DeepSeek V4.1 Flash 1017

We introduce DeepSeek-V4.1-Flash, a multimodal Mixture-of-Experts (MoE) model with 552B backbone parameters and support for contexts of up to one million tokens. The model natively processes images and text, and generates text autoregressively. By DeepSeek, on GridPup at $0.36 per million input tokens and $1.45 per million output tokens, paid from your GridPup balance per request. No subscription.

Try it in the Playground Get an API key

Price

Made by: DeepSeek
Input: $0.36 per million tokens
Output: $1.45 per million tokens
Context: 1.048576M tokens
Can: Tools, Reasoning, JSON, Reads images

What it costs, roughly
A 1,000-word answer to a 200-word question	$0.002
1,000 such answers	$2.03
Summarising a 50-page document (25,000 words) in 500 words	$0.013

Use it from your code

GridPup's API speaks OpenAI's format: use any OpenAI SDK with the base URL https://api.gridpup.com/v1/ai and a GridPup API key with Also use AI models. The answer tells you what it cost. More in the API docs.

from openai import OpenAI

client = OpenAI(base_url="https://api.gridpup.com/v1/ai", api_key="gp_live_…")

r = client.chat.completions.create(
    model="@cf/deepseek-ai/deepseek-v4.1-flash-1017",
    messages=[{"role": "user", "content": "Explain a KV cache in two sentences."}],
)
print(r.choices[0].message.content)
print("cost:", r.usage.cost_usd, "USD")

Questions

How much does DeepSeek V4.1 Flash 1017 cost?: $0.36 per million input tokens and $1.45 per million output tokens, charged per request from your prepaid balance. You need a small balance to start ($1 for most models); there is no monthly fee.
Who runs it?: DeepSeek made DeepSeek V4.1 Flash 1017. GridPup serves it through Cloudflare's AI Gateway, so you use it with one GridPup balance instead of an account with DeepSeek.
Does it work with the OpenAI SDK?: Yes: set base_url to https://api.gridpup.com/v1/ai and the model to @cf/deepseek-ai/deepseek-v4.1-flash-1017.

Similar chat and reasoning models

Llama 4 Scout 17B 16EMeta$0.33 per million input tokens
QwQ 32BQwen$0.80 per million input tokens
Qwen2.5 Coder 32BQwen$0.80 per million input tokens
GPT-5.4 nanoOpenAI$0.24 per million input tokens
DeepSeek V4 Flash 0731DeepSeek$0.53 per million input tokens
Nemotron 3 120B A12BNVIDIA$0.60 per million input tokens

All chat and reasoning models and prices

Loading…