20
Models Available
$0.000
Cheapest Input / 1M
200K
Largest Context
What is Perplexity?
Perplexity is an AI model provider offering 20 large language models for developers. Their cheapest model starts at $0.000 per 1M input tokens, and their largest context window reaches 200K. Perplexity provides 20 AI models accessible via API.
Perplexity Strengths
All Perplexity Models
| Model | Input $/1M | Output $/1M | Context | Max Output | Released |
|---|---|---|---|---|---|
| Pplx 70b Online | $0.000 | $2.80 | 4K | 4,096 | — |
| Pplx 7b Online | $0.000 | $0.28 | 4K | 4,096 | — |
| Sonar Medium Online | $0.000 | $1.80 | 12K | 12,000 | — |
| Sonar Small Online | $0.000 | $0.28 | 12K | 12,000 | — |
| Mistral 7b Instruct | $0.070 | $0.28 | 4K | 4,096 | — |
| Mixtral 8x7b Instruct | $0.070 | $0.28 | 4K | 4,096 | — |
| Pplx 7b Chat | $0.070 | $0.28 | 8K | 8,192 | — |
| Sonar Small Chat | $0.070 | $0.28 | 16K | 16,384 | — |
| Llama 3.1 8b Instruct | $0.20 | $0.20 | 131K | 131,072 | — |
| Codellama 34b Instruct | $0.35 | $1.40 | 16K | 16,384 | — |
| Sonar Medium Chat | $0.60 | $1.80 | 16K | 16,384 | — |
| Codellama 70b Instruct | $0.70 | $2.80 | 16K | 16,384 | — |
| Llama 2 70b Chat | $0.70 | $2.80 | 4K | 4,096 | — |
| Pplx 70b Chat | $0.70 | $2.80 | 4K | 4,096 | — |
| Llama 3.1 70b Instruct | $1.00 | $1.00 | 131K | 131,072 | — |
| Sonar | $1.00 | $1.00 | 128K | 128,000 | — |
| Sonar Reasoning | $1.00 | $5.00 | 128K | 128,000 | — |
| Sonar Deep Research | $2.00 | $8.00 | 128K | 128,000 | — |
| Sonar Reasoning Pro | $2.00 | $8.00 | 128K | 128,000 | — |
| Sonar Pro | $3.00 | $15.00 | 200K | 8,000 | — |
Model Details
Pplx 70b Online
Pplx 70b Online is available via Perplexity with a 4K context window and up to 4,096 output tokens. Pricing: $0.000000/1M input tokens, $2.80/1M output tokens.
Pplx 7b Online
Pplx 7b Online is available via Perplexity with a 4K context window and up to 4,096 output tokens. Pricing: $0.000000/1M input tokens, $0.2800/1M output tokens.
Sonar Medium Online
Sonar Medium Online is available via Perplexity with a 12K context window and up to 12,000 output tokens. Pricing: $0.000000/1M input tokens, $1.80/1M output tokens.
Sonar Small Online
Sonar Small Online is available via Perplexity with a 12K context window and up to 12,000 output tokens. Pricing: $0.000000/1M input tokens, $0.2800/1M output tokens.
Mistral 7b Instruct
Mistral 7b Instruct is available via Perplexity with a 4K context window and up to 4,096 output tokens. Pricing: $0.0700/1M input tokens, $0.2800/1M output tokens.
Mixtral 8x7b Instruct
Mixtral 8x7b Instruct is available via Perplexity with a 4K context window and up to 4,096 output tokens. Pricing: $0.0700/1M input tokens, $0.2800/1M output tokens.
Pplx 7b Chat
Pplx 7b Chat is available via Perplexity with a 8K context window and up to 8,192 output tokens. Pricing: $0.0700/1M input tokens, $0.2800/1M output tokens.
Sonar Small Chat
Sonar Small Chat is available via Perplexity with a 16K context window and up to 16,384 output tokens. Pricing: $0.0700/1M input tokens, $0.2800/1M output tokens.
Llama 3.1 8b Instruct
Llama 3.1 8b Instruct is available via Perplexity with a 131K context window and up to 131,072 output tokens. Pricing: $0.2000/1M input tokens, $0.2000/1M output tokens.
Codellama 34b Instruct
Codellama 34b Instruct is available via Perplexity with a 16K context window and up to 16,384 output tokens. Pricing: $0.3500/1M input tokens, $1.40/1M output tokens.
Sonar Medium Chat
Sonar Medium Chat is available via Perplexity with a 16K context window and up to 16,384 output tokens. Pricing: $0.6000/1M input tokens, $1.80/1M output tokens.
Codellama 70b Instruct
Codellama 70b Instruct is available via Perplexity with a 16K context window and up to 16,384 output tokens. Pricing: $0.7000/1M input tokens, $2.80/1M output tokens.
Llama 2 70b Chat
Llama 2 70b Chat is available via Perplexity with a 4K context window and up to 4,096 output tokens. Pricing: $0.7000/1M input tokens, $2.80/1M output tokens.
Pplx 70b Chat
Pplx 70b Chat is available via Perplexity with a 4K context window and up to 4,096 output tokens. Pricing: $0.7000/1M input tokens, $2.80/1M output tokens.
Llama 3.1 70b Instruct
Llama 3.1 70b Instruct is available via Perplexity with a 131K context window and up to 131,072 output tokens. Pricing: $1.00/1M input tokens, $1.00/1M output tokens.
Sonar
Sonar is available via Perplexity with a 128K context window and up to 128,000 output tokens. Pricing: $1.00/1M input tokens, $1.00/1M output tokens.
Sonar Reasoning
Sonar Reasoning is available via Perplexity with a 128K context window and up to 128,000 output tokens. Pricing: $1.00/1M input tokens, $5.00/1M output tokens.
Sonar Deep Research
Sonar Deep Research is available via Perplexity with a 128K context window and up to 128,000 output tokens. Pricing: $2.00/1M input tokens, $8.00/1M output tokens.
Sonar Reasoning Pro
Sonar Reasoning Pro is available via Perplexity with a 128K context window and up to 128,000 output tokens. Pricing: $2.00/1M input tokens, $8.00/1M output tokens.
Sonar Pro
Sonar Pro is available via Perplexity with a 200K context window and up to 8,000 output tokens. Pricing: $3.00/1M input tokens, $15.00/1M output tokens.
Compare Perplexity model pricing
Use our pricing calculator to find the cheapest Perplexity model for your workload.