Provider guide

DeepSeek through one OpenAI-compatible gateway

Call DeepSeek’s low-cost models with your OpenAI SDK through Routeplane — with fallback, in-data-plane guardrails, residency routing, and cost attribution.

DeepSeek serves an OpenAI-compatible API. Routeplane’s adapter handles the small differences — notably DeepSeek’s flat cache-hit token accounting — and lifts them into the canonical usage block so your cost tracking is correct.

DeepSeek’s pricing makes it a strong choice as a cost-first primary; the gateway falls back to a broader provider when you need one.

Drop in your OpenAI client

Point your existing OpenAI SDK at the gateway and add two headers — your virtual key and the provider. Nothing else about your code changes.

bashcurl

curl https://api.routeplane.ai/v1/chat/completions \
  -H "content-type: application/json" \
  -H "x-routeplane-api-key: rp_your_gateway_key" \
  -H "x-routeplane-provider: deepseek" \
  -d '{"model":"deepseek-chat","messages":[{"role":"user","content":"Hello!"}]}'

pythonopenai SDK

import openai

client = openai.OpenAI(
    api_key="rp_your_gateway_key",
    base_url="https://api.routeplane.ai/v1",
    default_headers={
        "x-routeplane-api-key": "rp_your_gateway_key",
        "x-routeplane-provider": "deepseek",   # route to DeepSeek
    },
)

resp = client.chat.completions.create(
    model="deepseek-chat",
    messages=[{"role": "user", "content": "Hello!"}],
)
print(resp.choices[0].message.content)

typescriptopenai SDK

import OpenAI from 'openai';

const client = new OpenAI({
  apiKey: 'rp_your_gateway_key',
  baseURL: 'https://api.routeplane.ai/v1',
  defaultHeaders: {
    'x-routeplane-api-key': 'rp_your_gateway_key',
    'x-routeplane-provider': 'deepseek', // route to DeepSeek
  },
});

const completion = await client.chat.completions.create({
  model: 'deepseek-chat',
  messages: [{ role: 'user', content: 'Hello!' }],
});
console.log(completion.choices[0]?.message.content);

Or use the Routeplane SDK

The Routeplane SDKs subclass the official OpenAI clients, wire up the x-routeplane-* headers for you, and add typed access to routing metadata and the non-OpenAI surfaces.

bashinstall

pip install routeplane

pythonrouteplane SDK

from routeplane import Routeplane

client = Routeplane(
    api_key="rp_your_gateway_key",
    provider="deepseek",   # route to DeepSeek
)

resp = client.chat.completions.create(
    model="deepseek-chat",
    messages=[{"role": "user", "content": "Hello!"}],
)
print(resp.choices[0].message.content)

bashinstall

npm i @routeplane/sdk

typescript@routeplane/sdk

import { Routeplane } from '@routeplane/sdk';

const client = new Routeplane({
  apiKey: process.env.ROUTEPLANE_API_KEY!, // rp_...
  provider: 'deepseek',                 // route to DeepSeek
});

const completion = await client.chat.completions.create({
  model: 'deepseek-chat',
  messages: [{ role: 'user', content: 'Hello!' }],
});
console.log(completion.choices[0]?.message.content);

Add a fallback chain

Try DeepSeek first for cost; fall back to OpenAI. Make the provider header a comma-separated list and the gateway walks it in order, skipping any provider whose circuit is open.

bashcurl

curl https://api.routeplane.ai/v1/chat/completions \
  -H "content-type: application/json" \
  -H "x-routeplane-api-key: rp_your_gateway_key" \
  -H "x-routeplane-provider: deepseek,openai" \
  -d '{"model":"deepseek-chat","messages":[{"role":"user","content":"Hello!"}]}'

DeepSeek on the gateway

The adapter supports chat completions and native streaming. Embeddings requests return a clean 422 — route them to a provider that offers them.

Cache-hit tokens preserved

DeepSeek reports cache hits as a flat prompt_cache_hit_tokens field; the adapter lifts that into canonical cached-token usage so your accounting reflects the discount.

Cost-first routing

Pair DeepSeek with x-routeplane-strategy: cost to order eligible providers cheapest-first, keeping DeepSeek at the head where it wins on price.

DeepSeek model pricing

List prices for the DeepSeek models you can call through the gateway — click any model for its per-token cost page.

deepseek-chat deepseek-reasoner

Sovereign routing

Sovereign routing works with DeepSeek the same way it works everywhere: add x-routeplane-residency to a request, and when the gateway classifies regulated personal data in it, only providers resident in the requested region stay eligible — a hard constraint that overrides the provider header. Declare where DeepSeek runs by setting DEEPSEEK_REGION.

Keep reading

Quickstart — send your first request in a few minutes.
Providers & routing strategy — how eligibility, fallback, and strategies work.
Python SDK and TypeScript SDK — the full typed clients.
All providers — every model provider behind the gateway.

Frequently asked questions

Is Routeplane a drop-in replacement for calling DeepSeek directly?

Yes. The gateway is OpenAI-compatible, so switching is a base-URL change — point your existing OpenAI SDK at https://api.routeplane.ai/v1 and set the x-routeplane-provider header to deepseek. You keep your code and gain automatic fallback, in-data-plane PII guardrails, sovereign routing, and per-team cost attribution.

Which DeepSeek models can I use through Routeplane?

Any DeepSeek model the provider serves. See the list prices linked above for the ones we publish.

Can I enforce data residency on DeepSeek requests?

Yes. Add the x-routeplane-residency header (for example IN) and, when a request carries regulated personal data, the gateway restricts routing to providers eligible in that region — overriding the provider header if it has to. The DeepSeek adapter reads DEEPSEEK_REGION to declare where it is resident.

Route your first request this week.

Point your existing OpenAI-compatible client at Routeplane, set one header, and get fallback, guardrails, and sovereign routing across every provider.

Request access → Read the quickstart