# Gemini 3.8 Flash Gemini 3.8 Flash is a Google reasoning model designed for software engineering, extended agent tasks, and business workflows. It builds on Gemini 3.7 Flash with stronger reasoning across tasks that require multiple steps. Its published context window is 1,048,576 tokens. The advertised input rate is $0.75 per million input tokens. The advertised output rate is $3.75 per million output tokens. - Model identifier: ` google/gemini-3.8-flash ` - Creator: Google - Model type: Text generation - Canonical model page: [Gemini 3.8 Flash]() - API availability: Listed as serving through Impossibl. - Creator release date: 2026-09-02 ## Capabilities and limits - Context window: 1,048,576 tokens - Maximum output tokens: Not published in the public catalog; this is separate from the context window. - Inputs: text, image, audio, video - Outputs: text - Tool calling: Not published ## API access Use ` google/gemini-3.8-flash ` as the model identifier through the Impossibl API. Published API endpoints: - ` /v1/chat/completions ` [API quickstart]() · [Models and billing documentation]() ## Published API prices All rates are in USD. An unpublished rate is unknown, not zero. Workspace-specific pricing, taxes, balance-purchase fees, billing adjustments, and tool charges can affect the amount paid. | Usage | Published base rate | Billing unit | | --- | --- | --- | | Input | $0.75 | per million input tokens | | Output | $3.75 | per million output tokens | | Cache read | $0.075 | per million cached input tokens | | Cache write (default retention) | Not published | per million tokens | | Cache write (one-hour retention) | Not published | per million tokens | | Audio input | Not published | per million audio input tokens | ## Independent benchmarks Source: [Artificial Analysis](). Last checked: 2026-09-11T11:21:18.106Z. Configurations are evaluated separately. API scores retain their original units. Unmeasured scores are omitted. ### Gemini 3.8 Flash (high) Source: [Evaluation source]() | Benchmark | Score | | --- | --- | | Intelligence Index | 41.19 | | Omniscience Index | 29.55 | | GPQA | 95.25% | | Humanity’s Last Exam | 47.82% | | SciCode | 56.60% | | CritPt | 18.29% | | Terminal-Bench v2.1 | 87.64% | | Terminal-Bench v4.0 | 19.70% | | AA-LCR | 81.33% | | Multilingual LCR | 21.67% | | GDPval Elo | 1463.81 | | GDP.pdf All-pass | 21.00% | | AutomationBench Partial | 59.93% | | MMMU-Pro | 85.61% | | Tau Banking | 44.95% | | coding index (API) | 76.3 | | agentic index (API) | 41.1 | | intelligence index (API) | 41.2 | ### Gemini 3.8 Flash (low) Source: [Evaluation source]() | Benchmark | Score | | --- | --- | | Intelligence Index | 33.79 | | Omniscience Index | 21.35 | | GPQA | 92.02% | | Humanity’s Last Exam | 37.07% | | SciCode | 54.98% | | CritPt | 4.00% | | Terminal-Bench v2.1 | 83.15% | | Terminal-Bench v4.0 | 10.10% | | AA-LCR | 80.67% | | GDPval Elo | 1358.55 | | GDP.pdf All-pass | 18.60% | | AutomationBench Partial | 36.51% | | MMMU-Pro | 84.51% | | Tau Banking | 33.20% | | coding index (API) | 73.5 | | agentic index (API) | 33.7 | | intelligence index (API) | 33.8 | ### Gemini 3.8 Flash (medium) Source: [Evaluation source]() | Benchmark | Score | | --- | --- | | Intelligence Index | 40.00 | | Omniscience Index | 28.58 | | GPQA | 93.54% | | Humanity’s Last Exam | 42.12% | | SciCode | 55.09% | | CritPt | 12.29% | | Terminal-Bench v2.1 | 83.90% | | Terminal-Bench v4.0 | 19.70% | | AA-LCR | 84.00% | | GDPval Elo | 1455.38 | | GDP.pdf All-pass | 22.80% | | AutomationBench Partial | 60.89% | | MMMU-Pro | 84.22% | | Tau Banking | 45.77% | | coding index (API) | 74.1 | | agentic index (API) | 40.5 | | intelligence index (API) | 40 | Full benchmark data and breakdowns: [Complete benchmark snapshot](). ## Availability and retirement The model is listed as serving. No retirement is announced in the current public catalog. ## Frequently asked questions ### What is Gemini 3.8 Flash? Gemini 3.8 Flash is a Google reasoning model designed for software engineering, extended agent tasks, and business workflows. It builds on Gemini 3.7 Flash with stronger reasoning across tasks that require multiple steps. Sources: [Gemini 3.8 Flash model documentation](); [Gemini 3.8 Flash release announcement]() ### How much does Gemini 3.8 Flash cost? Gemini 3.8 Flash costs $0.75 per million input tokens and $3.75 per million output tokens through the Impossibl API. Cache reads cost $0.075 per million tokens. All rates are in USD. ### What is the context length of Gemini 3.8 Flash? Gemini 3.8 Flash has a 1,048,576-token context window through the Impossibl API. ### What inputs and outputs does Gemini 3.8 Flash support? Gemini 3.8 Flash accepts text, image, audio, and video as input. Gemini 3.8 Flash returns text. ### How do I use Gemini 3.8 Flash through an API? Gemini 3.8 Flash is available through the Impossibl API. Use google/gemini-3.8-flash as the model identifier with /v1/chat/completions. The quickstart explains how to create an API key and send your first request. ### When was Gemini 3.8 Flash released? Google released Gemini 3.8 Flash on September 2, 2026. Sources: [Creator release announcement]() ## Sources and related links Prices, limits, capabilities, endpoints, and availability come from the public Impossibl catalog. Creator documentation supplies descriptions and release dates where available; it does not override the published API offering. - [Public Impossibl model catalog]() - [Full model directory as JSON]() - [Gemini 3.8 Flash: model details and pricing]() - [Model directory]() - [Gemini 3.8 Flash model documentation]() - [Gemini 3.8 Flash release announcement]()