DeepSeek / deepseek/deepseek-v4-pro
DeepSeek V4 Pro - access through LLMTR
DeepSeek-V4-Pro targets teams that prioritize top-tier reasoning, agentic workflows, and coding quality over minimum unit cost, while keeping the same 1M context class and similar feature surface as Flash. DeepSeek has announced peak-hour pricing for this model: every token item costs double between 01:00-04:00 and 06:00-10:00 UTC.
Technical specifications
| Canonical ID | deepseek/deepseek-v4-pro |
|---|---|
| Provider | DeepSeek |
| Context window | 1,000,000 tokens |
| Operations | CHAT_COMPLETIONS |
| Modalities | text |
Pricing
An 8% platform margin applies to credit top-ups; model usage prices are not separately marked up.
| Operation | Metric | Unit | Price |
|---|---|---|---|
| CHAT_COMPLETIONS | INPUT_TEXT | PER_1M_TOKENS | $0.435000 |
| CHAT_COMPLETIONS | CACHE_READ | PER_1M_TOKENS | $0.003625 |
| CHAT_COMPLETIONS | OUTPUT_TEXT | PER_1M_TOKENS | $0.870000 |
Example usage
With existing OpenAI SDK flows, change only the base URL and model identifier.
curl https://llmtr.com/v1/chat/completions \
-H "Authorization: Bearer llmtr-your_key" \
-H "Content-Type: application/json" \
-d '{"model":"deepseek/deepseek-v4-pro","messages":[{"role":"user","content":"Hello"}]}'Related models
- DeepSeek V4 Flash deepseek/deepseek-v4-flash
- DeepSeek Chat deepseek/deepseek-chat
- DeepSeek R1 deepseek/deepseek-reasoner
- Gemma 4 llmtr/gemma-4
- Qwen 3.6 35B-A3B llmtr/qwen3-6-35b
- MedGemma 4B llmtr/medgemma-4b
- Trendyol 7B llmtr/trendyol-7b
- Magibu 11B v8 llmtr/magibu-11b-v8