Running DeepSeek R1 via Together AI: Fastest Hosted Reasoning Model API
Together AI hosts DeepSeek R1 671B on serverless infrastructure with streaming thinking tokens, OpenAI-compatible SDK, and sub-5-second TTFT - at $3/1M input tokens with no cold starts.
DeepSeek offers its own API for R1 at $0.55/1M input tokens - cheaper than Together AI's $3/1M. But there are practical reasons to prefer Together:
Reliability - DeepSeek's API has experienced outages and rate limiting during peak demand. Together AI runs on dedicated US-based infrastructure with SLA guarantees.
Latency - Together AI has lower TTFT for US-based users (no cross-Pacific routing)
Compliance - data processed via Together AI stays in the US, relevant for regulated industries
No geoblocking - some enterprise networks block Chinese IP ranges
For teams where $3 vs $0.55 per million tokens is a meaningful budget concern, running R1 through DeepSeek direct or self-hosting makes sense. For most product teams, the reliability premium is worth it.
Setting Up Together AI
from together import Together
client = Together(api_key=os.environ["TOGETHER_API_KEY"])
response = client.chat.completions.create(
model="deepseek-ai/DeepSeek-R1",
messages=[
{
"role": "user",
"content": "Solve this step by step: If 5 workers can build a wall in 8 days, how many days would 10 workers take to build 3 such walls?",
}
],
stream=True,
)
for chunk in response:
if chunk.choices[0].delta.content:
print(chunk.choices[0].delta.content, end="", flush=True)
Team workspace
Ship faster with chat, meetings, and projects in one place — Zlyqor.
DeepSeek R1's "thinking" process - where it reasons through a problem before giving a final answer - can be streamed in real time. This allows you to show users a "thinking..." indicator while the model works, then display the final answer:
thinking_buffer = []
answer_buffer = []
in_thinking = False
for chunk in client.chat.completions.create(
model="deepseek-ai/DeepSeek-R1",
messages=[{"role": "user", "content": "Prove that the square root of 2 is irrational."}],
stream=True,
):
content = chunk.choices[0].delta.content or ""
if "<think>" in content:
in_thinking = True
elif "</think>" in content:
in_thinking = False
elif in_thinking:
thinking_buffer.append(content)
print(f"[thinking] {content}", end="", flush=True)
else:
answer_buffer.append(content)
print(content, end="", flush=True)
print("\n\nFinal answer:", "".join(answer_buffer))
Parallel Requests for Batch Processing
Together AI's serverless infrastructure handles parallel requests without rate limiting degradation. For batch reasoning tasks:
Together AI also hosts the distilled R1 variants, which are much smaller but retain much of the reasoning quality:
Model
Size
Cost (input)
vs R1 671B
DeepSeek-R1
671B
$3.00/1M
Baseline
DeepSeek-R1-Distill-Llama-70B
70B
$0.88/1M
~90% quality
DeepSeek-R1-Distill-Qwen-32B
32B
$0.27/1M
~85% quality
DeepSeek-R1-Distill-Qwen-7B
7B
$0.20/1M
~75% quality
For most math and coding reasoning tasks, the 70B distill performs within 10% of the full 671B model at less than one-third the price. Start with the 70B distill and only escalate to the full model for problems that require it.
Practical deep-dives on LLMs, developer tools, and AI engineering. No filler. Unsubscribe any time.
// written byFIG. AUTH-01
538
Mahmudul Haque Qudrati
CEO & ML Engineer
CEO and ML Engineer at Pristren. Builds AI-powered software for teams and writes about machine learning, LLMs, developer tools, and practical AI applications.
What Is Alibaba Banning Claude Code Over Backdoor Risks? A Practical Overview
Alibaba is reportedly banning Claude Code from its workplace due to alleged backdoor risks. This post explains the incident, the technical concerns, and the broader implications for AI coding assistants in regulated environments.
