Gemini 3.8 Live
| Provider | Price | Provider model ID | Status | Media deployment details | Source |
|---|---|---|---|---|---|
| Not collectedAwaiting verified pricing | gemini-3.8-live | Catalog-listedConditionsCatalog-listed; account access and regional availability may apply. | Not supplied | Official source ↗2026-09-28 |
Gemini 3.8 Live accepts text, image, audio, video and produces audio, text (transcription). Deployment limits and API options depend on the selected provider.
Specifications
- Catalog model ID
- google/gemini-3.8-live
- Developer model ID / revision
- gemini-3.8-liveDeveloper documentation ↗
- Input modalities
- text, image, audio, videoDeveloper documentation ↗
- Output modalities
- audio, text (transcription)Developer documentation ↗
- Context / input token limit
- 131,072Developer documentation ↗
- Maximum output tokens
- 65,536Developer documentation ↗
- Tool calling
- SupportedDeveloper documentation ↗
- Structured output
- Not supportedDeveloper documentation ↗
- Weight access
- Proprietary / hosted APIDeveloper documentation ↗
- Weight license / access terms
- Proprietary — API accessDeveloper documentation ↗
- Total parameters (billions)
- Not publicly disclosed
- Download size (GB)
- Not applicable — no public weights
- Release date
- Not verified in cited sources
- Notes
- The Live API response modality is audio. Enable output audio transcription to receive a text transcript. thinking_level is not supported on this model.
Catalog entries link to their specification and availability sources. This is a curated selection, not every model each provider offers. Best prices are the lowest collected USD tariffs, not a total-cost estimate. Token offers are selected by input price, with output from the same tariff; workload mix may change the cheapest provider. Listed variants may require batch processing, off-peak hours, or specific media settings. Price coverage varies by provider; collected tariffs include their source and observation time. Benchmark scores are a dated snapshot, not a live feed or a universal measure of quality. They apply to the shown evaluation configuration; listed prices may use different settings. Models without verified scores are not assumed to be weaker.