deepseek-v4-pro
DeepSeek V4 Pro is a 1.6T-parameter mixture-of-experts model for advanced reasoning, coding, and long-horizon agent work, with a 1M-token context window and tool calling.
Pricing: Input 229.2624 credits / 1M tokens (≈ $1.15), Output 458.5248 credits / 1M tokens (≈ $2.29).
Prices updated
How can I help you today?
This demo page does not include the full memory features of the client. For the complete experience, please use the client or the CLI.
More AI models from DeepSeek
DeepSeek V4 Pro API
Call DeepSeek V4 Pro on ModelFold with model id deepseek-v4-pro. It is a text model for hard reasoning, coding, and multi-step agent workflows.
What this model is for
Large mixture-of-experts
DeepSeek V4 Pro has about 1.6T total parameters and about 49B active parameters. It uses the same hybrid-attention design as DeepSeek V4 Flash for long context.
1M-token context and tools
The context window is 1,048,576 tokens, and the longest completion is 384,000 tokens. The model accepts tool calls, structured output, and reasoning. Input and output are text.
Reasoning effort
Reasoning is on by default at high effort. You can set reasoning effort to high, xhigh (maximum), or none.
Pricing
Billing follows token usage and the markup configured in the admin console. At the current markup, input is 229.2624 credits per 1M tokens (about $1.146) and output is 458.5248 credits per 1M tokens (about $2.293). Cached input is cheaper. Failed calls are not charged.
FAQ
What model id do I send?⌄
Send model deepseek-v4-pro to POST https://modelfold.ai/v1/chat/completions with Authorization: Bearer YOUR_API_KEY and an OpenAI-style messages array. stream: true returns server-sent events.
Does it support tools?⌄
Yes. Pass a tools array and tool_choice the same way as the OpenAI Chat Completions API. The model can also return structured output.
| Input | 229.2624 credits 1M tokens≈ $1.15 |
| Output | 458.5248 credits 1M tokens≈ $2.29 |
Billed per token: input and output are priced separately, and thinking tokens count as output. The Playground charges exactly the same way.
Read API docs →AI Agents · Claude Code / Cursor / Trae →curl https://modelfold.ai/v1/chat/completions \
-H "Authorization: Bearer $MODELFOLD_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"deepseek-v4-pro","messages":[{"role":"user","content":"Hello"}]}'