DeepSeek V4 Pro

DeepSeek V4 Pro on OptiQ Cloud, billed per token.

cloud

DeepSeek V4 Pro is DeepSeek's larger model, for the hardest coding tasks, with a context window of about 1 million tokens. It is served by OptiQ Cloud and billed per token. All OptiQ Cloud models are served at full precision, and your requests are never used for training.

Input$2.20 / M

Cached input$0.08 / M

Output$6.60 / M

Context1M tokens

Typical speed—

Next to the other OptiQ Cloud models

Scores are from each maker's model card, for benchmarks that more than one card reports; OptiQ did not run them. Prices are what OptiQ Cloud charges.

Output price, $ per million tokens

Input price, $ per million tokens

Use it

Connect this Mac

pip install mlx-optiq
optiq cloud login

Claude Code

optiq run claude --cloud deepseek-v4-pro

Codex

optiq run codex --cloud deepseek-v4-pro

OpenCode

optiq run opencode --cloud deepseek-v4-pro

Mistral Vibe

optiq run vibe --cloud deepseek-v4-pro

Hermes Agent

optiq run hermes --cloud deepseek-v4-pro

OpenClaw

optiq run openclaw --cloud deepseek-v4-pro

No local model is loaded. optiq run starts optiq serve --cloud-only, sets the agent up for this session only, and stops the server when the agent exits.

OptiQ Code

Boost: this model leads the task and your local model is its helper.

/boost deepseek-v4-pro

OptiQ Lab, and any app that talks to optiq serve

Pick optiq-cloud/deepseek-v4-pro in the model list. With no local model:

optiq serve --cloud-only

The API, from anywhere

Create a key on the dashboard.

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

from openai import OpenAI

client = OpenAI(
    base_url="https://cloud.mlx-optiq.com/api/v1",
    api_key="<your key>")
reply = client.chat.completions.create(
    model="deepseek-v4-pro",
    messages=[{"role": "user", "content": "Hello"}])
print(reply.choices[0].message.content)

Details

Input	$2.20 per million tokens
Cached input	$0.08 per million tokens
Output, including reasoning	$6.60 per million tokens
Context window	1M tokens
Longest reply	393,216 tokens
Model id	`deepseek-v4-pro` on the API, `optiq-cloud/deepseek-v4-pro` in optiq serve