DeepSeek V4 Specs and Pricing Leaked: Supports 1M Context
dotey · x · 2026-08-12
DeepSeek's API documentation page has revealed two suspected V4 series models: deepseek-v4-flash and deepseek-v4-pro.
- Core Specs: Both models support a massive 1M context length and up to 384K output tokens. They feature JSON Output, Tool Calls, and compatibility with both OpenAI and Anthropic API formats.
- Thinking Mode: The Pro version supports switching between thinking and non-thinking modes by default, while Flash also supports it.
- Pricing & Limits: Flash costs 1 RMB/M tokens for cache-miss input, and Pro costs 3 RMB. The docs note an upcoming significant price increase for the API service. Concurrency limits are set at 2500 for Flash and 500 for Pro.
Related event: DeepSeek V4 Specs and Pricing Leak Spark Debate(5 posts)→
More from Models
- GLM 5.5 rumored to drop soon, coding ability expected to match frontier models — bindureddy · 2026-10-16
- Five rounds of adversarial prompting make Opus 5.5 and Argon converge on identical output — LanceCharger · 2026-10-16
- DIY benchmark ranks 18 models on subjective judgments, GLM-5.3 tops consensus match — arkuto · 2026-10-16
- Bindu Reddy: Google's Argon excels at complex doc writing at half the cost of Opus — bindureddy · 2026-10-16
- MAI-2 is 2x bigger than V4-Pro while V4.1F is 3x smaller: Microsoft's scaling ladder questioned — teortaxesTex · 2026-10-16
- Step 5 Preview hits DeepInfra day-zero: 600B MoE, 1M context, $1/M input tokens — StepFun_ai · 2026-10-16