deepseekavailablesupports_function_callingsupports_native_streamingsupports_parallel_function_callingsupports_prompt_cachingsupports_response_schemasupports_system_messagessupports_tool_choice

Back to Model Explorer

DeepSeekAvailable on AvalAI

DeepSeek V3 API on AvalAI

deepseek-chat

DeepSeek V3 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 output8,192 tokens

Release date2024-12-26

Knowledge cutoff2024-07-31

Use DeepSeek V3 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-chat", "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-chat",
    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-chat",
  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

• Function calling
• Streaming
• Parallel function calling
• Prompt caching
• Structured output
• System messages
• Tool choice

Endpoints

• /v1/chat/completions

Third-party model parameters

Third-party reference data does not change AvalAI endpoint support; use the capabilities and endpoints above.

• frequency_penalty
• logit_bias
• max_tokens
• min_p
• presence_penalty
• repetition_penalty
• response_format
• seed
• stop
• structured_outputs
• temperature
• tool_choice
• tools
• top_k
• top_p

DeepSeek V3 rate limits

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

AvalAI and reference marketplace pricing

Token role	AvalAI final price0% platform fee	OpenRouter cost breakdown
		Model rate	Credit purchase fee	Effective OpenRouter cost after fee
Input price	$0.28 / 1M tokens	$0.26 / 1M tokens	5.5%	$0.27 / 1M tokens
Output price	$0.42 / 1M tokens	$1.03 / 1M tokens	5.5%	$1.09 / 1M tokens

AvalAI pricing is final with a 0% platform fee. The effective OpenRouter prices add its 5.5% credit purchase fee to the highest reported model rate, including long-context tiers. OpenRouter charges a 5.5% fee when credits are purchased ($0.80 minimum), so small credit purchases can have a higher effective cost. OpenRouter FAQ

Third-party model data

Source: OpenRouter

Independent sources supplement this context; AvalAI remains authoritative for pricing, availability, and endpoint support.

Reviewed snapshot 2026-07-31 · This snapshot was checked more than 14 days ago.

Provider count

—

Context window range

163,840

Maximum output range

16,000

OpenRouter model input rate range

$0.2574 / 1M

OpenRouter model output rate range

$1.0287 / 1M

OpenRouter fee

5.5% credit purchase fee · OpenRouter fee details

Effective input price range after fee

$0.2716 / 1M

Effective output price range after fee

$1.0853 / 1M

Related models

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

Frequently asked questions

What is the DeepSeek V3 API on AvalAI?

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

How much does the DeepSeek V3 API cost on AvalAI?

The DeepSeek V3 API on AvalAI costs $0.28 per 1M input tokens and $0.42 per 1M output tokens.

What is the token cost for DeepSeek V3?

Current AvalAI pricing for DeepSeek V3 is $0.28 / 1M tokens for input and $0.42 / 1M tokens for output.

What is the DeepSeek V3 context window?

The recorded maximum input context for DeepSeek V3 is 131,072 tokens.

What are the rate limits for DeepSeek V3 on AvalAI?

On tier 5, DeepSeek V3 on AvalAI supports up to 5,000 requests per minute and 15,000,000 tokens per minute.

What features does DeepSeek V3 support on AvalAI?

DeepSeek V3 on AvalAI supports Function calling, Streaming, Parallel function calling, Prompt caching, Structured output, System messages, Tool choice.

What account tier is required to use DeepSeek V3 on AvalAI?

Calling DeepSeek V3 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)
• OpenRouter marketplace · Last checked: 2026-07-31