The chemistry literature, down to the table.
Papers, compound data and patents in one API, with the values in tables and figures searchable alongside the text.
- Material
- Li₁₀GeP₂S₁₂
- Property
- Ionic conductivity
- Temperature
- 27 °C
- Source
- Kamaya et al., Nature Materials, 2011
Extraction
Turn a literature into a dataset.
Ask for a property across the literature and get each value back with its material, conditions and source.
| Material | σ (mS/cm) | Temp. | Source |
|---|---|---|---|
| Li₁₀GeP₂S₁₂ | 12 | 27 °C | Kamaya 2011 |
| Li₉.₅₄Si₁.₇₄P₁.₄₄S₁₁.₇Cl₀.₃ | 25 | 25 °C | Kato 2016 |
| Li₆PS₅Cl | < 10 | RT | Deiseroth 2008 |
2 of 3 materials at or above 10 mS/cmRun the extraction, then drag.
Patents
Papers and patents, in one record.
The same material often appears in a journal and a filing under different names. Search both at once.
Benchmarks
Proof on chemistry literature.
ScholarQA-Multi
Accuracy on scientific-literature synthesis across biology, chemistry and medicine.
Industries
Where teams use it.
Which cathode coatings report capacity retention above 90% after 500 cycles?
Which bio-based polyamides match PA66 on tensile strength?
Which single-atom catalysts report turnover frequencies for CO₂ reduction?
What dielectric constants are reported for hafnium-based high-k films?
FAQ
Questions from chemistry and materials teams.
Can it read tables and figures?
Which chemistry databases are covered?
Do you cover patents outside the US?
Enterprise on Valyu.
Private indexes on your firm's internal data, enterprise controls, and engineers who ship with you.
Talk to our team
SOC 2, Zero Data Retention, SSO with SAML or OIDC, scoped tenant isolation. US, EU, and UK deployment options, or dedicated in your VPC.
State-of-the-art retrieval on internal data: lab notebooks, internal reports, trial data, research archives. Agents run on your own research and every Valyu source, in one call.
When the API needs to go further, our engineers ship with you. Custom DeepResearch agents and vertical indexes tuned to your field.
Pick a property
Name a property. Get the dataset.
Every reported value across the literature, with its material, conditions and source, ready for your model.