Back to Registry

Perplexity API Catalog

Comprehensive overview of all perplexity models available through the LLM Kit

Overview

Provider
perplexity
Total Models
24
Last Updated
2026-08-03

codellama-34b-instruct

Model ID codellama-34b-instruct
Family
codellama-34b-instruct

Specifications

Context Window: 16,384 tokens
Max Output Tokens: 16,384 tokens

Modalities

Input
text
Output
text

Pricing (per million tokens)

Text Tokens - Standard
Input
$0.35
Output
$1.4

codellama-70b-instruct

Model ID codellama-70b-instruct
Family
codellama-70b-instruct

Specifications

Context Window: 16,384 tokens
Max Output Tokens: 16,384 tokens

Modalities

Input
text
Output
text

Pricing (per million tokens)

Text Tokens - Standard
Input
$0.7
Output
$2.8

llama-2-70b-chat

Model ID llama-2-70b-chat
Family
llama-2-70b-chat

Specifications

Context Window: 4,096 tokens
Max Output Tokens: 4,096 tokens

Modalities

Input
text
Output
text

Pricing (per million tokens)

Text Tokens - Standard
Input
$0.7
Output
$2.8

llama-3.1-70b-instruct

Model ID llama-3.1-70b-instruct
Family
llama-3.1-70b-instruct

Specifications

Context Window: 131,072 tokens
Max Output Tokens: 131,072 tokens

Modalities

Input
text
Output
text

Pricing (per million tokens)

Text Tokens - Standard
Input
$1.0
Output
$1.0

llama-3.1-8b-instruct

Model ID llama-3.1-8b-instruct
Family
llama-3.1-8b-instruct

Specifications

Context Window: 131,072 tokens
Max Output Tokens: 131,072 tokens

Modalities

Input
text
Output
text

Pricing (per million tokens)

Text Tokens - Standard
Input
$0.19999999999999998
Output
$0.19999999999999998

llama-3.1-sonar-huge-128k-online

Model ID llama-3.1-sonar-huge-128k-online
Family
llama-3.1-sonar-huge-128k-online

Specifications

Context Window: 127,072 tokens
Max Output Tokens: 127,072 tokens

Modalities

Input
text
Output
text

Pricing (per million tokens)

Text Tokens - Standard
Input
$5.0
Output
$5.0

llama-3.1-sonar-large-128k-chat

Model ID llama-3.1-sonar-large-128k-chat
Family
llama-3.1-sonar-large-128k-chat

Specifications

Context Window: 131,072 tokens
Max Output Tokens: 131,072 tokens

Modalities

Input
text
Output
text

Pricing (per million tokens)

Text Tokens - Standard
Input
$1.0
Output
$1.0

llama-3.1-sonar-large-128k-online

Model ID llama-3.1-sonar-large-128k-online
Family
llama-3.1-sonar-large-128k-online

Specifications

Context Window: 127,072 tokens
Max Output Tokens: 127,072 tokens

Modalities

Input
text
Output
text

Pricing (per million tokens)

Text Tokens - Standard
Input
$1.0
Output
$1.0

llama-3.1-sonar-small-128k-chat

Model ID llama-3.1-sonar-small-128k-chat
Family
llama-3.1-sonar-small-128k-chat

Specifications

Context Window: 131,072 tokens
Max Output Tokens: 131,072 tokens

Modalities

Input
text
Output
text

Pricing (per million tokens)

Text Tokens - Standard
Input
$0.19999999999999998
Output
$0.19999999999999998

llama-3.1-sonar-small-128k-online

Model ID llama-3.1-sonar-small-128k-online
Family
llama-3.1-sonar-small-128k-online

Specifications

Context Window: 127,072 tokens
Max Output Tokens: 127,072 tokens

Modalities

Input
text
Output
text

Pricing (per million tokens)

Text Tokens - Standard
Input
$0.19999999999999998
Output
$0.19999999999999998

mistral-7b-instruct

Model ID mistral-7b-instruct
Family
mistral-7b-instruct

Specifications

Context Window: 4,096 tokens
Max Output Tokens: 4,096 tokens

Modalities

Input
text
Output
text

Pricing (per million tokens)

Text Tokens - Standard
Input
$0.07
Output
$0.28

mixtral-8x7b-instruct

Model ID mixtral-8x7b-instruct
Family
mixtral-8x7b-instruct

Specifications

Context Window: 4,096 tokens
Max Output Tokens: 4,096 tokens

Modalities

Input
text
Output
text

Pricing (per million tokens)

Text Tokens - Standard
Input
$0.07
Output
$0.28

pplx-70b-chat

Model ID pplx-70b-chat
Family
pplx-70b-chat

Specifications

Context Window: 4,096 tokens
Max Output Tokens: 4,096 tokens

Modalities

Input
text
Output
text

Pricing (per million tokens)

Text Tokens - Standard
Input
$0.7
Output
$2.8

pplx-70b-online

Model ID pplx-70b-online
Family
pplx-70b-online

Specifications

Context Window: 4,096 tokens
Max Output Tokens: 4,096 tokens

Modalities

Input
text
Output
text

Pricing (per million tokens)

Text Tokens - Standard
Input
$0.0
Output
$2.8

pplx-7b-chat

Model ID pplx-7b-chat
Family
pplx-7b-chat

Specifications

Context Window: 8,192 tokens
Max Output Tokens: 8,192 tokens

Modalities

Input
text
Output
text

Pricing (per million tokens)

Text Tokens - Standard
Input
$0.07
Output
$0.28

pplx-7b-online

Model ID pplx-7b-online
Family
pplx-7b-online

Specifications

Context Window: 4,096 tokens
Max Output Tokens: 4,096 tokens

Modalities

Input
text
Output
text

Pricing (per million tokens)

Text Tokens - Standard
Input
$0.0
Output
$0.28

sonar

Model ID sonar
Family
sonar

Specifications

Context Window: 128,000 tokens

Modalities

Input
text
Output
text

Capabilities

Structured output Prompt caching System messages

Pricing (per million tokens)

Text Tokens - Standard
Input
$0.25
Output
$2.5
Text Tokens - Cached
Output
$0.0625

sonar-deep-research

Model ID sonar-deep-research
Family
sonar-deep-research

Specifications

Context Window: 128,000 tokens
Max Output Tokens: 128,000 tokens

Modalities

Input
text
Output
text

Capabilities

Structured output System messages Json output

Pricing (per million tokens)

Text Tokens - Standard
Input
$2.0
Output
$8.0

sonar-medium-chat

Model ID sonar-medium-chat
Family
sonar-medium-chat

Specifications

Context Window: 16,384 tokens
Max Output Tokens: 16,384 tokens

Modalities

Input
text
Output
text

Pricing (per million tokens)

Text Tokens - Standard
Input
$0.6
Output
$1.7999999999999998

sonar-medium-online

Model ID sonar-medium-online
Family
sonar-medium-online

Specifications

Context Window: 12,000 tokens
Max Output Tokens: 12,000 tokens

Modalities

Input
text
Output
text

Pricing (per million tokens)

Text Tokens - Standard
Input
$0.0
Output
$1.7999999999999998

sonar-pro

Model ID sonar-pro
Family
sonar-pro

Specifications

Context Window: 200,000 tokens
Max Output Tokens: 128,000 tokens

Modalities

Input
text, image
Output
text

Capabilities

Structured output System messages

Pricing (per million tokens)

Text Tokens - Standard
Input
$3.0
Output
$15.0

sonar-pro-search

Model ID sonar-pro-search
Family
sonar-pro-search

Specifications

Context Window: 200,000 tokens
Max Output Tokens: 8,000 tokens

Modalities

Input
text
Output
text

Pricing (per million tokens)

Text Tokens - Standard

sonar-reasoning-pro

Model ID sonar-reasoning-pro
Family
sonar-reasoning-pro

Specifications

Context Window: 128,000 tokens

Modalities

Input
text, image
Output
text

Capabilities

Json output Structured output

Pricing (per million tokens)

Text Tokens - Standard
Input
$2.0
Output
$8.0

sonar-small-chat

Model ID sonar-small-chat
Family
sonar-small-chat

Specifications

Context Window: 16,384 tokens
Max Output Tokens: 16,384 tokens

Modalities

Input
text
Output
text

Pricing (per million tokens)

Text Tokens - Standard
Input
$0.07
Output
$0.28