Home › VastLLM Catalog › DeepSeek V4 Pro 0813
DeepSeek V4 Pro 0813
by DeepSeek · Language Models
Context 1M tokensReasoning / thinkingFunction calling
by DeepSeek · Language Models
DeepSeek V4 Pro official GA release (0813). Supports thinking mode; up to 1M context tokens.
$0.5097 in · $1.529 out · $0.017 cached / 1M
| Usage | Rate (USD) | Unit |
|---|---|---|
| Input tokens | $0.5097 | per 1M tokens |
| Cached input (cache hit) | $0.017 | per 1M tokens |
| Output tokens | $1.529 | per 1M tokens |
Official model pricing · currency: USD · pre-deduction settled by actual usage
OpenAI-compatible · base URL https://api.tunerouter.com/v1/
curl https://api.tunerouter.com/v1/chat/completions \
-H "Authorization: Bearer $TUNEROUTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model": "deepseek-v4-pro-0813", "messages": [{"role": "user", "content": "Hello!"}]}'Model ID: deepseek-v4-pro-0813 · works with OpenAI SDKs — just point base_url at api.tunerouter.com