Gemini 3.7 Flash (batch)
Google· released 13 Aug 2026
google/gemini-3.7-flash:batch- Input / 1M tokens
- $0.375
- Output / 1M tokens
- $1.875
Longest answer: 66K tokens
About
Gemini 3.7 Flash (batch) is a Google multimodal model aimed at fast agentic workflows, coding and complex multi-step reasoning. It is described as designed for responsive performance and reliable handling of multi-step tasks. Inputs include text, images, video, files and audio; outputs are text. It supports vision, tools and reasoning, with a 1,048,576-token context window and a maximum output of 65,536 tokens. The model ID is `google/gemini-3.7-flash:batch`. It was released on 2026-08-13. Pricing is USD 0.375 per 1M input tokens and USD 1.875 per 1M output tokens. Those modalities and limits provide the practical boundaries for applications using it, while the batch model ID identifies the listed variant. Teams considering it for agent workflows or code tasks can weigh its broad input formats against the output modality and token rates.
Who it is for
It suits teams building agentic workflows, coding tasks or multi-step reasoning applications that may use text, images, video, files or audio as input. Text is the listed output modality.
What is good
- 1,048,576-token context window
- Accepts text, image, video, file and audio
- Tools and reasoning supported
- Maximum output is 65,536 tokens
What to know first
- USD 1.875 per 1M output tokens
- Outputs text only
Verdict
Gemini 3.7 Flash (batch) supports a broad range of inputs and has a large context window, with tools and reasoning included. Its text-only output and per-token rates matter for stack and cost fit.
Details
- Lab
- Googleopenrouter.ai · 3 Oct 2026
- Context
- 1,049Kopenrouter.ai · 3 Oct 2026
- Input price
- $0.375 / 1Mopenrouter.ai · 3 Oct 2026
- Output price
- $1.875 / 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-3.7-flash:batch· checked 3 Oct 2026