deepseek/deepseek-v4.1-flash
DeepSeek-V4.1-Flash-1017 is the October 17, 2026 checkpoint of DeepSeek V4.1 Flash. Supports a 1M-token context and up to 64K output tokens on the current OneHop route, thinking and non-thinking modes, tool calling, JSON output and streaming through the OpenAI-compatible Chat Completions API. Image input requires a base64 data URI; Playground uploads are converted automatically. Fixed OneHop prices per 1M tokens: input $0.09, output $0.36 and cache reads $0.0018, equal to 30% of DeepSeek's official peak USD rates. No time-of-day discount is applied.
Fuente: https://api-docs.deepseek.com/quick_start/pricing/ · Verificado el 2026-10-19
Lectura de caché $0.0018/M · Escritura de caché —/M
Puedes usar cualquiera de los IDs para llamar al modelo via API.
deepseek/deepseek-v4.1-flashdeepseek-v4.1-flash-1017You can use these names directly in the request model field.
Reemplaza el marcador ONEHOP_KEY con tu API key. Crear →
from openai import OpenAI
client = OpenAI(
base_url="https://api.onehop.ai/v1",
api_key="<ONEHOP_KEY>",
)
completion = client.chat.completions.create(
model="deepseek/deepseek-v4.1-flash",
messages=[{"role": "user", "content": "What is the meaning of life?"}],
)
print(completion.choices[0].message.content)