DeepSeek V4.1 Flash API
DeepSeek V4.1 Flash - multimodal MoE with 552B params, 1M context, CED architecture and controllable reasoning (1-100). Optimized for agentic workloads.
Provider: DeepSeek | Model ID: deepseek-v4-1-flash | Context Window: 1.0M tokens
Token Pricing
₹30/1M input · ₹100/1M output. Pay-as-you-go micro-metered token billing. UPI and cards accepted with zero minimum commitment.
| Token Type | Price (INR) |
|---|---|
| Input Tokens | ₹30/1M tokens |
| Output Tokens | ₹100/1M tokens |
| Prompt Caching Input | ₹10/1M tokens |
OpenAI-Compatible Integration
Directly drop into existing OpenAI SDK code by updating the base URL to https://api.luminoai.co.in/v1.
curl https://api.luminoai.co.in/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $LUMINO_API_KEY" \
-d '{
"model": "deepseek-v4-1-flash",
"messages": [
{"role": "system", "content": "You are a helpful assistant."},
{"role": "user", "content": "Explain KV cache in 2 sentences."}
]
}'Model Specifications
| Model Identifier | deepseek-v4-1-flash |
|---|---|
| Provider | DeepSeek |
| Category | agentic |
| Context Window | 1.0M tokens |
| API Protocol | OpenAI-compatible REST API (JSON) |
| Endpoint | https://api.luminoai.co.in/v1/chat/completions |
Explore all models in catalog | API Documentation | Test DeepSeek V4.1 Flash in Playground