Google's tool-calling-focused Gemini 3.1 Pro preview, built for multi-step agents with a 1M-token context and $2/$12 per million pricing.
Recorded modality support shows what this model can accept and produce. An undocumented modality is shown as unknown rather than assumed to be unsupported.
Accepts
Produces
gemini 3.1 pro preview custom tools is the tool-calling-oriented release in Google's 3.1 Pro line — same reasoning core as the standard Pro preview, but positioned for agents that spend most of a conversation calling out to external functions rather than talking. If you're wiring up a multi-step agent that hits a database, a search API, and a code sandbox in sequence, this is the variant built with that loop in mind.
The underlying specs match Gemini 3.1 Pro Preview: a 1,048,576 token context window, up to 65,536 tokens of output, and full support for function calling, vision, and reasoning. What the naming signals is intent — this build is meant for agent frameworks and orchestration layers that define their own tool schemas and expect the model to reason across several tool calls in one turn, rather than for single-shot chat or document Q&A.
Input runs $2.00 per million tokens, output $12.00 per million, and cached input drops to $0.20 per million. That cached rate matters more here than in most Gemini tiers: a tool-calling agent typically resends the same system prompt, tool definitions, and conversation history on every step, and those are exactly the tokens caching discounts. A long-running agent session that would otherwise re-bill the same 5,000-token tool manifest on every step gets a 10x break on that portion once it's cached.
Against Gemini 3.1 Flash Lite Preview's $0.25/$1.50 pricing, this model costs 8x more per token in both directions — pay it when the task genuinely needs Pro-level reasoning across tool calls, not for high-volume simple extraction.
It's a preview build, so treat pricing and rate limits as subject to change before general availability. There's no published benchmark data attached to this release, so any claim about how it performs against other tool-calling models should come from your own eval on your own tool schema, not from a spec sheet.
Use the recorded facts as a shortlist, then validate the model against representative inputs and production constraints.
Gemini 3.1 Pro Preview Custom Tools is categorized for Audio-text-to-text, Automatic speech recognition, Image-text-to-text, Image-to-text, Text generation, Text-to-text AI models, Video-text-to-text. Its current record accepts text, image, video, audio, pdf and produces text. Confirm file formats, preprocessing, and provider-specific request schemas before implementation.
The directory records 1.0M context and 65.5K maximum output. Listed token prices are $2.00 input and $12.00 output per 1M tokens. Treat missing values as unknown and recheck current commercial terms.
Recorded output speed is — and time to first token is —. Hosting route, region, prompt length, concurrency, and provider load can materially change both measurements.
This page separates sourced model facts from incomplete fields. Benchmark evidence is displayed only when its source is linked and verified. Before choosing Gemini 3.1 Pro Preview Custom Tools, test task quality, tool reliability, safety behavior, data controls, rate limits, and total cost on the exact route you intend to use.
Related approved models in Automatic speech recognition. Compare specifications and verify fit for your workload.
Google's low-cost Gemini 3 model with a 1,048,576-token context window, vision support, and $0.30/$2.50 per million token pricing for volume workloads.
Google's mid-tier Gemini 3 model: 1,048,576-token context, multimodal input, and $1.50/$7.50 per million token pricing for production agent workloads.
Google's cheapest Gemini 3 model, with a 1,048,576-token context window and $0.25/$1.50 per million token pricing for high-volume, cost-sensitive work.
Google's full Gemini 3 Flash model, with a 1,048,576-token context window and $1.50/$9.00 per million token pricing for production-grade agent work.
Google's fast, rolling-updated Gemini model with a 1M-token context window, reasoning, and tool calling at $1.50/$9.00 per million tokens.
Google's low-cost, high-volume Gemini model at $0.25/$1.50 per million tokens, with a 1M-token context window and reasoning support.