DeepSeek V4.1-Flash — Specifications
Compilado por Mustafa Ihsan de la documentación publicada por el proveedor · Última actualización
| Desarrollador | DeepSeek |
|---|---|
| Tipo | LLM (MoE, multimodal) |
| Modalidad | Texto y visión → texto |
| Parámetros | 552B total (MoE; 8B active for input, 16B for output) |
| Ventana de contexto | 1 millón |
| Salida máxima | 384 K |
| Licencia | MIT (abierto) |
| Pesos abiertos | Sí |
| Lanzado | 2026-09 |
| Precio de entrada | $0.30 /1M |
| Precio de salida | $1.20 /1M |
| Proveedores de API | DeepSeek API (deepseek-flash), Alibaba Cloud Model Studio, OpenRouter |
Benchmarks
| DeepSeek-reported (V4.1-Flash-1017, 17 Oct 2026) | HLE 42.6 (no tools); Terminal-Bench 4.0 42.3; DeepSWE v1.1 77.0; ProgramBench 29.1. Prices shown are peak rates; off-peak is half. |
|---|
What is DeepSeek V4.1-Flash?
DeepSeek V4.1-Flash is DeepSeek’s current Flash model, called deepseek-flash on its API. DeepSeek released it on 10 September 2026 as the smallest model in a new architecture family: a 552B-parameter mixture-of-experts whose causal encoder–decoder design activates 8B parameters for input and 16B for output, with native visual understanding. On 17 October 2026 DeepSeek shipped an update, DeepSeek-V4.1-Flash-1017, which now serves every deepseek-flash call at the same price. The weights are on Hugging Face under the MIT licence, a download of about 510 GB.
DeepSeek bills peak and off-peak rates. At peak it costs $0.30 per million input tokens (cache miss), $0.006 per million cached input tokens and $1.20 per million output tokens; off-peak rates are half that ($0.15 in, $0.003 cached, $0.60 out). Peak hours are 01:00–04:00 and 06:00–10:00 UTC, Monday to Friday, excluding Chinese public holidays; weekends are off-peak all day. The table on this page shows the peak price. The model has a 1M-token context window and up to 384K output tokens, thinks by default (a non-thinking mode is available) and accepts both OpenAI and Anthropic request formats.
V4.1-Flash replaced DeepSeek V4-Flash, which DeepSeek retired on 10 September 2026; the old deepseek-v4-flash name is still accepted and served by V4.1-Flash-1017. DeepSeek says V4.1-Flash scores ahead of its larger DeepSeek V4-Pro on benchmarks, while V4-Pro costs $1.32 in / $3.96 out at peak and takes no image input. All DeepSeek rates are on our Precios de la API de DeepSeek page, and the Calculadora de costos de API de IA turns them into a monthly bill.
DeepSeek V4.1-Flash pricing: API cost per 1M tokens
| Entrada (por cada millón de tokens) | $0.300 |
|---|---|
| Salida (por cada millón de tokens) | $1.20 |
| Relación salida/entrada | 4× |
| Combinada (4:1 entrada:salida) | $0.480 por 1 millón de tokens |
What DeepSeek V4.1-Flash costs per month
Gasto mensual real con una mezcla entrada:salida de 4:1, es decir, la proporción que realmente genera una carga de trabajo típica de chat o RAG.
| Carga de trabajo | Tokens/mes | Coste mensual |
|---|---|---|
| Proyecto secundario | 1 millón de tokens de entrada / 0,25 millones de tokens de salida | $0.60 |
| Pequeño equipo | 20 millones de tokens de entrada / 5 millones de tokens de salida | $12 |
| Producción | 200 millones de tokens de entrada / 50 millones de tokens de salida | $120 |
Calcule sus propios números en la Calculadora de costos de API de IA.
Cheaper alternatives to DeepSeek V4.1-Flash
| Modelo | Dólares por millón combinados | Usted ahorra |
|---|---|---|
| Llama 3.1 8B abierta | $0.0240 | 95% cheaper |
| Mistral NeMo 12B abierta | $0.0292 | 94% cheaper |
| Gemma 3 4B abierta | $0.0600 | 88% más barato |
Preguntas frecuentes
How much does DeepSeek V4.1-Flash cost per 1M tokens?
DeepSeek V4.1-Flash costs $0.300 per 1M input tokens and $1.20 per 1M output tokens. At a typical 4:1 input-to-output mix that blends to about $0.480 per 1M tokens.
How much does DeepSeek V4.1-Flash cost per month?
A small-team workload of 20M input and 5M output tokens a month costs about $12 on DeepSeek V4.1-Flash. A side project (1M in / 0.25M out) costs roughly $0.60.
What is a cheaper alternative to DeepSeek V4.1-Flash?
Llama 3.1 8B is the strongest cheaper option in our database at $0.0240 per 1M blended — about 95% less than DeepSeek V4.1-Flash. It is also open-weight, so self-hosting is an option.
Can I run DeepSeek V4.1-Flash locally?
Yes. DeepSeek V4.1-Flash is open-weight and needs about a large amount of VRAM at 4-bit quantisation.
Why does DeepSeek V4.1-Flash charge more for output than input?
Output tokens are generated one at a time and cannot be batched the way a prompt can, so they cost the provider more to serve. DeepSeek V4.1-Flash charges 4× more for output, which is why prompt-heavy workloads are far cheaper to run than generation-heavy ones.
Ve todos los modelos DeepSeek comparados lado a lado: Precios de la API de DeepSeek.
Los precios corresponden a las tarifas oficiales publicadas para la API principal del modelo y se revisan periódicamente conforme los proveedores los actualicen. No incluyen descuentos por volumen, procesamiento por lotes ni entradas en caché. Compare todos los modelos uno al lado del otro en la Base de datos de modelos de IA o el Clasificación de modelos de lenguaje grande (LLM).