devseek
Sign in Get API key

FREE INFERENCE · FOR CODING

A long-context coding model.
Free while you code.

devseek is an OpenAI-compatible endpoint for deepseek-v4.1-flash-free, meant for coding. No card, no token meter. Your limit is how many requests run at once: it grows when you use it for code and shrinks when you use it for anything else.

  1. 1Get a key: human check, contact email, your data choice.
  2. 2Export it as DEVSEEK_API_KEY.
  3. 3Run the request on the right. The answer streams back.
terminalstreaming
$ curl https://devseek.space/v1/chat/completions \
    -H "Authorization: Bearer $DEVSEEK_API_KEY" \
    -d '{"model":"deepseek-v4.1-flash-free","stream":true,
         "messages":[{"role":"user",
           "content":"Fix the off-by-one in bsearch()"}]}'

Context window

224K tokens

Max output

64K tokens

Streaming

Server-sent events

Tool calls

OpenAI function calling

API shape

OpenAI Chat Completions

Price

$0 · paid with data

HOW ACCESS WORKS

Built for coding.
Get a key in two minutes.

No credit card and no token budget. The only limit is how many requests you run at the same time.

Get API key
  1. 01 / CHECK

    Pass the human check.

    A Cloudflare Turnstile challenge, verified on our server, not only in your browser.

  2. 02 / CODE

    Use it for code.

    No GitHub check. Each request is classified as coding or not: local rules decide clear cases, jev decides unclear ones. Coding raises your level; other use lowers it.

  3. 03 / CHOOSE

    Agree to the data terms.

    The free service runs on data: your prompts and responses are stored and may be licensed (sold) in de-identified form. Without this agreement there is no key.

  4. 04 / BUILD

    Point your SDK at devseek.

    Same OpenAI client, new base URL. Streaming and tool calls included.

THE MODEL

One model. Measured live, not promised.

Live status

devseek serves exactly one model so the numbers below mean something. They come from the requests this gateway handled in the last 24 hours.

Model ID

deepseek-v4.1-flash-free

Input
224K
Output
64K
Features
Streaming · tools · JSON mode

Up to 224K tokens of context and 64K output. The upstream accepted 239,761 input tokens in our test; 224K leaves a safety margin.

—

Time to first token p50 · p95

—

Full response p50 · p95

—

Output speed

—

Success, 24h

—

LEVELS

100 levels. Counted in sessions, earned with coding tokens.

How levels move

Every key starts at level 1 with 2 concurrent sessions. The more tokens you spend on coding, the higher you climb, slowly, up to 10 sessions at level 100.

  1. 2ScriptL1–10Script
  2. 2–3FunctionL11–20Function
  3. 3–4ModuleL21–30Module
  4. 4–5PackageL31–40Package
  5. 5LibraryL41–50Library
  6. 6FrameworkL51–60Framework
  7. 6–7RuntimeL61–70Runtime
  8. 7–8CompilerL71–80Compiler
  9. 8–9KernelL81–90Kernel
  10. 9–10ArchitectL91–100Architect

↑

How you go up

Each request is judged once: is it about software? Only then is XP added: 1 XP per 750 tokens (prompt plus completion, as counted by the model), up to 90,000 XP a day. When XP reaches the next level, you move up at the daily update.

↓

How you go down

A request that is not about code removes 1 XP per 1,500 tokens, up to 45,000 XP a day. A day without coding shrinks XP by 3%. You drop a level only when XP falls clearly below your level's threshold (85% of it).

±1

At most one step a day

Levels change once a day, by at most one step up or down. A single burst of requests cannot jump you several levels.

STATUS · LIVE

Status. Straight from the gateway.

Live status

State

Loading live data…

Uptime
—
Accounts
—

Sessions in flight

—

Requests, last hour

—

Success, 24h

—

Upstream capacity in use

—
48 h agoAdmitted requests per hour, last 48 hoursnow

MADE FOR CODING

Your stack.
One line changed.

Use the Chat Completions format you already know. Keep your retries, your agent framework and your editor plugin.

  • 01OpenAI-compatible chat completions
  • 02Server-sent event streaming
  • 03Tool and function calling
  • 04Clear 429 bodies when you hit your session limit
Start integrating
OPENAI SDK · UNCHANGED
import os
from openai import OpenAI
 
client = OpenAI(
    api_key=os.environ["DEVSEEK_API_KEY"],
    base_url="https://devseek.space/v1",
)
 
stream = client.chat.completions.create(
    model="deepseek-v4.1-flash-free",
    messages=[{"role": "user", "content": "Write a binary search in Rust"}],
    max_tokens=4096,
    stream=True,
)
for chunk in stream:
    if chunk.choices:
        print(chunk.choices[0].delta.content or "", end="")
OpenAI-compatible /v1/chat/completionsAPI reference

THE DEAL, IN PLAIN WORDS

If it is free, the data is the price.

devseek stores your prompts and the model's responses, keeps the raw records encrypted for up to 30 days, removes obvious personal data and secrets, and may share or license (sell) de-identified datasets to third parties such as AI labs and dataset brokers. This is the condition of the free service: there is no key without it. You can download or delete your stored data at any time.

Read the data use page

Free

$0

No card. No token meter. No trial that ends.

Your data

Stored, de-identified and sold as datasets. Agreeing is required.

Retention

30 days

Raw records are deleted after 30 days; only de-identified data remains.

Stop paying per token
for the code you write.

Two minutes from now you can have a key.