DeepSeek R1 0528Chat
DeepSeek's open reasoning flagship with conformant GMI tool use and a lower-cost DeepInfra text fallback.
1.9sp50100%up2 rails164K ctx$0.006typical$0.72 → $2.75 /MTok
Playground
Providers
| Provider | Role | Context | Price · in / out | p50 | p95 | Uptime |
|---|---|---|---|---|---|---|
| ddeepinfraNo trainingNo training on your data | Primary | 1M | $0.24 / $0.33/MToksame price, any rail | 700ms | 700ms | 100% |
| ddigitaloceanNo trainingNo training on your data. Zero-retention available | Fallback | 1M | 1.4s | 4.2s |
Performance
Collecting — charts appear after two days.
Pricing
- Typical
- $0.002/req
- Input
- $0.24/M tok
- Cached input
- $0.16/M tok
- Output
- $0.33/M tok
API
POST/api/v1/chat/completionsOpenAI-compatible
deepseek-v4-flash
curl https://www.ninjachat.ai/api/v1/chat/completions \
-H "Authorization: Bearer $NINJACHAT_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "deepseek-v4-flash",
"messages": [{ "role": "user", "content": "Hello!" }],
"stream": true
}'messagestemperaturemax_completion_tokenstop_pstopfrequency_penaltypresence_penaltyseedstreamuserroutingtoolstool_choice
FAQ
What is DeepSeek V4 Flash?
DeepSeek's current V4 Flash release with million-token context and two fully probed neutral-host rails.
How much does DeepSeek V4 Flash cost?
DeepSeek V4 Flash costs $0.24/M input tokens and $0.33/M output tokens.
What inputs and outputs does DeepSeek V4 Flash support?
DeepSeek V4 Flash accepts text and returns text.
How do I call DeepSeek V4 Flash?
POST /api/v1/chat/completions with `"model": "deepseek-v4-flash"`.
What other DeepSeek models are on NinjaChat?
DeepSeek R1 0528, DeepSeek V3, DeepSeek V3.2, DeepSeek V4 Flash 0731, DeepSeek V4 Pro, DeepSeek V4 Pro 0813.