DeepSeek V4.1 Flash API

Fast 1M-context reasoning model with aggressive cache pricing, built for high-volume agent traffic. Always the latest version, now 1017. $0.06 input, $0.003 cached input and $0.24 output per 1M tokens, with a 1,048,568 tokens context.

DeepSeek V4.1 Flash price per 1M tokens

DeepSeek V4.1 Flash price in USD per 1M tokens
ModeInputCached inputOutput
Standard$0.06$0.003$0.24
Fast mode$0.28$0.028$1.10

Prices are USD per 1M tokens, 50% off the list price of $0.12 input, $0.006 cached input and $0.48 output. Cached input is a prompt prefix the model has seen before, which agents resend on every turn. You pay only for the tokens you use. Compare it with every model on OpenScale.

Specs

DeepSeek V4.1 Flash specs
SpecValue
Model iddeepseek/deepseek-v4.1-flash
DeveloperDeepSeek
Context length1,048,568 tokens
Max output384,000 tokens per request
Output speed200+ tokens per second
Fast mode speed~2x standard
Rate limit100 requests and 10M tokens per minute per key
  • Text and image input, text output.
  • Tool calling.
  • Structured outputs with a JSON schema, and JSON mode.
  • Reasoning you can turn on or off; the reasoning is returned as reasoning. Reasoning effort: low, high, max.

Versions

deepseek/deepseek-v4.1-flash always serves the latest version we have tested, now 1017. Pinned ids never change. Every version has the same price.

DeepSeek V4.1 Flash versions
Model idVersionReleasedBehavior
deepseek/deepseek-v4.1-flash101717 Oct 2026Moves to each new version
deepseek/deepseek-v4.1-flash-1017101717 Oct 2026Never changes
deepseek/deepseek-v4.1-flash-0910091010 Sep 2026Never changes
deepseek/deepseek-v4.1-flash:fast101717 Oct 2026Moves to each new version, fast mode
deepseek/deepseek-v4.1-flash-1017:fast101717 Oct 2026Never changes, fast mode
deepseek/deepseek-v4.1-flash-0910:fast091010 Sep 2026Never changes, fast mode

Call DeepSeek V4.1 Flash from your code

Use any OpenAI SDK with the base URL https://api.openscale.so/v1, or any Anthropic SDK with https://api.openscale.so/anthropic. Set your API key as OPENSCALE_API_KEY.

curl
curl https://api.openscale.so/v1/chat/completions \
  -H "Authorization: Bearer $OPENSCALE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek/deepseek-v4.1-flash",
    "messages": [{"role": "user", "content": "Explain what a token is in one sentence."}]
  }'
OpenAI SDK (Python)
import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.openscale.so/v1",
    api_key=os.environ["OPENSCALE_API_KEY"],
)

response = client.chat.completions.create(
    model="deepseek/deepseek-v4.1-flash",
    messages=[{"role": "user", "content": "Explain what a token is in one sentence."}],
)
print(response.choices[0].message.content)
Anthropic SDK (Python)
import os
from anthropic import Anthropic

client = Anthropic(
    base_url="https://api.openscale.so/anthropic",
    api_key=os.environ["OPENSCALE_API_KEY"],
)

message = client.messages.create(
    model="deepseek/deepseek-v4.1-flash",
    max_tokens=1024,
    messages=[{"role": "user", "content": "Explain what a token is in one sentence."}],
)
print(next(block.text for block in message.content if block.type == "text"))

Every parameter, streaming and errors are in the API reference.

Use DeepSeek V4.1 Flash in your coding agent

Each guide is a tested setup that keeps your existing configuration. Select deepseek/deepseek-v4.1-flash as the model.

Or pick your agent and copy one setup prompt on the agent setup page.

Questions

How much does the DeepSeek V4.1 Flash API cost?

$0.06 per 1M input tokens, $0.003 per 1M cached input tokens and $0.24 per 1M output tokens. That is 50% off the list price of $0.12, $0.006 and $0.48. You pay only for the tokens you use, from prepaid credit.

Is the DeepSeek V4.1 Flash API OpenAI compatible?

Yes. Point any OpenAI SDK at https://api.openscale.so/v1 and use the model id deepseek/deepseek-v4.1-flash, with Chat Completions or Responses. Anthropic SDKs work too, at https://api.openscale.so/anthropic.

What is the context length of DeepSeek V4.1 Flash?

1,048,568 tokens in total, input and output together, with up to 384,000 tokens of output per request.

How fast is DeepSeek V4.1 Flash on OpenScale?

200+ tokens per second of output, a floor under the measured median. Fast mode (deepseek/deepseek-v4.1-flash:fast) is ~2x standard, at $0.28 input and $1.10 output per 1M tokens.

Which DeepSeek V4.1 Flash version does the API serve?

deepseek/deepseek-v4.1-flash always serves the latest version we have tested, now 1017. To stay on one version, call a pinned id: deepseek/deepseek-v4.1-flash-1017, deepseek/deepseek-v4.1-flash-0910. Pinned ids never change, and every version has the same price.

Can I use DeepSeek V4.1 Flash in a coding agent?

Yes. OpenScale has a tested setup for 12 coding agents, including Claude Code, Codex, OpenCode, OpenClaw. One API key works for every agent.

What are the rate limits for DeepSeek V4.1 Flash?

100 requests and 10,000,000 tokens per minute for each API key. Need more? Email hello@openscale.so.

How do I start?

Create an account, add credit and create an API key. New accounts get free credit to try it.

Create an account to get an API key. Plain Markdown version of this page: /models/deepseek-v4.1-flash.md.