Multimodal Embedding
Multimodal Embedding is Google's embedding model with a 2K context window, starting at $0.800 / 1M input. A multimodal embedding model that encodes both text and images into a shared vector space for cross-modal retrieval and similarity tasks.
Capabilities
Input1/5
Text✓
Image·
Audio·
Video·
PDF·
Output1/5
Text·
Image·
Audio·
Video·
Embedding✓
Capabilities0/13
Reasoning·
Adaptive Reasoning·
Function Calling·
Parallel Function Calling·
Structured Outputs·
Native JSON Schema·
Web Search·
URL Context·
Computer Use·
Code Execution·
File Search·
Prompt Caching·
Assistant Prefill·
Pricing by Provider
| Provider | Standard |
|---|---|
| Input $ / 1M | |
 Google Vertex AI | $0.800 |
Cost Calculator
Preset:
Versions
| Version | Released | Context | Input / 1M | Output / 1M | Status |
|---|---|---|---|---|---|
| Text Embedding 5 | 2K | $0.025 | — | Available | |
| Embed 4 | 128K | $0.120 | $0.470 | Available | |
| Embed 4 Img | — | — | $0.470 | — | Available |
| Embed 4 Txt | — | — | $0.120 | — | Available |
| Text Embedding 4 | — | 2K | $0.100 | — | Deprecated |
| Voyage 4 | — | 32K | $0.060 | — | Available |
| Voyage 4 Large | — | 32K | $0.120 | — | Available |
| Voyage 4 Lite | — | 32K | $0.020 | — | Available |
| Voyage 3.5 | 32K | $0.060 | — | Available | |
| Voyage 3.5 Lite | 32K | $0.020 | — | Available | |
| Multimodal Embedding | — | 2K | $0.800 | — | Current |