1. 7API
  2. Models
  3. DeepSeek
  4. DeepSeek V4.1 Flash 1017 HQ

DeepSeek V4.1 Flash 1017 HQ API

Model ID: deepseek-v4.1-flash-1017-hq · Developer: DeepSeek · Available on 7API: yes, as of 2026-11-20

A separate HQ tier of DeepSeek V4.1 Flash 1017 with image input. Input and output cost $0.05/M; cached input costs $0.01/M.

Call DeepSeek V4.1 Flash 1017 HQ with any OpenAI- or Anthropic-compatible client. Use base URL https://7api.st/v1 (OpenAI) or https://7api.st (Anthropic) and send "model": "deepseek-v4.1-flash-1017-hq".

Specifications

Model IDdeepseek-v4.1-flash-1017-hq
Context window1,000,000 tokens
Max output65,536 tokens
InputText and images
Tool callingYes
StreamingYes
Reasoning effortModel default
API formatsChat Completions, Responses, Anthropic Messages

Pricing

USD per 1M tokens
Input$0.05
Output$0.05
Cached input$0.01

For example, an agent turn with 150,000 cached input tokens, 2,000 new input tokens and 800 output tokens costs about $0.0016 on DeepSeek V4.1 Flash 1017 HQ. Billing is pay per token from a prepaid balance. See Pricing and billing.

Example

Python (OpenAI SDK)
from openai import OpenAI

client = OpenAI(base_url="https://7api.st/v1", api_key="YOUR_7API_KEY")
r = client.chat.completions.create(
    model="deepseek-v4.1-flash-1017-hq",
    messages=[{"role": "user", "content": "Write a haiku about caching."}],
)
print(r.choices[0].message.content)

In Claude Code: /model claude-deepseek-v4.1-flash-1017-hq. Setup guides: Claude Code, OpenCode, Codex, Cursor.