handling\n\nThe prompt and any `--system` text ar", "cost": { "context_tokens": 540 } }

deepseek-reason

About

When to use

Data handling

Algorithm

Example

Install deepseek-reason and it becomes one more candidate the router can pick - when it fits.

What it costs to adopt - in engineering time.

One base URL

No vendor lock-in

Failover built in

Use it

Manifest

Reviews