DeepSeek V4 Flash
DeepSeek · Text
DeepSeek V4 Flash, a fast and low-cost variant for high-throughput and everyday tasks. Served through getmodel's low-cost domestic-models group over an OpenAI-compatible endpoint. DeepSeek V4 Flash is available on GetModel via an OpenAI-compatible API, billed pay-as-you-go. Get one key and call it from any OpenAI SDK.
Pricing
| Item | Price |
|---|---|
| Input | $0.081 / 1M tokens |
| Output | $0.162 / 1M tokens |
How to call
curl https://getmodel.ai/v1/chat/completions \
-H "Authorization: Bearer $GETMODEL_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"deepseek-v4-flash","messages":[{"role":"user","content":"Hello"}]}' from openai import OpenAI
client = OpenAI(base_url="https://getmodel.ai/v1", api_key="$GETMODEL_API_KEY")
resp = client.chat.completions.create(
model="deepseek-v4-flash",
messages=[{"role": "user", "content": "Hello"}],
)
print(resp.choices[0].message.content)