Notice
!

This Free Endpoint Has Retired

Thanks to everyone who tried DeepSeek‑V4‑Flash‑0731 here! Want your own, always‑on copy? Deploy it yourself on Hugging Face Inference Endpoints, starting at $10/hr with autoscale‑to‑zero, so you only pay while it's actually running.

DeepSeek‑V4‑Flash‑0731 — Read Me

DeepSeek‑V4‑Flash‑0731

A 284B‑parameter mixture‑of‑experts language model, 6 of 256 experts active per token, with a built‑in speculative decoder ("DSpark") and a 1,048,576‑token context window (64K native, YaRN‑extended).

MoE · 6 / 256 experts 1M ctx (YaRN) DSpark spec‑decode MIT license served by victor

The Endpoint

This is a free, public Hugging Face Inference Endpoint — an OpenAI‑compatible Chat Completions API. No Hugging Face token required.

Terminal — curl
curl https://q5dh1rfszfym23hj.us-east-2.aws.endpoints.huggingface.cloud/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek-ai/DeepSeek-V4-Flash-0731",
    "messages": [{"role": "user", "content": "Write a haiku about sparse attention."}],
    "reasoning_effort": "high",
    "temperature": 1.0,
    "top_p": 0.95
  }'
client.py — Python (openai SDK)
from openai import OpenAI

client = OpenAI(
    base_url="https://q5dh1rfszfym23hj.us-east-2.aws.endpoints.huggingface.cloud/v1",
    api_key="not-needed",   # public endpoint — any non-empty string works
)

resp = client.chat.completions.create(
    model="deepseek-ai/DeepSeek-V4-Flash-0731",
    messages=[{"role": "user", "content": "Explain DSpark speculative decoding in 3 sentences."}],
    extra_body={"reasoning_effort": "max"},   # low (default) · high · max
)
print(resp.choices[0].message.content)

Reasoning Effort

Thinking is controlled by reasoning_effort: omit it for fast non‑reasoning replies, set it to make the model think. Note: on this deployment (vLLM v0.26.0), low and high behave identically — only max adds an extra maximum‑effort directive.

Recommended sampling: temperature = 1.0, top_p = 0.95 for agentic use, top_p = 1.0 otherwise.
valuebehaviour
(omitted)No reasoning — fastest replies.
"low" / "high"Thinking mode on (equivalent on this deployment).
"max"Thinking plus a maximum‑effort directive — slowest, most thorough.

This deployment serves up to 393,216 tokens of context (the documented floor for high/max effort) — a slice of the model's native 1,048,576‑token window.

Tool Calling

Internally the model emits a DeepSeek‑specific markup ("DSML") for tool calls, but the endpoint's built‑in parser translates it to standard OpenAI tools / tool_calls JSON — use it exactly like any other OpenAI‑style function‑calling model.

tools.json
{
  "tools": [{
    "type": "function",
    "function": {
      "name": "get_weather",
      "parameters": {"type": "object", "properties": {"location": {"type": "string"}}}
    }
  }],
  "tool_choice": "auto"
}
!

This is a Community Endpoint

Shared, free, and rate‑limited to be fair to everyone: about 20 requests in a burst, refilling to roughly 12 requests/minute, per IP address. Parallel agent tool‑calls are fine — hammering it from a script is not. Over the limit, you'll get a 429 with a friendly note and a Retry‑After header.

Be NiceDeploy Your Own →
Chat With It

Prefer a UI?

There's a full chat-ui front end running on this same endpoint — reasoning effort and artifacts both switched on.

Terminal — pi (pi‑mono)

Wiring It Into pi

pi reads custom model providers from ~/.pi/agent/models.json. Add a provider entry pointing at this endpoint's OpenAI‑compatible base URL, then select it from the CLI.

~/.pi/agent/models.json
{
  "providers": {
    "hf-dsv4": {
      "name": "DeepSeek V4 Flash 0731 (HF public)",
      "baseUrl": "https://q5dh1rfszfym23hj.us-east-2.aws.endpoints.huggingface.cloud/v1",
      "api": "openai-completions",
      "apiKey": "not-needed",
      "compat": {
        "supportsReasoningEffort": true,
        "maxTokensField": "max_tokens",
        "thinkingFormat": "deepseek",
        "requiresReasoningContentOnAssistantMessages": true
      },
      "models": [{
        "id": "deepseek-ai/DeepSeek-V4-Flash-0731",
        "name": "DeepSeek V4 Flash 0731",
        "reasoning": true,
        "thinkingLevelMap": {
          "off": null,
          "minimal": "low",
          "low": "low",
          "medium": "high",
          "high": "high",
          "xhigh": "max",
          "max": "max"
        },
        "input": ["text"],
        "contextWindow": 393216,
        "maxTokens": 393216,
        "cost": {"input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0}
      }]
    }
  }
}

Then run it — no restart needed, pi picks up models.json on launch:

Terminal — zsh
# interactive, thinking level "high"
pi --provider hf-dsv4 --model deepseek-ai/DeepSeek-V4-Flash-0731 --thinking high

# one-shot, non-interactive
pi -p --no-session --provider hf-dsv4 \
  --model deepseek-ai/DeepSeek-V4-Flash-0731 --thinking max \
  "Summarize how DSpark speculative decoding works."

# add it to your Ctrl+P model cycle alongside others
pi --models "hf-dsv4/*,sonnet,haiku"

Same shape works for any OpenAI‑compatible server — swap baseUrl for a local vllm serve or llama.cpp instance and keep the rest.

About This Hardware

Powered by Hugging Face Inference Endpoints

This whole thing — 4×H200, vLLM, autoscaling, the works — is one deploy form on Inference Endpoints: dedicated, production-grade deployments of any model on the Hub.

Pick a model, pick your hardware (CPU to multi-GPU H200), and get an OpenAI-compatible URL with autoscaling, scale-to-zero, and per-minute billing. No shared queues, no rate limits from strangers — your model, your GPUs.

5 windows · deepseek-ai/DeepSeek-V4-Flash-0731