Back to Models

Google: Gemini 3.7 FlashActive50% OFF

google/gemini-3.7-flash
CompareChat

Gemini 3.7 Flash is Google’s efficient multimodal model designed for coding and agentic workflows. It improves code generation, web application development, tool use, and reliability in complex multi-step tasks while supporting text, image, audio, and video inputs. With a 1-million-token context window, up to 64,000 tokens of output, and adjustable reasoning levels, it is well suited for coding agents, enterprise automation, complex document analysis, and large-scale multimodal applications.

By:GoogleInput Type:Output Type:Publish time:2026-08-14

Providers

Route requests across multiple providers. Copy a provider slug to set your preference.

ProviderCache Hit RateContext
Google Vertex
google-vertex
41.6%$1.5$0.75/ M tokens$7.5$3.75/ M tokensRead:0.150.075/ M tokensWrite:-/ M tokens1.05M11.8s97.4tps

Uptime

24hours

Direct request success rate on AI Gateway and per-provider.

Oct 26, 20:09
Google Vertex100.00%

Throughput

24hours

P50 throughput on live AI Gateway traffic, in tokens per second (TPS).

Oct 26, 18:00
Google Vertex97.4 tps

Latency

24hours

P50 time to first token (TTFT) on live AI Gateway traffic, in milliseconds.

Oct 26, 18:00
Google Vertex11.78s

Activity

Token volume and request traffic to this model over time.

Token Consumption
Oct 25
Google Vertex17.2M

Token volume broken down by the provider that served each request. Larger segments indicate providers handling more of this model's traffic.

Benchmarks

Scores on standardized evaluations. Higher percentages are better — and rank percentile shows

Metrics sourced fromArtificial Analysis

Gemini 3.7 FlashGoogle
Intelligence Index39.1

Apps

Public apps that send the most traffic to this model. Good signal for what real production workloads look like — and a hint at which use cases this model is best suited for. View All

Token Ranking
1OpenQiao Studio ChatOpenQiao Studio Chat is the built-in web chat workspace of the OpenQiao AI model aggregation platform, operated by OpenQiao Singapore. It lets users converse with many different large language models in a browser GUI, with features such as multi-model side-by-side comparison, multimodal file input, Artifacts generation, web search, image generation/editing and voice input/output.
332.8K
2TauriTavernTauriTavern is an open-source, SillyTavern-compatible native client maintained by developer Darkatse (not affiliated with SillyTavern officially). It keeps the upstream SillyTavern frontend for AI roleplay and character-card chatting while replacing the Node.js backend with a Rust/Tauri v2 implementation, shipping as an installable app for Windows, macOS, Linux, Android and iOS. Users use it for LLM-driven roleplay and conversation with character cards, presets, world info and frontend extensions stored locally.
190.9K87.86%
3Cherry StudioCherry Studio is a free, open-source cross-platform desktop AI client (Windows, macOS, Linux) developed by the CherryHQ team. It brings multi-model chat, autonomous agents, knowledge bases, AI drawing, translation and MCP tool integration into a single local-first workspace, letting users access many large language model providers from one interface.
156.2K
4magpiemagpie is an open-source menu bar app, TUI and CLI (written in Go by developer yetone) that shows every AI coding agent installed on a machine and the model each one is set to, letting users switch models with one click. It runs a local gateway that translates between OpenAI Chat Completions, OpenAI Responses, Anthropic Messages and Gemini formats, so agents such as Claude Code, Codex, Gemini CLI, OpenCode, Goose, Pi and Copilot CLI can run on any provider's models or on existing subscriptions.
49.9K2.37%
5AxonHubAxonHub is an open-source AI gateway written in Go by developer looplj that exposes unified OpenAI-, Anthropic- and Gemini-compatible API endpoints and forwards requests to 100+ large language models from many providers. It lets teams switch model providers without changing application code, and adds channel routing, automatic failover, load balancing, access control, cost accounting and end-to-end request tracing through a built-in web console.
9.1K
6RikkaHubRikkaHub is an open-source native Android AI chat client built with Kotlin and Jetpack Compose in Material You style, developed by the RikkaHub open-source project (author rerere). It lets users add their own OpenAI-, Google Gemini- and Anthropic-compatible providers and switch models mid-conversation, with multimodal input (images, PDF, DOCX), Markdown/LaTeX/Mermaid rendering, web search integrations, memory, custom agents and MCP tool support.
8.9K

Related Models

More models from Google

Google: Gemini 4 Argon
11.60Btokens

Gemini 4 Argon is a frontier model from Google DeepMind, released on September 30, 2026. It is the first model in the Gemini 4 series and uses a new naming scheme. It is strong in coding, financial research, legal drafting, and autonomously patching cybersecurity vulnerabilities. It accepts text, image, video, and file inputs and has a 1-million-token context window. On benchmarks, it scores 77.9% on DeepSWE v1.1, ahead of Claude Opus 5.5 and GPT-6 Astra, and ranks first on the Vals Index with 68.90%.

Google: Nano Banana 2.1 (Gemini Nano Banana 2.1)
87.96Mtokens

Gemini Nano Banana 2.1 is an upgraded multimodal reasoning image model for production-grade image generation and editing, with stronger prompt adherence, multi-reference editing, and improved visual fidelity. It understands text, images, video, and PDF inputs, supports interleaved text and image generation, and can reason over complex spatial and compositional instructions before generating images. The model also supports grounding with Google Search and Google Image Search for better long-tail entity recognition, visual understanding, and output accuracy.

Gemini 3.8 Flash TTS
594.57Ktokens

Gemini 3.8 Flash TTS is a text-to-speech model from Google and the successor to Gemini 3.1 Flash TTS Preview. It is the creative tier of the 3.8 TTS family, suited for narration, character work, and multi-speaker dialogue where voice fidelity, acting nuance, and regional dialect coverage matter more than latency.