Calculate the cost of using pplx-embed-v1-4b from Perplexity for your AI applications
Pricing data last updated:
Mode: Embedding
Max: 32,768 tokens
Built for enterprise-grade reliability, governance, and scale. Deploy in seconds.
pplx-embed-v1-4b is an embedding model from Perplexity, one of 2 embedding models they offer. It is priced at $0.03 per 1M input tokens and $0.0000 per 1M output tokens, ranking 43 out of 150 embedding models by cost and cheaper than 71% of models in this category. Its 33K-token context window is in the top 16% among embedding models.
Note: Use the interactive calculator above to estimate costs for your specific usage patterns.
Use the maximum token limits shown above to understand the model's capacity. This model can handle up to 32,768 input tokens.
At $0.03 per 1M input tokens and $0.0000 per 1M output tokens, pplx-embed-v1-4b ranks 43 out of 150 embedding models by input cost. It is more affordable compared to the median of $0.10 for embedding models, and is cheaper than 71% of models in this category.
pplx-embed-v1-4b is one of 2 Perplexity embedding models, its 33K-token context window places it in the top 16% of embedding models.
| Model | Provider | Input / 1M tokens | Output / 1M tokens | vs pplx-embed-v1-4b |
|---|---|---|---|---|
| amazon.titan-embed-text-v2:0 | AWS Bedrock | $0.02 | $0.0000 | -20% |
| text-embedding-005 | Vercel Ai Gateway | $0.02 | $0.0000 | -17% |
| text-multilingual-embedding-002 | Vercel Ai Gateway | $0.02 | $0.0000 | -17% |
Similar embedding models from other providers
No. pplx-embed-v1-4b costs $0.03 per 1M input tokens while amazon.titan-embed-text-v2:0 costs $0.02 per 1M input tokens, making amazon.titan-embed-text-v2:0 20% more affordable for input. However, pplx-embed-v1-4b may offer different capabilities or performance characteristics that justify the price difference.
pplx-embed-v1-4b input pricing is $0.03 per 1M tokens, which is 70% below the median of $0.10 for embedding models. It ranks 43 out of 150 embedding models by input cost, making it cheaper than 71% of models in this category. For output, it costs $0.0000 per 1M tokens compared to the median of $0.02.
Among Perplexity's 2 embedding models, pplx-embed-v1-4b ranks 1 by input cost.
The most comparable embedding models to pplx-embed-v1-4b are: amazon.titan-embed-text-v2:0 from AWS Bedrock ($0.02/1M input tokens); text-embedding-005 from Vercel Ai Gateway ($0.02/1M input tokens); text-multilingual-embedding-002 from Vercel Ai Gateway ($0.02/1M input tokens); pplx-embed-v1-4b from OpenRouter ($0.03/1M input tokens). These alternatives were selected based on similar capabilities, pricing, and provider diversity. You can compare any of these models in detail using the Bifrost Model Library.
pplx-embed-v1-4b supports up to 32,768 input tokens, placing it in the top 16% of embedding models by context window size (rank 14 of 133). This makes it suitable for processing long documents, extensive code repositories, or maintaining detailed conversation histories.
You can monitor Perplexity service health in real time on the Bifrost Perplexity Status page. It tracks current component status, active incidents, and historical reliability data pulled from the official status page every 60 seconds.
pplx-embed-v1-4b is priced based on input and output tokens. Use the interactive calculator at the top of this page to estimate costs for your specific workload. Enter your expected input and output tokens volume and the calculator will show the total cost breakdown. For reference, processing 1M input tokens costs $0.03 and generating 1M output tokens costs $0.0000.