DeepSeek V4 Pro (0813)
ReasoningDeepSeek
Large-scale DeepSeek MoE model for hard reasoning.
- Input
- $0.105
- per 1M tokens
- Output
- $0.24
- per 1M tokens
- Context window
- 1M
- tokens
- Max output
- 384K
- tokens
Pricing
Prices are in USD per 1M tokens. Cached input is billed at the cache read price.
- Input
- $0.105/ 1M
- Output
- $0.24/ 1M
- Cache read
- $0.003/ 1M
Use it from code
The samples read your key from the ORYNX_API_KEY environment variable.
OpenAI Chat
curl https://api.orynx.dev/v1/chat/completions \
-H "Authorization: Bearer $ORYNX_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "deepseek-v4-pro-0813",
"messages": [{"role": "user", "content": "Explain what an API gateway does in one sentence."}]
}'Use it in your tools
Minimal configuration for popular coding agents. Replace sk-orynx-... with your key.
Cursor
Full guideCursor Settings → Models
OpenAI API Key: sk-orynx-...
Override OpenAI Base URL: https://api.orynx.dev/v1
Custom model name: deepseek-v4-pro-0813OpenCode
Full guideopencode.json
{
"$schema": "https://opencode.ai/config.json",
"provider": {
"orynx": {
"npm": "@ai-sdk/openai-compatible",
"name": "ORYNX",
"options": {
"baseURL": "https://api.orynx.dev/v1",
"apiKey": "{env:ORYNX_API_KEY}"
},
"models": {
"deepseek-v4-pro-0813": {
"name": "DeepSeek V4 Pro (0813)",
"limit": {
"context": 1048576,
"output": 384000
}
}
}
}
}
}More from DeepSeek
deepseek-v4.1-flashSparse MoE model from DeepSeek; fast and inexpensive.
- Input
- $0.40/ 1M
- Output
- $1.60/ 1M
OpenAI Chat1M ctx
deepseek-v4-flash-0731Efficient DeepSeek MoE with 13B active parameters.
- Input
- $0.024/ 1M
- Output
- $0.03/ 1M
OpenAI Chat1M ctx
DeepSeek V4 Flash Vision (exp)Dynamic pricing
deepseek-v4-flash-vision-expExperimental vision-enabled DeepSeek V4 Flash. Peak-hour pricing applies.
- Input
- $0.045/ 1M
- Output
- $0.18/ 1M
OpenAI Chat1M ctx
