TeamoRouter
Bench

DeepSeek V4 Flash

Call the DeepSeek V4 Flash API

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

OpenAI-compatible

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

Anthropic format

curl https://api.teamorouter.ai/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","max_tokens":1024,"messages":[{"role":"user","content":"Hello"}]}'

Loading model catalog…

Back to models

About DeepSeek V4 Flash

DeepSeek V4 Flash is a DeepSeek model. On TeamoRouter its model ID is deepseek-v4-flash, 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
Provider
DeepSeek
Context window
1M tokens
Official list price
$0.44 input / $1.32 output per 1M tokens

More DeepSeek models

Similar-priced models

Compare all models →Video generation models →

Use the DeepSeek V4 Flash API

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

from openai import OpenAI

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

Use DeepSeek V4 Flash in Claude Code / OpenCode

Claude Code

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

Full Claude Code setup

OpenCode

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

Full OpenCode setup

DeepSeek V4 Flash guides

DeepSeek V4 Flash FAQ

What is the DeepSeek V4 Flash API model ID?
The model ID is deepseek-v4-flash. The OpenAI-compatible base URL is https://api.teamorouter.ai/v1.
How do I get a DeepSeek V4 Flash API key?
You don't need a DeepSeek account. Sign up for TeamoRouter, create a key (sk-teamo-…) under API Keys in the dashboard, top up from $5, and call deepseek-v4-flash — the same key also works for every other model. Create an API key.
How large is the DeepSeek V4 Flash context window?
DeepSeek V4 Flash has a 1M-token context window.
How much does the DeepSeek V4 Flash API cost?
The official list price of DeepSeek V4 Flash is $0.44 input / $1.32 output per 1M tokens. TeamoRouter bills per use with no monthly fee; see the price table on this page for the current discounted price.
How do I pay for the DeepSeek V4 Flash API?
New accounts start with a $0 balance. Top up from $5 by card in the TeamoRouter dashboard, then usage is deducted per request, with no subscription. Top up.
Can I use DeepSeek V4 Flash 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 на русском.
Can I use DeepSeek V4 Flash in Cursor, Cline or Cherry Studio?
Yes. Choose the OpenAI-compatible provider, set the base URL to https://api.teamorouter.ai/v1, use your TeamoRouter API key, and enter deepseek-v4-flash as the model name.
Can I pay for the DeepSeek V4 Flash 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.