DeepSeek Chat API - RouterBase

Overview

DeepSeek chat models on RouterBase, served through the standard OpenAI-compatible chat completions endpoint with streaming and tool calling.


Provider	DeepSeek
Families	`deepseek-v4`, `deepseek-v3`, `deepseek-r1`, `deepseek-prover`
Modality	Chat
Input	Text
Output	Text

Models

deepseek/deepseek-v4-pro
deepseek/deepseek-v4-pro-0813
deepseek/deepseek-v4-flash
deepseek/deepseek-r1-0528
deepseek/deepseek-v3-0324
deepseek/deepseek-v3.2-exp
deepseek/deepseek-v3.1-terminus
deepseek/deepseek-v3.1
deepseek/deepseek-v3.2
deepseek/deepseek-r1-turbo
deepseek/deepseek-v3-turbo
deepseek/deepseek-prover-v2-671b
deepseek/deepseek-r1-distill-llama-70b
deepseek/deepseek-r1-distill-llama-8b

Pricing is deliberately not reproduced here. Rates are set per model in the RouterBase catalogue and can be overridden per account, so any figure copied into this page is a snapshot that goes stale the next time a rate changes. Fetch the current rate for any model from the Models API:

GET /api/models/{model}/pricing

URL-encode the slash in the model id — e.g. deepseek%2Fdeepseek-v4-pro.

Endpoint

POST https://routerbase.com/v1/chat/completions

Drop-in compatible with the OpenAI Chat Completions API — point your OpenAI client at https://routerbase.com/v1 with your RouterBase key. See the Chat Completions reference for every supported parameter.

Quickstart

curl https://routerbase.com/v1/chat/completions \
  -H "Authorization: Bearer $ROUTERBASE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek/deepseek-v4-pro",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'