deepseek/deepseek-reasoner

deepseek/deepseek-reasoner
JSON
by deepseek

DeepSeek alias for V4 Flash thinking mode — 1M context, open chain-of-thought reasoning (legacy alias, slated for deprecation).

ctx1M tokens
Max output384K
Inputtext
p50 TTFT897 ms
INPUT$0.15/ 1M tokens
OUTPUT$0.29/ 1M tokens
p50 TTFT897 ms7d
p95 TTFT1.92 s7d
TRAFFIC12.7Mtokens / 7d

DeepSeek Reasoner is a text-only reasoning model from DeepSeek, optimized for tasks that require deep logical deduction and extended context understanding. It is accessible through OrcaRouter's…

What is DeepSeek Reasoner?

Who should use this model?

How does it handle long contexts?

What makes it a 'reasoner' model?

Code samples

Call from any SDK

OpenAI-compatible — keep the SDK you already use

  • OpenAI SDKhttps://api.orcarouter.ai/v1
import os

from openai import OpenAI

client = OpenAI(
    base_url="https://api.orcarouter.ai/v1",
    api_key=os.environ["ORCAROUTER_API_KEY"],
)

response = client.chat.completions.create(
    model="deepseek/deepseek-reasoner",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Supported parameters

  • max_tokens
  • response_format
  • stream

Pricing

Input / 1M tokens · Off-peak$0.147
Output / 1M tokens · Off-peak$0.295
Cache read / 1M · Off-peak$0.028
Peak hours01:00–04:00, 06:00–10:00 ×2 (UTC)
Input / 1M tokens · ×2$0.294
Output / 1M tokens · ×2$0.590
Cache read / 1M · ×2$0.056
CurrencyUSD

Cost calculator

Tokens / month10MM
Input share70%%
Estimated / month $1.91 · With prompt caching $1.50

Estimate based on list price

Token & cost estimator

Input tokens: 20Cost per request: $0.000150

Estimate only — actual token counts depend on the provider's tokenizer.

Performance

p50 TTFT
897 ms
Output speed
114 tok/s
p95 TTFT
1.92 s
Error rate
1.8%

Public benchmarks

Source: Design Arena

Community buzz

What developers are saying this week

Hacker News1 mentions · 7dup 1 vs the previous week

How it compares

deepseek/deepseek-reasonerDeepSeek V4 ProDeepSeek V4 FlashDeepSeek V4 Flash Vision (Exp)
Input $/M$0.15$0.44$0.15$0.15
Output $/M$0.29$0.88$0.29$0.29
Context1.0M1.0M1.0M1.0M
Quality5/108/107/107/10
Compare side-by-sideCompare side-by-sideCompare side-by-sideCompare side-by-side

FAQ

What is the cost to run DeepSeek Reasoner on OrcaRouter?
The cost is $0.44 per 1M input tokens and $0.87 per 1M output tokens. OrcaRouter charges zero markup, so you pay exactly the provider rate. There are no additional fees.
What is the context window size?
The context window is 1,048,576 tokens (approximately 750,000 words). The model can also output up to 384,000 tokens per request.
What are the main strengths of DeepSeek Reasoner?
Its main strengths are the extremely large context and output limits, combined with a focus on step-by-step reasoning. It excels at math, code, and analysis tasks that require logical chain-of-thought and long document processing.
How does it compare to GPT-4?
DeepSeek Reasoner has a larger context and output capacity at a lower cost per token. GPT-4 supports multimodal input and may have broader knowledge, but DeepSeek Reasoner is more cost-effective for long-context reasoning tasks.
Does it support image or audio input?
No. DeepSeek Reasoner accepts only text input. It does not process images, audio, or video.
How do I call DeepSeek Reasoner via an OpenAI-compatible API?
Use the base URL https://api.orcarouter.ai/v1 and set the model to "deepseek/deepseek-reasoner". All standard OpenAI chat completion parameters are supported. Include your OrcaRouter API key in the Authorization header.
Can I use streaming with this model?
Yes. The API supports streaming via the 'stream' parameter. Set stream=true to receive tokens incrementally, following the same format as OpenAI's streaming.
Is the model suitable for real-time applications?
Due to its large context window and reasoning depth, latency for the first token may be higher than smaller models. It is better suited for batch or asynchronous tasks than real-time, low-latency applications.

Embed this badge

deepseek/deepseek-reasoner$0.15/M in897ms p50via OrcaRouter
HTML <a href="https://www.orcarouter.ai/models/deepseek/deepseek-reasoner" target="_blank"> <img src="https://www.orcarouter.ai/embed/deepseek/deepseek-reasoner.svg" alt="deepseek/deepseek-reasoner on OrcaRouter" /> </a>
Markdown [![deepseek/deepseek-reasoner](https://www.orcarouter.ai/embed/deepseek/deepseek-reasoner.svg)](https://www.orcarouter.ai/models/deepseek/deepseek-reasoner)

Model card as data

GET /api/public/models/deepseek/deepseek-reasonerOpen
Machine-readable:/llms.txt/llms-full.txt