Developer FAQ
Short answers with primary sources. For HTTP errors and retries see the API error codes guide; for Claude Code with DeepSeek see the Claude Code setup guide.
DeepSeek-V4.1-Flash is a multimodal Mixture-of-Experts model with 552B backbone parameters and a context of up to one million tokens.
Source: V4.1-Flash-1017 model card
The model card describes a Causal Encoder-Decoder that activates 8B parameters per token during prefill and 16B during decode, Engram conditional memory of 196B parameters, 384 routed experts with 6 activated, and a global KV cache of 890 bytes per token. On the API it is called with model deepseek-flash. Weights were refreshed as DeepSeek-V4.1-Flash-1017 on 17 October 2026 with unchanged API naming and token prices.
V4.1-Flash has a 552B backbone (8B active in prefill, 16B in decode) while V4-Pro has 1.6T parameters with 49B activated; both API models list a 1M context.
Source: Models & Pricing
Search and Fetch each cost $0.75 per 1,000 successful requests. Billing is per successful request, not by tokens or by how many results Search returns.
Source: Search & Fetch guide
At peak, deepseek-flash costs $0.30 per 1M cache-miss input tokens, $0.006 per 1M cache-hit input tokens, and $1.20 per 1M output tokens; off-peak is half of each rate.
Source: Models & Pricing
This site does not publish Claude or GPT prices, because those figures were not checked against the vendors’ current price pages.
Source: DeepSeek pricing (DeepSeek only)
For OpenAI-compatible clients use base URL https://api.deepseek.com. For Anthropic-compatible clients use https://api.deepseek.com/anthropic.
Source: Models & Pricing
The current model names are deepseek-flash for DeepSeek-V4.1-Flash and deepseek-v4-pro for DeepSeek-V4-Pro-0813.
Source: Models & Pricing
Point the OpenAI SDK at base URL https://api.deepseek.com and set the model to deepseek-flash or deepseek-v4-pro.
Source: Thinking Mode
Both deepseek-flash and deepseek-v4-pro list a 1M token context length and a maximum output of 384K tokens.
Source: Models & Pricing
Off-peak rates are half of peak rates, and peak hours are 01:00–04:00 and 06:00–10:00 UTC, Monday through Friday, excluding Chinese public holidays.
Source: Models & Pricing
DeepSeek does not publish a ranking for Cline, Aider, or Cursor; the current general API model is deepseek-flash.
Source: V4.1-Flash model card
V4.1-Flash publishes weights and an inference folder for local runs, but that README introduction does not state a minimum GPU count.
Source: V4.1-Flash model card
They are open-source libraries from DeepSeek: FlashMLA for MLA attention kernels, DeepEP for expert-parallel communication, and DeepGEMM for GPU GEMM kernels.
Source: open-infra-index
DeepSeek-R1 is the January 2025 reasoning model; the current API pricing table serves V4.1-Flash and V4-Pro, not a separate R1 model name.
Source: DeepSeek-R1 README