Gemini 3.1 Flash Lite (batch)
Google· released 7 May 2026
google/gemini-3.1-flash-lite:batch- Input / 1M tokens
- $0.125
- Output / 1M tokens
- $0.75
Longest answer: 66K tokens
About
Gemini 3.1 Flash Lite (batch) is a Google text model released on 2026-05-07. Its listed summary describes it as a high-efficiency multimodal model intended for low-latency, high-volume workloads, as well as lightweight agentic work. It accepts text, images, video, files, and audio, and has vision and tool support. Despite its text modality and text output, its input formats cover those additional media types. The context window is 1,048,576 tokens, and the maximum output is 65,536 tokens. Reasoning is supported. Its model ID is google/gemini-3.1-flash-lite:batch. Listed pricing is USD 0.125 per 1M input tokens and USD 0.75 per 1M output tokens. These details give teams evaluating batch use a clear basis for assessing media inputs, context size, output limits, and token costs for their workloads.
Who it is for
This model suits teams with high-volume or low-latency workloads that need multimodal inputs, tools, or lightweight agentic capabilities. Its large context window may also fit tasks that need to provide substantial input.
What is good
- Accepts text, image, video, file, and audio inputs.
- Context window is 1,048,576 tokens.
- Supports vision, reasoning, and tools.
- Input costs USD 0.125 per 1M tokens.
What to know first
- Maximum output is 65,536 tokens.
- Output costs USD 0.75 per 1M tokens.
Verdict
Gemini 3.1 Flash Lite (batch) pairs broad input support with a large context window and listed reasoning and tool capabilities. Check the output limit and token prices against the volume and format of your work.
Details
- Lab
- Googleopenrouter.ai · 3 Oct 2026
- Context
- 1,049Kopenrouter.ai · 3 Oct 2026
- Input price
- $0.125 / 1Mopenrouter.ai · 3 Oct 2026
- Output price
- $0.75 / 1Mopenrouter.ai · 3 Oct 2026
- Max output
- 65,536 tokensopenrouter.ai · 3 Oct 2026
- Inputs
- text, image, video, file, audioopenrouter.ai · 3 Oct 2026
- Open weights
- Noopenrouter.ai · 3 Oct 2026
More newest models
See the list
Listed on Inferse
- Newest Models in 2026466 listed
- Longest-Context Models in 2026466 listed
- Cheapest Language Models in 2026437 listed
- Models with Tool Calling in 2026395 listed
- Reasoning Models in 2026332 listed
- Vision Language Models in 2026295 listed
- Google Models: Pricing per 1M Tokens and Context (2026)43 listed
Sources
- openrouter.ai/google/gemini-3.1-flash-lite:batch· checked 3 Oct 2026