Multimodal embedding model mapping text, images, video, audio, and PDFs into a unified embedding space
Context
8K
8,192 tokens
Max output
1
1 tokens
Input
$0.20
per 1M tokens
Output
Free
per 1M tokens
Providers
5
5 listings
Intelligence
—
Not yet scored
Pricing
USD per 1M tokens · listed by Google
| Token type | Standard |
|---|---|
| Input | $0.20 |
| Output | Free |
| Audio input | $6.50 |
Lowest input price across providers: $0.20.
Capabilities
ReasoningNo
Tool callNo
Structured outputNo
TemperatureNo
AttachmentsYes
Interleaved reasoningNo
Open weightsNo
ModeratedUnknown
Input
TextImageAudioVideoPDF
Output
Text
Benchmarks
Published scores and Design Arena Elo
No published benchmark scores for this model yet.
Rankings
Position on each OneAtlas leaderboard
Providers · 5
5 listings
| Provider | Model ID | Context | Input limit | Output | Input $ | Output $ | Reasoning $ | Cache read | Cache write | Audio in | Audio out | Reasoning | Tools | Structured | Temp. | Updated |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Google | gemini-embedding-2 | 8K | — | 1 | $0.20 | Free | — | — | — | $6.50 | — | No | No | Unknown | No | Apr 22, 2026 |
 Merge Gateway | google/gemini-embedding-2 | 8K | — | 8K | $0.20 | Free | — | — | — | — | — | No | No | No | No | Apr 22, 2026 |
| SAP AI Core | gemini-embedding-2 | 8K | — | 3K | — | — | — | — | — | — | — | No | No | Unknown | No | Apr 22, 2026 |
 Tempr Gateway | google/gemini-embedding-2 | 8K | — | 1 | $0.20 | Free | — | — | — | — | — | No | No | Unknown | No | Apr 22, 2026 |
 Vercel AI Gateway | google/gemini-embedding-2 | 8K | — | 3K | — | — | — | — | — | — | — | No | No | Unknown | No | Apr 22, 2026 |