deepseek-v4-flash API

deepseek-v4-flash is the speed-and-throughput tier of DeepSeek's V4 generation. DeepSeek's own API docs position it as the successor to the long-running deepseek-chat line (the legacy deepseek-chat and deepseek-reasoner names are being retired in favor of the V4 models), and give it a 1M-token context window with up to 384K output tokens — an unusually large window for a model in this price class. If you have pipelines built around earlier DeepSeek chat models, this is the natural drop-in upgrade. On CaMeL Hub the model is billed purely per token at $1 per 1M input and $2 per 1M output, with no subscription required — top up a wallet balance and pay only for what you send. You call it through the same OpenAI-compatible endpoint as every other model on the platform: set base_url to https://api.camel-hub.com/v1 in the official OpenAI SDK (Python, Node.js, or any compatible client), pass your CaMeL Hub API key, and request the model name deepseek-v4-flash. Switching between it and a GPT, Claude, or Gemini model is a one-line model-name change. In practice v4-flash behaves like a workhorse: it streams tokens quickly, follows structured instructions reliably, and its function-calling support makes it a solid engine for agent loops and structured-extraction jobs where you would rather not pay frontier-model rates per iteration. For tasks that need deeper multi-step reasoning, DeepSeek offers the heavier deepseek-v4-pro tier — also available on CaMeL Hub — but for the bulk of everyday chat, summarization, and tool-calling traffic, flash is the cost-effective default.

curl https://api.camel-hub.com/v1/chat/completions \
  -H "Authorization: Bearer $CAMEL_HUB_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek-v4-flash",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from openai import OpenAI

client = OpenAI(
    api_key="$CAMEL_HUB_KEY",
    base_url="https://api.camel-hub.com/v1",  # <-- the only change vs. the OpenAI default
)

resp = client.chat.completions.create(
    model="deepseek-v4-flash",
    messages=[{"role": "user", "content": "Hello!"}],
)
print(resp.choices[0].message.content)

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.CAMEL_HUB_KEY,
  baseURL: "https://api.camel-hub.com/v1", // <-- the only change vs. the OpenAI default
});

const resp = await client.chat.completions.create({
  model: "deepseek-v4-flash",
  messages: [{ role: "user", content: "Hello!" }],
});
console.log(resp.choices[0].message.content);