deepseekavailablesupports_native_streamingsupports_prompt_cachingsupports_reasoningsupports_response_schemasupports_system_messages

Back to Model Explorer

DeepSeekAvailable on AvalAI

deepseek-reasoner API on AvalAI

deepseek-reasoner

deepseek-reasoner is an AI model from DeepSeek that is available through AvalAI's OpenAI-compatible API.

Open dashboardCompare

Price display scale

Input price$0.28 / 1M tokens

Output price$0.42 / 1M tokens

Context window131,072 tokens

Maximum output65,536 tokens

Use deepseek-reasoner with the AvalAI API

Keep the API key in an environment variable and send requests from server-side code.

Bash

curl https://api.avalai.ir/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $AVALAI_API_KEY" \
  -d '{"model": "deepseek-reasoner", "messages": [{"role": "user", "content": "Give a concise, practical solution."}]}'

Python

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["AVALAI_API_KEY"],
    base_url="https://api.avalai.ir/v1",
)

response = client.chat.completions.create(
    model="deepseek-reasoner",
    messages=[{"role": "user", "content": "Give a concise, practical solution."}],
)

print(response.choices[0].message.content)

JavaScript

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.AVALAI_API_KEY,
  baseURL: "https://api.avalai.ir/v1",
});

const response = await client.chat.completions.create({
  model: "deepseek-reasoner",
  messages: [{ role: "user", content: "Give a concise, practical solution." }],
});

console.log(response.choices[0].message.content);

Create an API keyRead the quickstart

Capabilities and endpoints

• Streaming
• Prompt caching
• Reasoning
• Structured output
• System messages

Endpoints

• /v1/chat/completions

deepseek-reasoner rate limits

Tier	RPM	TPM
Basic	3	40,000
Tier 1	250	500,000
Tier 2	500	3,000,000
Tier 3	1,500	4,000,000
Tier 4	2,500	8,000,000
Tier 5	5,000	15,000,000

Related models

• DeepSeek V4 Pro 0423
• DeepSeek V4 Flash 0423
• deepseek-v3.2-speciale
• DeepSeek V3.2

Frequently asked questions

What is the deepseek-reasoner API on AvalAI?

Create an AvalAI API key and send the model ID deepseek-reasoner to one of the supported endpoints shown on this page.

How much does the deepseek-reasoner API cost on AvalAI?

The deepseek-reasoner API on AvalAI costs $0.28 per 1M input tokens and $0.42 per 1M output tokens.

What is the token cost for deepseek-reasoner?

Current AvalAI pricing for deepseek-reasoner is $0.28 / 1M tokens for input and $0.42 / 1M tokens for output.

What is the deepseek-reasoner context window?

The recorded maximum input context for deepseek-reasoner is 131,072 tokens.

What are the rate limits for deepseek-reasoner on AvalAI?

On tier 5, deepseek-reasoner on AvalAI supports up to 5,000 requests per minute and 15,000,000 tokens per minute.

What features does deepseek-reasoner support on AvalAI?

deepseek-reasoner on AvalAI supports Streaming, Prompt caching, Reasoning, Structured output, System messages.

What account tier is required to use deepseek-reasoner on AvalAI?

Calling deepseek-reasoner on AvalAI requires the Basic tier (tier 0) or higher.

Third-party data and freshness

• Pricing, availability, endpoints, and rate limits: AvalAI structured data (authoritative)