Documentation Index Fetch the complete documentation index at: https://docs.oxen.ai/llms.txt
Use this file to discover all available pages before exploring further.
Try DeepSeek V4 Flash in the Workbench Run this model interactively, tune parameters, and compare outputs.
Model ID: deepseek-v4-flashDeepSeek V4 Flash is the efficiency variant of the V4 family. With 284B total parameters and 13B active per token, it targets fast, cheap inference while keeping the family’s strong reasoning and tool-use behaviour. Pairs naturally with V4 Pro: route the hard prompts to Pro, everyday traffic to Flash.
Metric Value Parameter Count 284 billion (13 billion active) Mixture of Experts Yes Active Parameter Count 13 billion Context Length 1,048,576 tokens Multilingual Yes Tool Use Yes Structured Outputs Yes
Example request Use the Workbench as a request builder: configure parameters for this model in the UI, then open the API tab to copy the exact cURL or Python call. Minimal
Basic parameters
All parameters
curl -X POST https://hub.oxen.ai/api/ai/chat/completions \ -H "Content-Type: application/json" \ -H "Authorization: Bearer $OXEN_API_KEY " \ -d '{ "model": "deepseek-v4-flash", "messages": [ { "role": "user", "content": "Hello, what can you do?" } ] }'
curl -X POST https://hub.oxen.ai/api/ai/chat/completions \ -H "Content-Type: application/json" \ -H "Authorization: Bearer $OXEN_API_KEY " \ -d '{ "model": "deepseek-v4-flash", "messages": [ { "role": "user", "content": "Hello, what can you do?" } ], "temperature": 0.7, "max_tokens": 1024, "stream": false }'
curl -X POST https://hub.oxen.ai/api/ai/chat/completions \ -H "Content-Type: application/json" \ -H "Authorization: Bearer $OXEN_API_KEY " \ -d '{ "model": "deepseek-v4-flash", "messages": [ { "role": "user", "content": "Hello, what can you do?" } ], "temperature": 0.7, "max_tokens": 1024, "stream": false, "top_p": 1.0 }'
Fetch model details The models endpoint returns the full model object, including its json_request_schema.
curl -H "Authorization: Bearer $OXEN_API_KEY " https://hub.oxen.ai/api/ai/models/deepseek-v4-flash
Request parameters This model follows the standard OpenAI chat completions request body. See the chat completions reference for the full parameter list. 
