Google · in Borg
Gemini 3.5 Flash
Gemini 3.5 Flash moves the Flash line toward sustained agentic work instead of simply answering isolated prompts.
Reasoning1,048,576 tokenstext, image, video, audio, pdf
Included in Borg
Download Borg Borg for BusinessAt a glance
| Specification | Value |
|---|---|
| Provider | |
| Family | Gemini |
| Release date | 2026-05-19 Vendor source |
| Context window | 1,048,576 tokens Vendor source |
| Input modalities | text, image, video, audio, pdf |
| Output modalities | text |
| Reasoning | Yes |
| Open weights | No |
| Borg lane ids | google/gemini-3.5-flash |
| Versions in Borg | Gemini 2.5 Flash · Gemini 3 Flash · Gemini 3.5 Flash · Gemini 3.6 Flash · Gemini 3.7 Flash · Gemini 3.8 Flash |
Not published by the vendor: thinking modes, knowledge cutoff, fusion roles.
What Gemini 3.5 Flash is good for
Gemini 3.5 Flash moves the Flash line toward sustained agentic work instead of simply answering isolated prompts. Built on the Gemini 3 Flash reasoning foundation, it targets iterative coding, subagent deployment and longer sequences of tool calls while retaining multimodal intake and adjustable thinking. It sits above the cheaper 3.5 Flash-Lite for harder work and precedes the newer 3.6 through 3.8 Flash revisions, which emphasize different efficiency and reliability gains. It reads text, audio, video, images and PDFs but produces text rather than pictures. Borg includes this model in the subscription; Borg Fusion can assign it coding or agent steps, or you can choose its lane directly to run repeated experiments with the same Flash version.
- iterative coding agents
- long-horizon subagent workflows
- multimodal investigation
How Borg uses it
Gemini 3.5 Flash is available as a subscription catalog lane in Borg. The catalog does not publish which Fusion profiles route to this model, so no routing role is claimed here. You can pick it directly by setting the OpenAI-compatible gateway model field to a listed lane id. Check the current catalog for availability before building a workflow around a lane.
model: "google/gemini-3.5-flash"Measured on Borg
Measured on Borg: SearchAtlas AI Gateway production request logs. 30-day window ending 2026-10-08; 0 requests. Minimum 100 samples per published request metric.
Completion speed covers the whole turn including queueing and reasoning time; it is not a streaming tokens-per-second figure.
No speed figures are available yet.
Benchmarks
Google-reported internal automated safety evaluations, relative to the comparator named below. These are changes in evaluation performance, not absolute capability scores or human red-team results. Google says updated evaluations are not directly comparable with results in earlier model cards. Vendor evaluation details
| Benchmark | Vendor-reported score | Source |
|---|---|---|
| Text-to-text safety vs Gemini 3 Flash | -3.9% | Vendor source |
| Multilingual safety vs Gemini 3 Flash | -2.6% | Vendor source |
| Tone vs Gemini 3 Flash | +8.9% | Vendor source |
Pricing
Included in Borg subscription. Vendor API list price: $1.5 input / $9 output per 1M tokens. Vendor price source.
Compare subscription and API pricing · Cost Savings Calculator
FAQ
What is Gemini 3.5 Flash?
Gemini 3.5 Flash is listed in Borg's subscription catalog as google/gemini-3.5-flash. Gemini 3.5 Flash moves the Flash line toward sustained agentic work instead of simply answering isolated prompts.
Is Gemini 3.5 Flash in Borg?
Yes. Gemini 3.5 Flash is listed in Borg's subscription catalog under the lane google/gemini-3.5-flash. You can choose the lane directly, or explore the available Fusion profiles. Availability and model details can change; check the current catalog before deployment.
What context window does Gemini 3.5 Flash have?
The published context window is 1,048,576 tokens. Consult the cited sources for details and current limits. Vendor source
Is Gemini 3.5 Flash good for coding?
Vendor-published evaluations appear in the benchmarks section; their settings may differ from your tasks. Its listed uses include iterative coding agents, long-horizon subagent workflows, multimodal investigation. Try the lane for your own tasks, and compare the output with your requirements before choosing a default.
How fast is Gemini 3.5 Flash on Borg?
No speed figures are available yet.
How much does Gemini 3.5 Flash cost on Borg vs the API?
This model is included in the Borg subscription. The vendor API list prices appear below with a source link. See the pricing explainer and cost savings calculator to compare billing approaches.