Model APIs

DeepSeek V4 Flash

Chat completions for server-side applications through a workspace API key.

JSON mode
Streaming

per 1M input tokens: $0.14
per 1M cached input tokens: $0.14
per 1M output tokens: $0.28

No cache discount applies. Cached input is billed at the standard $0.14 per 1M input tokens.

Hosted inference requires the Core plan or higher.

Copy a request

Set RUNINFRA_GATEWAY_KEY to a workspace API key. Each example reads the key from the environment.

API access is paused until Aug 11, 2026, 9:17 AM UTC. You can still review and copy the request.

OpenAI Python SDK

import os
import uuid
from openai import OpenAI

api_key = os.environ.get("RUNINFRA_GATEWAY_KEY")
if not api_key: raise RuntimeError("Set RUNINFRA_GATEWAY_KEY first.")

client = OpenAI(
    api_key=api_key,
    base_url="https://api.runinfra.ai/v1",
)

response = client.chat.completions.create(
    model="deepseek-v4-flash",
    messages=[{"role": "user", "content": "Hello"}],
    max_tokens=512,
    extra_headers={"X-Client-Request-Id": str(uuid.uuid4())},
)
print(response.choices[0].message.content)

Specifications

Context window: 131,072 tokens
Maximum generated output: 32,768 tokens
API: Chat completions

DeepSeek V4 Flash

Copy a request

Specifications

Who you are buying from

DeepSeek V4 Flash

Copy a request

Specifications

Who you are buying from