DeepSeek V4.1 Flash (batch) pricing & benchmarks
DeepSeek V4.1 Flash (batch) is available from DeepSeek at $0.050 per million input tokens and $0.150 per million output tokens ($0.075 blended at 3:1). It accepts up to 1,048,576 tokens of context. DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture. It activates 8B parameters on input and 16B on...
Pricing
Per million tokens · OpenRouter
Input$0.050
Output$0.150
Blended (3:1)$0.075
Specification
deepseek/deepseek-v4.1-flash:batch
Context window1.0M
Max output384K
ReleasedSep 2026
LicenceOpen weights
Modalitiesin:text, in:image, out:text
No independently-run benchmark scores are published for DeepSeek V4.1 Flash (batch) yet. We show nothing rather than reprinting an unverified figure.
Where to run DeepSeek V4.1 Flash (batch)
2 hosts · 2.2× between cheapest and dearest. Blended at 3:1. ⚠ marks an option serving less context than the best available, or re-pricing above a prompt-length threshold. Bracketed labels are the provider's own service tier or region.
| Host | Blended $/1M | In / Out | Context | Weights | Uptime 24h |
|---|---|---|---|---|---|
| Sail Research | $0.075 | $0.050 / $0.150 | 1.0M | fp4 | — |
| DeepInfra | $0.168 | $0.112 / $0.336 | 1.0M | fp8 | — |
Host prices and uptime from OpenRouter, synced 2026-10-22. Lower-precision weights (fp4, fp8) can cost less and score worse than the same model at bf16 — the score above is not host-specific.
Compare DeepSeek V4.1 Flash (batch)
DeepSeek V4.1 Flash (batch) vs Gemini 3.7 Flash
DeepSeek V4.1 Flash (batch) vs Grok 4.6
DeepSeek V4.1 Flash (batch) vs Inkling Small
DeepSeek V4.1 Flash (batch) vs Qwen3.7 Flash
DeepSeek V4.1 Flash (batch) vs Claude Opus 5
DeepSeek V4.1 Flash (batch) vs Gemini 3.6 Flash
DeepSeek V4.1 Flash (batch) vs Gemini 3.5 Flash Lite
DeepSeek V4.1 Flash (batch) vs Inkling
FAQ
How much does DeepSeek V4.1 Flash (batch) cost?
DeepSeek V4.1 Flash (batch) costs $0.050 per million input tokens and $0.150 per million output tokens on OpenRouter. At a 3:1 input:output mix that blends to $0.075 per million tokens.
What is DeepSeek V4.1 Flash (batch)'s context window?
DeepSeek V4.1 Flash (batch) accepts up to 1,048,576 tokens of context, and can generate up to 384,000 output tokens.