All models

DeepSeek V4 Flash Free runs at 99.9% off on TeamoRouter.

DeepSeek: DeepSeek V4 Flash Free

No training

New accounts start at a $0 balance — this tier is still billed at a lower rate, so top up from $5 before your first call.

Top up

DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated parameters, supporting a 1M-token context window. It is designed for fast inference and high-throughput workloads, while maintaining strong reasoning and coding performance. The model includes hybrid attention for efficient long-context processing. It is well suited for applications such as coding assistants, chat systems, and agent workflows where responsiveness and cost efficiency are important.

Modalities

Price (in / out)

99.9% off

$0.0004 / $0.0013$0.44 / $1.32per 1M

Context

1M

Released

Apr 24, 2026

Call the DeepSeek V4 Flash Free API

Model ID deepseek-v4-flash-free · replace <TEAMOROUTER_API_KEY> with your API key

Get an API key

OpenAI-compatible

curl https://api.teamorouter.com/v1/chat/completions \
  -H "Authorization: Bearer <TEAMOROUTER_API_KEY>" \
  -H "Content-Type: application/json" \
  -d '{"model":"deepseek-v4-flash-free","messages":[{"role":"user","content":"Hello"}]}'

Anthropic format

curl https://api.teamorouter.com/v1/messages \
  -H "x-api-key: <TEAMOROUTER_API_KEY>" \
  -H "anthropic-version: 2023-06-01" \
  -H "Content-Type: application/json" \
  -d '{"model":"deepseek-v4-flash-free","max_tokens":1024,"messages":[{"role":"user","content":"Hello"}]}'

Providers

TeamoRouter routes by health and cost within the discount range and provider list you configured. When one returns an error we fall through to the next best — you don't pick a provider in the request. Configure discount range

Need a specific set of providers?

ProviderContextInputOutputCacheLatencyThroughputNo training
DeepSeek1M$0.44$0.0004$1.32$0.0013$0.014$0———No training
Baidu AI Cloud1M$0.44$0.0004$1.32$0.0013$0.014$0———No training
Volcengine1M$0.44$0.0004$1.32$0.0013$0.014$0———No training
Tencent Cloud1M$0.44$0.0004$1.32$0.0013$0.014$0———No training

Uptime

TeamoRouter continuously probes every provider and falls through to the next best one on error.

Uptime (24h)

—

Uptime (3d)

—

Uptime, last 3 days

—

-72h-48h-24hNow

Uptime, last 24 hours

One line per upstream provider, taking the best success rate among that provider's channels. The TeamoRouter line counts only the final attempt of each request — the end-to-end result after all fallbacks.

    AVAILABILITY · LAST 24H · TEAMOROUTER GATEWAY

    Data security

    TeamoRouter does not use your data to train models.

    For the full data-security policy, learn more.

    Need to pick your own providers? .

    Quickstart

    from openai import OpenAI
    
    client = OpenAI(
        base_url="https://api.teamorouter.com/v1",  # the only line that changes
        api_key="<TEAMOROUTER_API_KEY>",
    )
    response = client.chat.completions.create(
        model="deepseek-v4-flash-free",
        messages=[{"role": "user", "content": "Hello"}],
    )
    print(response.choices[0].message.content)

    Endpoint: https://api.teamorouter.com/v1

    About DeepSeek V4 Flash Free

    DeepSeek V4 Flash Free is a DeepSeek model. On TeamoRouter its model ID is deepseek-v4-flash-free, and the same TeamoRouter API key works for it and every other model. Setup steps are in the API docs.

    Model ID
    deepseek-v4-flash-free
    Provider
    DeepSeek
    Context window
    1M tokens
    Official list price
    $0.44 input / $1.32 output per 1M tokens
    Released
    Apr 24, 2026

    Use the DeepSeek V4 Flash Free API

    Point the base URL at TeamoRouter and use deepseek-v4-flash-free as the model name; nothing else changes. Python example:

    from openai import OpenAI
    
    client = OpenAI(
        base_url="https://api.teamorouter.com/v1",  # the only line that changes
        api_key="<TEAMOROUTER_API_KEY>",
    )
    response = client.chat.completions.create(
        model="deepseek-v4-flash-free",
        messages=[{"role": "user", "content": "Hello"}],
    )
    print(response.choices[0].message.content)

    Use DeepSeek V4 Flash Free in Claude Code / OpenCode

    Claude Code

    export ANTHROPIC_BASE_URL=https://api.teamorouter.com
    export ANTHROPIC_AUTH_TOKEN=<your TeamoRouter API key>
    export ANTHROPIC_API_KEY=""
    claude --model deepseek-v4-flash-free

    Full Claude Code setup

    OpenCode

    OpenCode → Settings → Providers → Custom provider
    Provider ID: teamorouter
    Base URL:    https://api.teamorouter.com/v1
    API key:     <your TeamoRouter API key>
    Model ID:    deepseek-v4-flash-free

    Full OpenCode setup

    DeepSeek V4 Flash Free FAQ

    What is the DeepSeek V4 Flash Free API model ID?
    The model ID is deepseek-v4-flash-free. The OpenAI-compatible base URL is https://api.teamorouter.com/v1.
    How large is the DeepSeek V4 Flash Free context window?
    DeepSeek V4 Flash Free has a 1M-token context window.
    Can I use DeepSeek V4 Flash Free from Russia?
    Yes. TeamoRouter works from Russia without a VPN, and the Russian version of the site lets you pay in rubles with SBP, SberPay, T-Bank or YooMoney. DeepSeek V4 Flash Free на русском.
    Can I use DeepSeek V4 Flash Free in Cursor, Cline or Cherry Studio?
    Yes. Choose the OpenAI-compatible provider, set the base URL to https://api.teamorouter.com/v1, use your TeamoRouter API key, and enter deepseek-v4-flash-free as the model name.
    Can I pay for the DeepSeek V4 Flash Free API with USDT?
    Yes. In the top-up dialog, click "Pay with crypto" and send USDT, USDC or ETH from Binance, OKX or any wallet. The minimum is $5 and no browser extension is needed. Step by step: how to pay for the API with USDT.
    DeepSeek V4 Flash Free API: Model ID, Pricing & Setup