DeepSeek: DeepSeek V4.1 Flash

DeepSeek

DeepSeek: DeepSeek V4.1 Flash by DeepSeek costs $0.05 per 1M input tokens and $0.50 per 1M output tokens, with a 1M-token context window.

Pricing

Input (per 1M tokens)

$0.05

Output (per 1M tokens)

$0.50

Cached input (per 1M)

$0.01

Specifications

Provider: DeepSeek
Context window: 1M tokens
Parameters: —
Released: —
Open weights: —
Frontier model: No
Hugging Face: deepseek-ai/DeepSeek-V4.1-Flash

Benchmarks

Epoch Capabilities Index: 158.8
GPQA Diamond: 93.2
LMArena (Chatbot Arena) Elo: 1464.5
LMArena Vision Elo: 1277.9
LMArena WebDev Elo: 1665.0

Speed & latency

Time to first token

1.43s

Output speed

407 tok/s

Fastest host: particle (via vercel-ai-gateway).

Compare DeepSeek: DeepSeek V4.1 Flash with…

DeepSeek: DeepSeek V4.1 Flash vs Claude Haiku 5.5$0.50/1M DeepSeek: DeepSeek V4.1 Flash vs GPT-6 Luna$0.50/1M DeepSeek: DeepSeek V4.1 Flash vs Qwen3 30B A3B$0.50/1M DeepSeek: DeepSeek V4.1 Flash vs Olmo 3 32B Think$0.50/1M DeepSeek: DeepSeek V4.1 Flash vs Grok 3 Mini$0.50/1M DeepSeek: DeepSeek V4.1 Flash vs xAI Grok 4.1 Fast Non-Reasoning$0.50/1M

FAQ

How much does DeepSeek: DeepSeek V4.1 Flash cost?

DeepSeek: DeepSeek V4.1 Flash is priced at $0.05 per 1M input tokens and $0.50 per 1M output tokens. Output tokens cost more than input.

What is DeepSeek: DeepSeek V4.1 Flash's context window?

DeepSeek: DeepSeek V4.1 Flash supports a context window of 1M tokens — the maximum prompt plus response length it can handle in a single request.

Is DeepSeek: DeepSeek V4.1 Flash open weight?

Open-weight status for DeepSeek: DeepSeek V4.1 Flash is not recorded in our dataset.

Data as of 2026-10-31. Source: Pricing via OpenRouter API, openrouter.ai. Pricing is per 1M tokens (USD); confirm with the provider before production use.