DeepSeek: DeepSeek Reasoner

DeepSeek reasoning model for multi-step analysis, math, coding, and tools

Model lab: DeepSeek
Model family: deepseek-thinking

Model resources

Hugging Face

Modalitiestext → text

Context window1,000,000

Maximum output384,000

InputUSD 0.1176 / 1M tokens

OutputUSD 0.236 / 1M tokens

Try now

Quickstart

Use your Moduck API Key, set the API base URL to https://api.moduck.ai/v1, and set the model parameter to deepseek/deepseek-reasoner.

import os
import requests

base_url = "https://api.moduck.ai/v1"
api_key = os.environ["MODUCK_API_KEY"]
model_id = "deepseek/deepseek-reasoner"

response = requests.post(
    f"{base_url}/chat/completions",
    headers={
        "Authorization": f"Bearer {api_key}",
        "Content-Type": "application/json",
    },
    json={
        "model": model_id,
        "messages": [{"role": "user", "content": "Hello!"}],
        "stream": False,
    },
    timeout=60,
)
response.raise_for_status()
print(response.json())

Use the familiar OpenAI-style chat request format to make model integration easier.

DeepSeek Reasoner API Pricing

Type	Price information
Input	USD 0.1176 / 1M tokens
Output	USD 0.236 / 1M tokens
Cached input	USD 0.0224 / 1M tokens

Benchmarks

Benchmark	Score	Measurement	Source
Aider Polyglot	74.2	percent correct · Date: 2025-10-03

Performance

Performance trends

Throughput84.2 tok/sCurrent

Time to first token3.0 sCurrent

End-to-end latency7.5 sCurrent

Throughput

Current84.2 tok/s

Window average89.5 tok/s

Time to first token

Current3.0 s

Window average1.5 s

End-to-end latency

Current7.5 s

Window average7.5 s

Tail latency (P99)

Current16.7 s

Window average16.5 s

Prompt cache hit rate

Current18.2%

Window average24.6%

Error rate

Current0.0%

Window average0.2%

Availability

Uptime100%At least one provider responded

Availability100%Requests actually served

Error rate0%Share of failed requests

Served requests, hour by hour

24 hours agoNow

DeepSeek Reasoner Compare models

Model	Input price	Output price	Context window	Capabilities
DeepSeek ReasonerThis page	USD 0.1176 / 1M tokens	USD 0.236 / 1M tokens	1,000,000	Text output · Reasoning · Tool calling
DeepSeek V4 Pro 0813	USD 0.3536 / 1M tokens	USD 0.7072 / 1M tokens	1,000,000	Text output · Reasoning · Tool calling
DeepSeek V4 Pro	USD 0.34288 / 1M tokens	USD 0.68568 / 1M tokens	1,000,000	Text output · Reasoning · Tool calling
DeepSeek V4 Pro 0423	USD 1.32 / 1M tokens	USD 2.64 / 1M tokens	1,000,000	Text output · Reasoning · Tool calling
DeepSeek R1 0528 Qwen3 8B	USD 0.048 / 1M tokens · Context ≤ 128000 tokens · Maximum output 32000 tokens	USD 0.072 / 1M tokens · Context ≤ 128000 tokens · Maximum output 32000 tokens	131,072	Text output · Reasoning

Model specifications

Input: text
Output: text
Context window: 1,000,000
Maximum output: 384,000
Release date: 2025-12-01
Attachments: Yes
Reasoning: Yes
Tool calling: Yes
Temperature setting: Yes
Open weights: Yes

Frequently asked questions

What is DeepSeek Reasoner for?

DeepSeek reasoning model for multi-step analysis, math, coding, and tools

What inputs and outputs does DeepSeek Reasoner support?

Recorded inputs: text; outputs: text.

How is DeepSeek Reasoner priced?

The pricing table shows the current recorded Moduck price. For example: Input USD 0.1176 / 1M tokens; Output USD 0.236 / 1M tokens. See the pricing table for all units, variants, and conditions.

What specifications are recorded for DeepSeek Reasoner?

Current model records list Context window 1,000,000 tokens; Maximum output 384,000 tokens.

What model parameter does the Quickstart use?

The example uses deepseek/deepseek-reasoner. This value comes from the page identifier and is not confirmed as a callable Moduck public ID.

Can I call this model through the Moduck API now?

This page has no verified Moduck API call for this model. A Quickstart example or reserved ID does not establish access; check the models available to your account.