Lowest listed unit cost
OpenAI text-embedding-3-small$0.02 input and $0 output per 1M tokens.
Compare embedding API prices for OpenAI, Cohere, Voyage AI, Jina AI, Google, and Mistral.
| Provider / model | Estimated monthly cost | Unit price | Context | Rate limit | Signal |
|---|
| Provider / model | Status | Reason |
|---|
$0.02 input and $0 output per 1M tokens.
$0.02 input and $0 output per 1M tokens.
$0.025 input and $0 output per 1M tokens.
| Provider | Model | Category | Pricing | Context | Capabilities |
|---|---|---|---|---|---|
| OpenAI | text-embedding-3-small | embedding | $0.02 input / $0 output | 8,191 | batch api |
| Google Gemini | text-embedding-004 | embedding | $0.025 input / $0 output | 2,048 | batch api |
| Mistral AI | Mistral Embed | embedding | $0.1 input / $0 output | 8,192 | batch api |
| Cohere | Embed English v3 | embedding | $0.1 input / $0 output | 512 | batch api |
| Voyage AI | Voyage 3 | embedding | $0.06 input / $0 output | 32,000 | batch api |
| Jina AI | Jina Embeddings v3 | embedding | $0.02 input / $0 output | 8,192 | batch api |
Prices can change and rate limits are often account-tier specific. Use this calculator for planning, then confirm final numbers on the official provider pages before committing budget.
For token APIs, monthly cost is input tokens times input price plus output tokens times output price. For TTS, it uses monthly characters. Vector database estimates depend more heavily on storage and read/write usage.
The calculator excludes models that do not satisfy required context window, requests per minute, streaming, JSON mode, or tool calling constraints.
No. The dataset is designed for comparison and should be checked against official pricing pages before production decisions.