DeepSeek V4.1 Flash API pricing

Price comparison

Cloudflare's list price is what the provider charges through Cloudflare; one-api.ai is what a call debits here. one-api.ai runs DeepSeek V4.1 Flash on Cloudflare Workers AI, so the maker's own API price does not apply and is not shown.

Per 1M tokens

Sources: Cloudflare Workers AI pricing (page updated 2026-10-20), checked 2026-10-22; hiapi's public price page, collected 2026-10-21.

What a month costs

Three example workloads. "Monthly cost" multiplies the tokens by the one-api.ai price per 1M, and that is what billing debits: usage is metered to a millionth of a credit, with no rounding up per call. A credit is a tenth of a cent.

Prompts that reuse a long prefix can cost less where the model has a cached-input rate, shown in the price comparison above.

Context and cache tiers

The context window is not stated on the source page, so it is not given here. There is one price tier for every prompt length. Cached input is billed at the cached rate only when the provider reports a cache hit; the cost examples above assume no cache hits. one-api.ai sets max_tokens to 4,096 when a request leaves it out and clamps it to 16,384.

Request examples

Python

import os
from openai import OpenAI

client = OpenAI(base_url="https://one-api.ai/v1/launch", api_key=os.environ["ONE_API_TOKEN"])
resp = client.chat.completions.create(
    model="@cf/deepseek-ai/deepseek-v4.1-flash-1017",
    messages=[{"role": "user", "content": "Summarise RDAP in one sentence."}],
    max_tokens=512,
)
print(resp.choices[0].message.content)
print(resp.usage)

JavaScript

import OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://one-api.ai/v1/launch", apiKey: process.env.ONE_API_TOKEN });
const resp = await client.chat.completions.create({
  model: "@cf/deepseek-ai/deepseek-v4.1-flash-1017",
  messages: [{ role: "user", content: "Summarise RDAP in one sentence." }],
  max_tokens: 512,
});
console.log(resp.choices[0].message.content, resp.usage);

curl

curl https://one-api.ai/v1/launch/chat/completions \
  -H "Authorization: Bearer $ONE_API_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"model":"@cf/deepseek-ai/deepseek-v4.1-flash-1017","messages":[{"role":"user","content":"Say hello in one sentence."}],"max_tokens":512}'

Notes on DeepSeek V4.1 Flash

This model runs on Cloudflare Workers AI under the id @cf/deepseek-ai/deepseek-v4.1-flash-1017. Cloudflare caps Workers AI models that are paid with prepaid AI Gateway credits at 50 requests per minute, so a burst above that is refused upstream even when your one-api.ai balance is fine. Plan batch jobs around that ceiling or spread them over time.

The cached-input rate is about one fiftieth of the plain input rate. Cloudflare decides when a prefix counts as cached; you cannot force a cache hit, and the cost examples on this page assume none.

hiapi, the other public reseller we track, posts a higher input price for the same model family. Their figure was collected by hand from their price page and may have changed since.

Context window: the Cloudflare pricing page we cite does not state it, so this page does not either. Check the Cloudflare model catalog before sending very long prompts.

FAQ

Is DeepSeek V4.1 Flash the same model as DeepSeek's own API?

It is the Cloudflare Workers AI build named @cf/deepseek-ai/deepseek-v4.1-flash-1017. We do not call DeepSeek's own API, so behaviour and limits follow Cloudflare's deployment.

Why is there a 50 requests per minute limit?

Cloudflare applies it to Workers AI models billed through prepaid AI Gateway credits. It sits on top of one-api.ai's own per-IP and per-key limits.

Does streaming change the price?

No. Streaming and non-streaming calls debit the same per-token rates. If a stream ends without a usage object the call settles at the amount reserved before it ran, so prefer clients that read the final usage chunk.

Related

• LLM API pricing comparison
• How one-api.ai prices are set
• DeepSeek V4 Pro API pricing
• GLM 5.3 API pricing
• Claude Haiku 5.5 API pricing
• Grok 4.7 API pricing