DeepSeek V3.1

About DeepSeek V3.1

DeepSeek-V3.1 is a large hybrid reasoning model (671B parameters, 37B active) that supports both thinking and non-thinking modes via prompt templates. It extends the DeepSeek-V3 base with a two-phase long-context training process, reaching up to 128K tokens, and uses FP8 microscaling for efficient inference. Users can control the reasoning behaviour with the `reasoning` `enabled` boolean. [Learn more in our docs](https://openrouter.ai/docs/use-cases/reasoning-tokens#enable-reasoning-with-default-config) The model improves tool use, code generation, and reasoning efficiency, achieving performance comparable to DeepSeek-R1 on difficult benchmarks while responding more quickly. It supports structured tool calling, code agents, and search agents, making it suitable for research, coding, and agentic workflows. It succeeds the [DeepSeek V3-0324](/deepseek/deepseek-chat-v3-0324) model and performs well on a variety of tasks.

Model Specifications

💰 Real-World Cost Examples

Estimated monthly costs for common use cases

DeepSeek Model Lineup

Compare all models from DeepSeek to find the best fit

Similar Models from Other Providers

Cross-brand alternatives with similar capabilities

Mistral Small 3.1 24B

Mistral

Input: $0.35

Output: $0.56

Context: 128k

Qwen3 Coder Next

Alibaba Qwen

Input: $0.12

Output: $0.80

Context: 262k

Qwen3 32B

Alibaba Qwen

Input: $0.29

Output: $0.59

Context: 131k

Qwen3 Next 80B A3B Thinking

Alibaba Qwen

Input: $0.10

Output: $0.78

Context: 262k

💡 Cheaper Alternatives

Same Brand (DeepSeek)

Cross Brand

🚀 Quick Start

Get started with DeepSeek V3.1 API

from openai import OpenAI

client = OpenAI(
    base_url="https://api.provider.com/v1",
    api_key="YOUR_API_KEY"
)

response = client.chat.completions.create(
    model="deepseek/deepseek-chat-v3.1",
    messages=[
        {"role": "user", "content": "Hello!"}
    ]
)
print(response.choices[0].message.content)

Continue Your Decision