Specifications
Context window164K tokens
Max output—
API typechat
AddedAug 26, 2025
Model IDdeepinfra/deepseek-ai/DeepSeek-V3.1
Benchmarks
Benchmarks haven't been published yet for this exact variant.
Some variants (region-specific deployments, highspeed tiers) share benchmarks with their base model — check the base model page or the DeepInfra Inc. models overview.
Pricing
Input / 1M
$0.30
Output / 1M
$1.00
Cache write
—
Cache read
—
Estimated cost
100K input + 10K output$0.0400
1M input + 100K output$0.40
10M input + 1M output$4.00
Requesty charges exactly what the upstream provider charges — no markup, no per-request fees. Prompt caching and smart routing can reduce effective cost by 30-80%.
Quickstart
Drop-in compatible with the OpenAI SDK. Change the base URL, swap in your Requesty API key, and set the model to deepinfra/deepseek-ai/DeepSeek-V3.1.
123456789101112131415from openai import OpenAI client = OpenAI( api_key="YOUR_REQUESTY_API_KEY", base_url="https://router.requesty.ai/v1", ) response = client.chat.completions.create( model="deepinfra/deepseek-ai/DeepSeek-V3.1", messages=[ {"role": "user", "content": "Explain quantum computing in one paragraph."}, ], ) print(response.choices[0].message.content)
Other DeepInfra Inc. models
Frequently asked questions
How much does deepseek-ai/DeepSeek-V3.1 cost?
deepseek-ai/DeepSeek-V3.1 is priced at $0.30 per million input tokens and $1.00 per million output tokens when accessed via Requesty. Requesty charges exactly what the upstream provider charges — we don't add markup.
What is the context window of deepseek-ai/DeepSeek-V3.1?
deepseek-ai/DeepSeek-V3.1 has a context window of 164K tokens. That's roughly 218 words of input you can fit in a single prompt.
What can deepseek-ai/DeepSeek-V3.1 do?
deepseek-ai/DeepSeek-V3.1 supports tool calling. You can call it through any OpenAI-compatible client by pointing base_url to Requesty.
How do I use deepseek-ai/DeepSeek-V3.1 with the OpenAI SDK?
Install the OpenAI SDK, set base_url to "https://router.requesty.ai/v1", set your API key to your Requesty key, and set the model to "deepinfra/deepseek-ai/DeepSeek-V3.1". The Quickstart above shows Python, JavaScript and cURL snippets.
Access deepseek-ai/DeepSeek-V3.1 through Requesty
One API key, 400+ models, OpenAI-compatible. No markup on provider prices, automatic failover, and smart caching built-in.