Primary use stated or inferred cautiously from official documentation.
G
GOOGLE / gemini-3.8-flash
Gemini 3.8 Flash
Flash model for long-running software engineering, autonomous agents, and complex business flows.
01 / SUMMARY
The essential
Maximum input capacity when published by the source.
Documented maximum generation limit.
Verified availability channels.
Primary functional family and verified specialties.
Declared terms for API access, model weights, or self-hosting.
02 / TECHNICAL SHEET
Limits and integration
| API ID | gemini-3.8-flash |
|---|---|
| Model type | Text and reasoning |
| Access model | Paid proprietary |
| License | Proprietary |
| Deployment | Hosted API |
| Release | September 2, 2026 |
| Knowledge cutoff | Not published in the source consulted |
| Entrance | Text · Image · Video · Audio · PDF |
| Exit | Text |
| Context window | 1,048,576 entry tokens |
| maximum output | 65,536 output tokens |
| Reasoning | low, medium, and high levels |
| Published tools | Features · Web search · Google Maps · Code execution · Computer use (preview) · File search · URL context |
| Structured Outings | Supported |
| Batch processing | Compatible · 50% discount |
| Prompt cache | Supported |
| Fine-tuning | Not published in the source consulted |
| Verified platforms | Gemini API · Google AI Studio |
Low-cost agents, long-running software, and broad multimodal analysis.
The price is introductory, and using grounding may incur per-query charges.
03 / CAPABILITIES
What it can do
Freelance agents
Planning and orchestrating tools into multi-step objectives.
Code
Aimed at extensive software engineering and extensive refactorings.
Multimodality
Supports text, image, video, audio and PDF as input.
Adjustable reasoning
It offers low, medium and high levels to adjust the effort.
Input modalities
TextImageVideoAudioPDF
04 / PRICES
Documented cost
| Concept | Worth | Unit/condition |
|---|---|---|
| Standard input | 0.75 USD / 1M tokens | Standard API rate |
| Cached input | 0.075 USD / 1 M tokens | Reading reused prefixes |
| Cache write or storage | 0.50 USD / 1 M tokens per hour of storage | The condition varies by provider |
| Standard output | 3.75 USD / 1M tokens | May include reasoning tokens |
| Batch input | 0.375 USD / 1 M tokens | Asynchronous processing |
| Batch output | 1.875 USD / 1 M tokens | Asynchronous processing |
Introductory pricing until December 31, 2026; from 2027, standard rates double.
i Prices change and may depend on level, region or context length. Check the source before making a decision.
05 / EVALUATIONS
How to read the results
“
Google describes it as its smartest Flash model for code and agents. Prices shown are introductory until December 31, 2026.
| Benchmark | Result | Metric | Source |
|---|---|---|---|
| Artificial Analysis Intelligence v4.1 | 50,2 | Index | View source ↗ |
| GDPval-AA v2 | 1.348,8 | Elo | View source ↗ |
Inferama only highlights a “best result” when the metric, test set, configuration, and date allow for an equivalent comparison. The supplier's figures are presented as claims from its own source.
06 / VERSIONS
Chronology
Gemini 3.8 Flash
General availability and stable version.
Gemini 3.7 Flash
Previous version for code and agents.
Gemini 3.6 Flash
First stable version of the series 3.6.
ANALYSIS
Related analysis
Gemini 3.8 Flash: What We Know About Agents, Access, Pricing, and Safety
Google positions Gemini 3.8 Flash for long-horizon software engineering and autonomous agents. That stated focus does not, by itself, show that the model can reliably complete extended tasks. This review separates the provider’s claims from documented access and Agent Platform pricing conditions, and identifies evidence that is missing from the sources reviewed.
30 Sep 2026 ↗
Artificial Analysis Intelligence v4.1: How to Read a Composite Index Without Confusing Methodology with Capability
Artificial Analysis Intelligence v4.1 brings heterogeneous evaluations together in a single number. That number can support shortlisting, but it is interpretable only when the exact version, per-test breakdown, and execution conditions are retained. This guide explains what changed in v4.1, which comparisons withstand scrutiny, and why average cost, time, and tokens-per-task metrics are not the same as a budget for your own workload.
22 Sep 2026 ↗
Contracts for AI Applications: Detecting Model, SDK, or Tool Changes Before Production
A response that appears correct may still violate the format, authorization, provenance, or business rule that supports an AI workflow. This guide explains how to turn those assumptions into verifiable contracts and use them to block regressions before production.
19 Sep 2026 ↗
Gemini 3.8 Flash reaches stable release: what changes and what remains unproven
Google has marked Gemini 3.8 Flash as stable in its API. Its documentation positions it for long-horizon software engineering, autonomous agents, and complex enterprise workflows. The specification confirms a large context window, multimodal input, and tool integration, but it does not provide independent evidence that the model outperforms alternatives on real projects.
02 Sep 2026 ↗07 / SOURCES