DeepSeek-V3.1 API

DeepSeek-V3.1 is the latest advanced LLM with improved architecture and performance across various natural language tasks.

Modalities: Text, ImageText
In / Out price: $0.6877/$1.8per 1M
Context window: 125K tokens
Released: Aug 28, 2025

DeepSeek-V3.1 overview

DeepSeek-V3.1 by DeepSeek

DeepSeek V3.1 is a high-efficiency hybrid AI model optimized for fast, direct responses without deep reasoning, supporting extensive multimodal inputs and large context windows.

DeepSeek-V3.1 specs

Model ID: deepseek/deepseek-chat-v3.1
Developer: DeepSeek
Context window: 128,000 tokens
Max output: 8,000 tokens
Input: Text, Image
Output: Text
API: OpenAI-compatible, base URL https://api.aimlapi.com/v1

What Is DeepSeek-V3.1?

DeepSeek-V3.1 is a next-generation hybrid language model built by DeepSeek AI. It runs on a Mixture-of-Experts (MoE) transformer architecture, which means it routes each inference request through a small, relevant subset of its parameters, keeping latency low and compute costs lean without sacrificing output quality.

The Chat variant specifically operates in non-thinking mode. Rather than working through multi-step reasoning chains, it returns direct, high-quality answers with minimal overhead. That design choice makes DeepSeek-V3.1 a natural fit for applications where speed is a first-class requirement: customer-facing chatbots, CI/CD code automation pipelines, real-time data extraction, and any agentic system calling external tools in a tight loop.

Native Tool & Agent Calling

First-class support for structured function calls, code agents, and search agents. Build complex agentic pipelines without bolting on workarounds.

Mixture-of-Experts Efficiency

MoE layers activate only the parameters relevant to each token. The result: competitive performance at a significantly lower compute footprint than dense alternatives.

100+ Language Multilinguality

Extended multilingual training means you can serve global users from a single model deployment without separate fine-tuning per language.

Technical Specifications

Every parameter below is relevant to planning your integration. Understanding them upfront helps you size context windows correctly, avoid truncation surprises, and choose the right sampling settings for your use case.

Architecture: Hybrid MoE Transformer, FP8 microscaling
Context Window:128,000 tokens (input)
Max Output: 8,000 tokens per completion
Reasoning Mode: Non-thinking (direct response)
Tool Calls: Structured function calling
Agent Support: Code agents, search agents
Languages: 100+ with high contextual accuracy
Input Modalities: Text, images (multimodal)

Where DeepSeek-V3.1 Delivers

The model's non-thinking, high-speed profile makes it particularly strong in scenarios where fast, accurate, and contextually aware output matters more than deep step-by-step deliberation.

Use cases

Fast software engineering assistance including code synthesis and debugging.
Multimodal chatbots focusing on image and text understanding with prompt responses.
Routine research and document analysis with moderate context requirements.
Efficient multi-turn dialogue suited for basic task-oriented educational tools.
Business intelligence processes emphasizing rapid visual data interpretation.
Agentic applications requiring intelligent tool calls without deep reasoning overhead.

Capabilities

Function calling
Streaming
Structured outputs
Reasoning

DeepSeek-V3.1 benchmarks by Artificial Analysis

See how DeepSeek-V3.1 compares in generation speed and latency. Data retrieved Nov 3, 2026.

Speed#90 / 219121Output tokens / second Latency#173 / 2162.92Seconds to first token Humanity's Last Exam#171 / 45814.3%Score GPQA Diamond#152 / 43977.9%Score

Speed

Output tokens / second

Benchmark results

Compare 15 models available on AI/ML API across 5 independent benchmarks.

Humanity's Last Exam

Expert-written questions across academic subjects.

DeepSeek-V3.1 API pricing

DeepSeek-V3.1 pricing in US dollars
Usage	Price	Unit
Input	$0.6877	1M tokens
Output	$1.8	1M tokens
Cached input	$0.5819	1M tokens

Prices from the AI/ML API price list, checked on Nov 4, 2026.

DeepSeek-V3.1 vs other models: token prices

AI/ML API input and output rates for 5 models, per million tokens.

AI/ML API model prices in USD per million tokens
Model	Input	Output
DeepSeek-V3.1	$0.6877	$1.8
DeepSeek Chat (V4.1 Flash)	$0.3	$1.2
DeepSeek V4.1 Flash	$0.3	$1.2
DeepSeek V4 Flash Vision Exp	$0.44	$1.32
DeepSeek V4.1 Flash 1017	$0.39	$1.56

How to use the DeepSeek-V3.1 API

View docs

Build with your agent

Give your agent the model details, code and documentation.

1Get your API key

Create API key

export AIMLAPI_KEY="8f2b4c7d9a1e6b3f…"

2Make your first request

curl 'https://api.aimlapi.com/v1/chat/completions' \
  -H "Authorization: Bearer $AIMLAPI_KEY" \
  -H 'Content-Type: application/json' \
  -d '{
  "model": "deepseek/deepseek-chat-v3.1",
  "messages": [
    {
      "role": "user",
      "content": "Write a haiku about the ocean."
    }
  ]
}'

import os
import requests

headers = {
    "Authorization": f"Bearer {os.environ['AIMLAPI_KEY']}",
    "Content-Type": "application/json",
}
payload = {
    "model": "deepseek/deepseek-chat-v3.1",
    "messages": [
        {
            "role": "user",
            "content": "Write a haiku about the ocean."
        }
    ]
}

response = requests.post("https://api.aimlapi.com/v1/chat/completions", headers=headers, json=payload, timeout=120)
response.raise_for_status()
print(response.json())

const response = await fetch("https://api.aimlapi.com/v1/chat/completions", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.AIMLAPI_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    "model": "deepseek/deepseek-chat-v3.1",
    "messages": [
      {
        "role": "user",
        "content": "Write a haiku about the ocean."
      }
    ]
  }),
});

if (!response.ok) throw new Error(`HTTP ${response.status}`);
console.log(await response.json());

All posts

DeepSeek-V3.1 FAQ

What is the context window of DeepSeek-V3.1?

DeepSeek-V3.1 has a 128,000 tokens context window and can return up to 8,000 tokens.

What inputs and outputs does DeepSeek-V3.1 support?

DeepSeek-V3.1 takes text as input and returns text.

What is the model ID for DeepSeek-V3.1?

Use deepseek/deepseek-chat-v3.1 as the model id. Requests go to https://api.aimlapi.com/v1/chat/completions.

When was DeepSeek-V3.1 released?

DeepSeek-V3.1 became available on August 28, 2025.

How much does DeepSeek-V3.1 cost?

DeepSeek-V3.1 costs $0.6877 input and $1.8 output per 1M tokens on AI/ML API, billed as you go with no subscription.

Does DeepSeek-V3.1 support streaming?

Yes, DeepSeek-V3.1 can stream responses as they are generated.

Who created DeepSeek-V3.1?

DeepSeek-V3.1 was built by DeepSeek.

Is DeepSeek-V3.1 a reasoning model?

Yes, its capabilities include reasoning alongside function calling and structured outputs.

Start building with DeepSeek-V3.1

Get API key

DeepSeek-V3.1 API

deepseek/deepseek-chat-v3.1

Build with your agent

Give your agent the model details, code and documentation.

1Get your API key

Create API key

export AIMLAPI_KEY="8f2b4c7d9a1e6b3f…"

2Make your first request

curl 'https://api.aimlapi.com/v1/chat/completions' \
  -H "Authorization: Bearer $AIMLAPI_KEY" \
  -H 'Content-Type: application/json' \
  -d '{
  "model": "deepseek/deepseek-chat-v3.1",
  "messages": [
    {
      "role": "user",
      "content": "Write a haiku about the ocean."
    }
  ]
}'

import os
import requests

headers = {
    "Authorization": f"Bearer {os.environ['AIMLAPI_KEY']}",
    "Content-Type": "application/json",
}
payload = {
    "model": "deepseek/deepseek-chat-v3.1",
    "messages": [
        {
            "role": "user",
            "content": "Write a haiku about the ocean."
        }
    ]
}

response = requests.post("https://api.aimlapi.com/v1/chat/completions", headers=headers, json=payload, timeout=120)
response.raise_for_status()
print(response.json())

const response = await fetch("https://api.aimlapi.com/v1/chat/completions", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.AIMLAPI_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    "model": "deepseek/deepseek-chat-v3.1",
    "messages": [
      {
        "role": "user",
        "content": "Write a haiku about the ocean."
      }
    ]
  }),
});

if (!response.ok) throw new Error(`HTTP ${response.status}`);
console.log(await response.json());

Docs for AI agents Plain-text index · llms.txt API documentation API reference and examples

Talk to our sales team

Thanks for reaching out

DeepSeek-V3.1 API

DeepSeek-V3.1 overview

DeepSeek-V3.1 by DeepSeek

DeepSeek-V3.1 specs

What Is DeepSeek-V3.1?

Native Tool & Agent Calling

Mixture-of-Experts Efficiency

100+ Language Multilinguality

Technical Specifications

Where DeepSeek-V3.1 Delivers

Use cases

Capabilities

DeepSeek-V3.1 benchmarks by Artificial Analysis

Speed

Benchmark results

Humanity's Last Exam

GPQA Diamond

AA-LCR

IFBench

τ²-Bench Telecom

DeepSeek-V3.1 API pricing

DeepSeek-V3.1 vs other models: token prices

How to use the DeepSeek-V3.1 API

Build with your agent

1Get your API key

2Make your first request

Related articles

DeepSeek-V3.1 FAQ

Start building with DeepSeek-V3.1

DeepSeek-V3.1 API

Build with your agent

1Get your API key

2Make your first request

DeepSeek-V3.1 API

DeepSeek-V3.1 overview

DeepSeek-V3.1 by DeepSeek

DeepSeek-V3.1 specs

What Is DeepSeek-V3.1?

Native Tool & Agent Calling

Mixture-of-Experts Efficiency

100+ Language Multilinguality

Technical Specifications

Where DeepSeek-V3.1 Delivers

Use cases

Capabilities

Speed

Benchmark results

Humanity's Last Exam

GPQA Diamond

AA-LCR

IFBench

τ²-Bench Telecom

DeepSeek-V3.1 API pricing

DeepSeek-V3.1 vs other models: token prices

How to use the DeepSeek-V3.1 API

Build with your agent

1Get your API key

2Make your first request

Models similar to DeepSeek-V3.1

DeepSeek Chat (V4.1 Flash)

DeepSeek V4.1 Flash

DeepSeek V4.1 Flash 1017

Gemma 2 (27b)

Glimpse

Nemotron 3 Ultra

Related articles

Best AI Models for Agentic Workflows and Tool Use in 2026

Best LLMs for Long-Context & Multimodal Tasks in 2026

DeepSeek-V3.1 FAQ

Start building with DeepSeek-V3.1