DeepSeek V4 Flash 0731
DeepSeek's V4 Flash (July 31 build): fast, low-cost reasoning with a 1M-token context.
- Modalities
- IntextOuttext
- Input / output
- $0.22 / $0.66USD per 1M tokens
- Context
- 1M
- Providers
- 14 live
Playground
Preparing playground
Performance
Response latency estimates
Time to first token
Generation speed · tok/s
Request success
Text-model timing and speed, plus API request success. Daily latency percentiles are estimates. Your request logs
Generation speed by provider · tok/s
P50 latency estimates by provider
Time to first token by provider
Request success by provider
API
POST/api/v1/chat/completionsOpenAI-compatible
deepseek-v4-flash-0731
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-0731",
"messages": [{ "role": "user", "content": "Hello!" }],
"stream": true
}'messagestemperaturemax_completion_tokenstop_pstopfrequency_penaltypresence_penaltyseedstreamuserroutingtoolstool_choiceresponse_formatreasoningreasoning_effort
Pricing
- Input
- $0.22/M tokens
- Cached input
- $0.007/M tokens
- Output
- $0.66/M tokens
Published USD rates. Actual cost depends on input, output, cache usage and request options.
