NewHow we catch a seller listing the wrong model, and refund you if one does.
UberLLM
deepseek logo

How do I use DeepSeek V4 Pro in OpenCode?

deepseek/deepseek-v4-pro

OpenCode reaches DeepSeek V4 Pro through the OpenAI-compatible chat address of UberLLM. In ~/.config/opencode/opencode.json, add a provider named uberllm that uses the @ai-sdk/openai-compatible package with baseURL set to https://api.uberllm.dev/v1, list deepseek/deepseek-v4-pro under its models, put your UberLLM key in the UBERLLM_API_KEY environment variable, then pick uberllm/deepseek/deepseek-v4-pro with /models. The limit numbers are the context size and the largest reply of DeepSeek V4 Pro; OpenCode uses them to know when to compact a long session.

json
{
  "$schema": "https://opencode.ai/config.json",
  "provider": {
    "uberllm": {
      "npm": "@ai-sdk/openai-compatible",
      "name": "UberLLM",
      "options": {
        "baseURL": "https://api.uberllm.dev/v1",
        "apiKey": "{env:UBERLLM_API_KEY}"
      },
      "models": {
        "deepseek/deepseek-v4-pro": {
          "name": "DeepSeek V4 Pro",
          "limit": {
            "context": 1000000,
            "output": 128000
          }
        }
      }
    }
  },
  "model": "uberllm/deepseek/deepseek-v4-pro"
}

OpenCode calls: OpenAI chat completions https://api.uberllm.dev/v1/chat/completions · Full OpenCode guide

Replace ull_your_key with your UberLLM API key. One key works in every tool and for every model.

By API, DeepSeek V4 Pro answers on three addresses with the same UberLLM key and the model id deepseek/deepseek-v4-pro: OpenAI chat completions at https://api.uberllm.dev/v1/chat/completions, the OpenAI Responses API at https://api.uberllm.dev/v1/responses and the Anthropic Messages API at https://api.uberllm.dev/v1/messages.

How much does the DeepSeek V4 Pro API cost?

On November 19, 2026, DeepSeek V4 Pro costs $0.0376 per million input tokens and $0.0627 per million output tokens through UberLLM, 97.2% below its list price of $1.32 and $3.96. 169 sellers on the market can serve it. In the 7 days before, half of its 5,180 streamed requests got their first token within 8.2 seconds, with a typical prompt of 45,639 tokens. It reads up to 1,000,000 tokens of context. UberLLM adds no fee to these prices, and a request that fails is not billed.

Prices as of 09:00 UTC.

DeepSeek V4 Pro in other tools

Other models in OpenCode