Gemini 3.8 Flash
| Provider | Price | Provider model ID | Status | Context / max output | Source |
|---|---|---|---|---|---|
| Google Gemini API | Batch Input $0.375USD / 1M tokensOutput $1.875USD / 1M tokens Google Gemini API · BatchInput: $0.375 Output: $1.875 Input: $0.375 through December 31, 2026. $0.75 starting January 1, 2027. Output: $1.875 through December 31, 2026. $3.75 starting January 1, 2027.. Cache, grounding and storage billed separately. Checked 2026-10-03T15:45:22.224Z Price source ↗Flex Input $0.375USD / 1M tokensOutput $1.875USD / 1M tokens Google Gemini API · FlexInput: $0.375 Output: $1.875 Input: $0.375 through December 31, 2026. $0.75 starting January 1, 2027. Output: $1.875 through December 31, 2026. $3.75 starting January 1, 2027.. Cache, grounding and storage billed separately. Checked 2026-10-03T15:45:22.224Z Price source ↗Standard Input $0.75USD / 1M tokensOutput $3.75USD / 1M tokens Google Gemini API · StandardInput: $0.75 Output: $3.75 Input: $0.75 through December 31, 2026. $1.50 starting January 1, 2027. Output: $3.75 through December 31, 2026. $7.50 starting January 1, 2027.. Cache, grounding and storage billed separately. Checked 2026-10-03T15:45:22.224Z Price source ↗Priority Tariff not listedInput $1.35USD / 1M tokensOutput $6.75USD / 1M tokens Google Gemini API · PriorityInput: $1.35 Output: $6.75 Input: $1.35 through December 31, 2026. $2.70 starting January 1, 2027. Output: $6.75 through December 31, 2026. $13.50 starting January 1, 2027.. Cache, grounding and storage billed separately. Checked 2026-10-03T15:45:22.224Z Price source ↗ | gemini-3.8-flash | Catalog-listedConditionsCatalog-listed; account access and regional availability may apply. | Not supplied | Official source ↗2026-09-28 |
 Google Cloud Vertex AI | Global / <=200K input Input $0.75USD / 1M tokensOutput $3.75USD / 1M tokens Google Cloud Vertex AI · Global / <=200K inputInput: $0.75 Cache Read: $0.075 Output: $3.75 Gemini 3.8 Flash* through December 31, 2026. Regional prices and long-context thresholds are retained from the source. Checked 2026-10-03T15:45:22.224Z Price source ↗Global / >200K input Input $0.75USD / 1M tokensOutput $3.75USD / 1M tokens Google Cloud Vertex AI · Global / >200K inputInput: $0.75 Cache Read: $0.075 Output: $3.75 Gemini 3.8 Flash* through December 31, 2026. Regional prices and long-context thresholds are retained from the source. Checked 2026-10-03T15:45:22.224Z Price source ↗Non-global / <=200K input Input $0.825USD / 1M tokensOutput $4.125USD / 1M tokens Google Cloud Vertex AI · Non-global / <=200K inputInput: $0.825 Cache Read: $0.0825 Output: $4.125 Gemini 3.8 Flash* through December 31, 2026. Regional prices and long-context thresholds are retained from the source. Checked 2026-10-03T15:45:22.224Z Price source ↗Non-global / >200K input Tariff not listedInput $0.825USD / 1M tokensOutput $4.125USD / 1M tokens Google Cloud Vertex AI · Non-global / >200K inputInput: $0.825 Cache Read: $0.0825 Output: $4.125 Gemini 3.8 Flash* through December 31, 2026. Regional prices and long-context thresholds are retained from the source. Checked 2026-10-03T15:45:22.224Z Price source ↗ | gemini-3.8-flash | Catalog-listedConditionsCatalog-listed; account access and regional availability may apply. | Not supplied | Official source ↗2026-09-28 |
 OpenRouter | Router catalog Tariff not listedInput $0.75USD / 1M tokensOutput $3.75USD / 1M tokens OpenRouter · Router catalogInput: $0.75 Output: $3.75 Cache Read: $0.075 Cache Write: $0.0416666666666667 Image Input: $0.00000075 Web Search: $0.014 Audio Input: $0.00000075 OpenRouter route catalog price, not a direct-provider price. Routing, modality and endpoint conditions can change the actual bill. Checked 2026-10-03T15:45:22.224Z Price source ↗ | google/gemini-3.8-flash | Catalog-listedConditionsCatalog-listed; account access and regional availability may apply. | Context tokens 1048576Output tokens 65536 | Official source ↗2026-09-28 |
Gemini 3.8 Flash accepts text, image, video, audio, PDF and produces text. Tool calling and structured outputs are available on supported routes.
Specifications
- Catalog model ID
- google/gemini-3.8-flash
- Developer model ID / revision
- gemini-3.8-flashDeveloper documentation ↗
- Input modalities
- text, image, video, audio, PDFDeveloper documentation ↗
- Output modalities
- textDeveloper documentation ↗
- Context / input token limit
- 1,048,576Developer documentation ↗
- Maximum output tokens
- 65,536Developer documentation ↗
- Tool calling
- SupportedDeveloper documentation ↗
- Structured output
- SupportedDeveloper documentation ↗
- API parameters (source-specific)
- include_reasoning, max_tokens, reasoning, reasoning_effort, response_format, seed, stop, structured_outputs, temperature, tool_choice, tools, top_pOpenRouter catalog ↗
- API parameter scope
- OpenRouter API; support varies by route
- Weight access
- Proprietary / hosted APIDeveloper documentation ↗
- Weight license / access terms
- Proprietary — API accessDeveloper documentation ↗
- Total parameters (billions)
- Not publicly disclosed
- Active parameters (billions)
- Not publicly disclosed
- Download size (GB)
- Not applicable — no public weights
- Release date
- Not verified in cited sources
- Added to OpenRouter
- 2026-09-02OpenRouter catalog ↗
- Notes
- API parameter names are reported by OpenRouter and do not describe the developer’s native API. Token limits labeled OpenRouter are route catalog limits, not universal model limits. Media limits on this page describe the linked provider endpoint; other deployments may differ.
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.