deepseek/deepseek-chat-v3.1
32,768 context · $0.15/M input tokens · $0.75/M output tokens
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...
Pricing
Pay-per-use
No upfront costs, pay only for what you use
API Usage
Use the following code examples to integrate with our API:
from openai import OpenAI
client = OpenAI(
api_key="YOUR_API_KEY",
base_url="https://llm.wavespeed.ai/v1"
)
response = client.chat.completions.create(
model="deepseek/deepseek-chat-v3.1",
messages=[
{"role": "user", "content": "Hello!"}
]
)
print(response.choices[0].message.content)Model Introduction
Deepseek deepseek-chat-v3.1
deepseek deepseek-chat-v3.1
Why It Looks Great
- Large Language Model architecture for efficient processing
- 32768 context window for long document handling
- Competitive pricing at $0.2/$0.8 per million tokens
Key Features
- Context Window: 32768 tokens
- Max Output: 7168 tokens
- Vision: Supported
- Function Calling: Supported
Specifications
| Specification | Value |
|---|---|
| Provider | Deepseek |
| Model Type | Large Language Model (LLM) |
| Architecture | N/A |
| Context Window | 32768 tokens |
| Max Output | 7168 tokens |
| Input | Text |
| Output | Text |
| Vision | Supported |
| Function Calling | Supported |
Pricing
| Token Type | Cost per Million Tokens |
|---|---|
| Input | $0.2 |
| Output | $0.8 |
How to Use
- Write your prompt — describe the task, provide context, and specify desired output format.
- Submit — the model processes your request and returns the response.
API Integration
Base URL: https://llm.wavespeed.ai/v1 API Endpoint: chat/completions Model ID: deepseek/deepseek-chat-v3.1
API Usage
Python SDK
from openai import OpenAI
client = OpenAI(
api_key="YOUR_API_KEY",
base_url="https://llm.wavespeed.ai/v1"
)
response = client.chat.completions.create(
model="deepseek/deepseek-chat-v3.1",
messages=[
{"role": "user", "content": "Hello!"}
]
)
print(response.choices[0].message.content)cURL
curl https://llm.wavespeed.ai/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer YOUR_API_KEY" \
-d '{
"model": "deepseek/deepseek-chat-v3.1",
"messages": [{"role": "user", "content": "Hello!"}]
}'Notes
- Model: deepseek/deepseek-chat-v3.1
- Provider: Deepseek
Info
Supported Functionality
API Access Guide
DeepSeek Chat V3.1 API
deepseek/deepseek-chat-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...
Input
$0.15 /M
Output
$0.75 /M
Context
33K
Max Output
7K
Tool Use
Supported
Try DeepSeek Chat V3.1 on WaveSpeedAI
Access DeepSeek Chat V3.1 through our unified API — OpenAI-compatible, no cold starts, transparent pricing.
Open PlaygroundFrequently Asked Questions about DeepSeek Chat V3.1
How much does DeepSeek Chat V3.1 cost via the API?+
Pricing on WaveSpeedAI: $0.15 per million input tokens and $0.75 per million output tokens. Prompt caching and batch processing are billed separately and reduce effective cost on long, repetitive workloads.
What is the context window of DeepSeek Chat V3.1?+
DeepSeek Chat V3.1 supports up to 33K tokens of context with up to 7K tokens of output per request.
Is DeepSeek Chat V3.1 OpenAI-compatible?+
Yes. WaveSpeedAI exposes DeepSeek Chat V3.1 through an OpenAI-compatible endpoint at https://llm.wavespeed.ai/v1. Point the official OpenAI SDK at this base URL with your WaveSpeedAI API key — no other code changes required.
How do I get started with DeepSeek Chat V3.1?+
Sign in to WaveSpeedAI, create an API key in Access Keys, then send a request to https://llm.wavespeed.ai/v1/chat/completions with model id set to the value shown above. New accounts receive free credits to evaluate DeepSeek Chat V3.1 before paying per token.