Cheapest Embedding API Models
As of October 21, 2026, the cheapest of LiteLLM's active paid embedding models is PPLX Embed V1 0.6B, at $0.004 per 1M tokens (input), from Perplexity.
Top 20
Sorted by input price at each model's headline price. Active embedding models only; free models are left out.
| # | Model | Lab | Price per 1M input tokens | Price per 1M (in / out) | Context | Providers | Price from |
|---|---|---|---|---|---|---|---|
| 1 | PPLX Embed V1 0.6B | – | $0.004 | $0.004 / – | 32K | 1 | Perplexity |
| 2 | Text Embedding Preview | – | $0.00625 | $0.00625 / – | 3K | 1 | Google Vertex AI |
| 3 | BGE Base En V1.5 | – | $0.008 | $0.008 / – | 512 | 1 | Together AI |
| 4 | GTE Base | – | $0.008 | $0.008 / – | 512 | 1 | Fireworks AI |
| 5 | Nomic Embed Text V1 | – | $0.008 | $0.008 / – | 8K | 1 | Fireworks AI |
| 6 | Nomic Embed Text V1.5 | – | $0.008 | $0.008 / – | 8K | 1 | Fireworks AI |
| 7 | PPLX Embed Context V1 0.6B | – | $0.008 | $0.008 / – | 32K | 1 | Perplexity |
| 8 | BGE En Icl | – | $0.01 | $0.01 / – | 32K | 1 | Nebius AI Studio |
| 9 | BGE M3 | – | $0.01 | $0.01 / – | 8K | 2 | LibertAI |
| 10 | BGE Multilingual Gemma2 | – | $0.01 | $0.01 / – | 8K | 2 | Nebius AI Studio |
| 11 | E5 Mistral 7B Instruct | – | $0.01 | $0.01 / – | 32K | 1 | Nebius AI Studio |
| 12 | Qwen3 Embedding 8B | Alibaba | $0.01 | $0.01 / – | 40K | 5 | Nebius AI Studio |
| 13 | GTE Large | – | $0.016 | $0.016 / – | 512 | 1 | Fireworks AI |
| 14 | Uae Large V1 | – | $0.016 | $0.016 / – | 512 | 1 | Fireworks AI |
| 15 | Nomic Embed Text | – | $0.02 | $0.02 / – | 8K | 1 | LlamaGate |
| 16 | Text Embedding 3 Small | OpenAI | $0.02 | $0.02 / – | 8K | 4 | OpenAI |
| 17 | Titan Embed Text V2 | Amazon | $0.02 | $0.02 / – | 8K | 2 | Amazon Bedrock |
| 18 | Voyage 3 Lite | Voyage AI | $0.02 | $0.02 / – | 32K | 1 | Voyage AI |
| 19 | Voyage 3.5 Lite | Voyage AI | $0.02 | $0.02 / – | 32K | 1 | Voyage AI |
| 20 | Voyage 4 Lite | Voyage AI | $0.02 | $0.02 / – | 32K | 1 | Voyage AI |