Data points: 32
Model compare
The readout for Gemini Embedding 2 and Voyage 4 Large, before the detailed comparison sheet.
Weighted outcome: Gemini Embedding 2. Benchmark capability categories carry 80%, while price, API performance, and availability carry 20%.
Decision read
Gemini Embedding 2
Gemini Embedding 2 has the higher weighted result; Model A / B score 100 to 0.
Evidence depth
32 data points
Includes 0 benchmark rows, 0 audit samples, and 2 provider examples.
Selection signal
Start with Gemini Embedding 2
The charts below split 2 high-signal samples across speed, scores, and audit health.
Switch either side of this report to compare another model with the same LMSpeed data pipeline.
Select a different model to open a new comparison URL.
This report only uses LMSpeed data for Gemini Embedding 2 and Voyage 4 Large: pricing, speed aggregates, third-party benchmark scores, and shared provider samples.
| Model compare | Gemini Embedding 2 | Voyage 4 Large |
|---|---|---|
| Overall leader | Leading | Contender |
| Weighted overall score | 100.0 pts | 0.0 pts |
| Benchmark category leads | 0 categories | 0 categories |
| Operational advantages | Cheapest input price, Free providers, Provider coverage | No data |
| Context window | 8.2K tokens | 32K tokens |
| Max output | No data | No data |
| Modalities | Input TextImageFileAudiovideo Output |
The overall result weights benchmark capability categories at 80% and price, API speed/latency, and availability at 20%. Recent test volume does not affect the winner, and missing benchmark categories are excluded.
| Model compare | Gemini Embedding 2 | Voyage 4 Large |
|---|---|---|
| Developer | VoyageAI by MongoDB | |
| Released | May 2026 | Jul 2026 |
| Parameters | No data | No data |
| Tokenizer | Gemini | Other |
| Knowledge cutoff | No data | No data |
| OpenRouter ID | google/gemini-embedding-2 | voyageai/voyage-4-large |
| References | No data | No data |
This report only uses LMSpeed data for Gemini Embedding 2 and Voyage 4 Large: pricing, speed aggregates, third-party benchmark scores, and shared provider samples.
Gemini Embedding 2
Gemini Embedding 2 has these operational advantages: Cheapest input price, Free providers, Provider coverage.
Voyage 4 Large
Voyage 4 Large does not clearly lead in the benchmark or operational dimensions shared by both models.
Third-party benchmark profile synced into LMSpeed; only metrics available for both models are shown.
Metric-level scores with benchmark source, rank depth, confidence, error, and evaluation date where available.
No shared professional benchmark scores are available yet.
Latest completed audits from shared providers, with four safety and integrity score groups plus report links.
| Provider | Gemini Embedding 2 | Voyage 4 Large |
|---|---|---|
| No completed audits are available from shared providers yet. | ||
Speed aggregates and input/output pricing share each provider row for real API selection and migration cost checks.
| Provider | Gemini Embedding 2 | Voyage 4 Large |
|---|---|---|
0 tests | Gemini Embedding 2 gemini-embedding-2-preview speed / latency N/A / N/A input / output $40.00/M/$160.00/M | Voyage 4 Large voyage-4-large speed / latency N/A / N/A input / output $20.00/M/$20.00/M |
0 tests | Gemini Embedding 2 speed / latency N/A / N/A input / output No data | Voyage 4 Large speed / latency N/A / N/A input / output No data |
Weighted outcome: Gemini Embedding 2. Benchmark capability categories carry 80%, while price, API performance, and availability carry 20%.
Input Text Output embeddings |
| Features | Text inputImage inputFile inputAudio inputEmbeddings outputJSON mode | Text inputEmbeddings output |
|---|
