---
title: Google Gemini
slug: google-gemini
url: "https://toolweight.com/tools/google-gemini"
homepage: "https://ai.google.dev"
categories: llm-apis
last_verified: 2026-11-06
dataset_version: 0738be72
license: CC-BY-4.0
---

# Google Gemini

> Gemini via AI Studio for prototyping or Vertex AI for production

- Gemini through two doors: AI Studio (free tier, prototyping) and Vertex AI (region pinning, quotas, contracts)
- Pitch is long context at low cost and genuinely native audio in and out
- The deepest regional footprint here, including Australian regions competitors cannot match

## Identity

|  |  |
| --- | --- |
| Name | Google Gemini |
| Company | Google |
| One-liner | Gemini via AI Studio for prototyping or Vertex AI for production |
| Site | https://ai.google.dev |
| Docs | https://ai.google.dev/gemini-api/docs |
| Founded | 1998 |
| Open source | No |
| Compared in | 1 |

## Where it is compared

### [LLM APIs](https://toolweight.com/compare/llm-apis)
Ranked **#2 of 18** on default weights.
| Field | Value | Confidence | Verified | Source | Note | Permalink |
| --- | --- | --- | --- | --- | --- | --- |
| Flagship model | Gemini 3.1 Pro Preview (gemini-3.1-pro-preview) | Vendor-claimed | 2026-07-30 | https://ai.google.dev/gemini-api/docs/models/gemini-3.1-pro-preview | Current flagship general-purpose Pro model; Gemini 3 Pro Preview was shut down 2026-03-09. | https://toolweight.com/compare/llm-apis#google-gemini--flagship_model |
| Context window | 1,048,576 tokens | Vendor-claimed | 2026-07-30 | https://ai.google.dev/gemini-api/docs/models/gemini-3.1-pro-preview | Input window (1M). Google publishes a separate, much smaller output cap alongside it. | https://toolweight.com/compare/llm-apis#google-gemini--context_window |
| Max output | 65,536 tokens | Vendor-claimed | 2026-07-30 | https://ai.google.dev/gemini-api/docs/models/gemini-3.1-pro-preview | Output cap, well below the million-token input window. | https://toolweight.com/compare/llm-apis#google-gemini--max_output |
| Image input | ● | Vendor-claimed | 2026-07-30 | https://ai.google.dev/gemini-api/docs/models/gemini-3.1-pro-preview | Accepts text, image, video, audio and PDF input. | https://toolweight.com/compare/llm-apis#google-gemini--vision |
| Audio in/out | ◐ | Vendor-claimed | 2026-07-30 | https://ai.google.dev/gemini-api/docs/models/gemini-3.1-pro-preview | The flagship gemini-3.1-pro-preview takes audio in but outputs text only; native audio out is a separate Live API model, graded on the same flagship basis as the other rows. | https://toolweight.com/compare/llm-apis#google-gemini--audio_io |
| Open weights | ◐ | Vendor-claimed | 2026-01-15 | https://ai.google.dev/gemma | The Gemma family is downloadable; Gemini itself is not. | https://toolweight.com/compare/llm-apis#google-gemini--open_weights |
| OpenAI-compat API | ● | Vendor-claimed | 2026-01-15 | https://ai.google.dev/gemini-api/docs/openai | A chat-completions compatibility endpoint is documented for both AI Studio and Vertex. | https://toolweight.com/compare/llm-apis#google-gemini--openai_compatible |
| TTFT p50 | - | Unknown | - | - | - | https://toolweight.com/compare/llm-apis#google-gemini--ttft_p50 |
| Output tok/s | - | Unknown | - | - | - | https://toolweight.com/compare/llm-apis#google-gemini--throughput_tps |
| $/M input | $2/M tok | Vendor-claimed | 2026-11-06 | https://aistudio.google.com/docs/pricing | - | https://toolweight.com/compare/llm-apis#google-gemini--price_in |
| $/M output | $12/M tok | Vendor-claimed | 2026-11-06 | https://aistudio.google.com/docs/pricing | - | https://toolweight.com/compare/llm-apis#google-gemini--price_out |
| $/M cache read | $0.2/M tok | Vendor-claimed | 2026-07-30 | https://ai.google.dev/gemini-api/docs/pricing | Cache read at the ≤200K tier ($0.40 above it). Google also charges cache storage at $4.50 per 1M tokens/hour, which can dominate for small caches held a long time. | https://toolweight.com/compare/llm-apis#google-gemini--cached_input |
| Batch discount | 50% | Vendor-claimed | 2026-07-30 | https://ai.google.dev/gemini-api/docs/pricing | - | https://toolweight.com/compare/llm-apis#google-gemini--batch_discount |
| Tool use | ● | Vendor-claimed | 2026-07-30 | https://ai.google.dev/gemini-api/docs/models/gemini-3.1-pro-preview | - | https://toolweight.com/compare/llm-apis#google-gemini--tool_use |
| Schema output | ● | Vendor-claimed | 2026-01-15 | https://ai.google.dev/gemini-api/docs/structured-output | responseSchema constrains decoding to a supplied schema. | https://toolweight.com/compare/llm-apis#google-gemini--structured_output |
| Effort control | ● | Vendor-claimed | 2026-01-15 | https://ai.google.dev/gemini-api/docs/thinking | Thinking level / thinking budget controls reasoning depth per request. | https://toolweight.com/compare/llm-apis#google-gemini--reasoning_effort |
| Computer use | ◐ | Inferred | 2026-01-15 | https://ai.google.dev/gemini-api/docs/computer-use | A dedicated computer-use model rather than a tool on the flagship, which is this column's definition of partial, so it is now graded that way rather than as a yes. | https://toolweight.com/compare/llm-apis#google-gemini--computer_use |
| MCP support | ◐ | Vendor-claimed | 2026-07-30 | https://ai.google.dev/gemini-api/docs/function-calling | Connects to remote MCP servers (Streamable HTTP only, no SSE) via the Interactions API — a client/remote integration, not a built-in native connector. | https://toolweight.com/compare/llm-apis#google-gemini--mcp_support |
| Cache TTL | Explicit caches, default 1 h TTL; implicit caching too | Inferred | 2026-01-15 | - | - | https://toolweight.com/compare/llm-apis#google-gemini--prompt_cache_ttl |
| Continuity policy | Stable versions carry dated suffixes you can pin, and Google publishes a retirement date per version. In practice this is the fastest-moving line-up here: preview models are withdrawn with weeks of notice, and the 1.5 generation was retired roughly a year after GA. Vertex adds contractual predictability that AI Studio does not. | Community-reported | 2026-01-15 | - | - | https://toolweight.com/compare/llm-apis#google-gemini--continuity_policy |
| Notice period | - | Unknown | - | - | Google publishes per-version retirement dates but no single guaranteed notice window; preview models get materially less than stable ones. | https://toolweight.com/compare/llm-apis#google-gemini--deprecation_notice |
| Pinnable versions | ● | Vendor-claimed | 2026-01-15 | https://ai.google.dev/gemini-api/docs/models | - | https://toolweight.com/compare/llm-apis#google-gemini--pinned_snapshots |
| Zero retention | ◐ | Inferred | 2026-01-15 | - | Tier-dependent, which is what this column calls partial: on Vertex, prompts are not stored and enterprise controls apply, but the free AI Studio tier is a different bargain, assume it is used to improve products. We have not confirmed exclusion from abuse-monitoring logs, which is the bar the column's definition actually sets. | https://toolweight.com/compare/llm-apis#google-gemini--zero_retention |
| Trains on your data | ◐ | Inferred | 2026-01-15 | - | No for paid Vertex and paid AI Studio usage; the free tier explicitly is used to improve Google products. | https://toolweight.com/compare/llm-apis#google-gemini--trains_on_data |
| AU region | ● | Inferred | 2026-01-15 | - | Vertex AI serves Gemini from australia-southeast1, with region pinning enforced at the project level. | https://toolweight.com/compare/llm-apis#google-gemini--au_region |
| API since | 2023 | Inferred | - | - | - | https://toolweight.com/compare/llm-apis#google-gemini--launch_year |
| Positioning | Long context and native multimodality across Google's cloud | Inferred | - | - | - | https://toolweight.com/compare/llm-apis#google-gemini--positioning |

**Verdict.** The cheapest million-token window and only genuinely native audio, but the fastest-churning line-up here, so expect yearly migrations.

## Alternatives

- [Qwen](https://toolweight.com/tools/alibaba-qwen), Alibaba's model family, huge open-weight range, closed flagship
- [Amazon Bedrock](https://toolweight.com/tools/amazon-bedrock), Multi-vendor model access inside your existing AWS account
- [Anthropic](https://toolweight.com/tools/anthropic), Claude models, built around long agentic runs and tool use
- [Cerebras](https://toolweight.com/tools/cerebras), Wafer-scale inference, the fastest tokens per second available
- [Cohere](https://toolweight.com/tools/cohere), Enterprise-focused models built for RAG and private deployment
- [DeepSeek](https://toolweight.com/tools/deepseek), Frontier-adjacent models at a small fraction of Western prices
- [Fireworks AI](https://toolweight.com/tools/fireworks-ai), Fast open-weight inference with strong structured-output support
- [Groq](https://toolweight.com/tools/groq), Custom LPU silicon serving open-weight models at extreme speed
- [Meta Llama](https://toolweight.com/tools/meta-llama), Open-weight Llama models, hosted almost everywhere but Meta
- [Mistral AI](https://toolweight.com/tools/mistral-ai), European lab with an open-weight lineage and EU-resident hosting
- [Moonshot AI](https://toolweight.com/tools/moonshot-ai), Kimi models, open-weight agentic performance at low cost
- [OpenAI](https://toolweight.com/tools/openai), GPT models plus audio, images and embeddings on one bill

## Logo & brand colours

SVG files: https://toolweight.com/teams/google/logo.svg and https://toolweight.com/teams/google/mono.svg. JSON: https://toolweight.com/api/v1/brands/google.

| Hex | oklch |
| --- | --- |
| #3086ff | oklch(63.4% 0.198 258.0) |

## Licence and attribution

Data from Toolweight (https://toolweight.com), licensed CC-BY-4.0.

- Licence: [CC-BY-4.0](https://creativecommons.org/licenses/by/4.0/)
- Canonical HTML: https://toolweight.com/tools/google-gemini
- Machine-readable: https://toolweight.com/tools/google-gemini.md · https://toolweight.com/api/v1 · https://toolweight.com/mcp
- Toolweight takes no affiliate revenue and sells no placements.