Gemini API Family
Use one EvoLink API to compare Gemini 3.8 Flash, 3.7 Flash, Pro, Flash, and Lite routes by current pricing, context, modality, accuracy, and token use — then pick the right model for your workload.
11 routes
Pro, Flash, and Lite tiers for every budget
Unified API access
OpenAI compatible, one key for all Gemini
Choose by workflow
Match Pro vs Flash vs Lite to your task
Compare Gemini API routes
Start from the workload: flagship reasoning, production Flash traffic, low-cost extraction, or long-context multimodal analysis.
| Route | Best for | Pricing | Context window | Modality | Status |
|---|---|---|---|---|---|
Gemini 3.8 Flash Newest Flash — GA | Google's newest Flash for higher-accuracy coding and agentic tasks; compare its higher token use with 3.7 Flash. | $0.675/$3.375 per MTok | 1M | Text, image, video, audio, PDF inputs | Available |
Gemini 3.7 Flash Flash — GA | Agentic workhorse of the Gemini 3 family with stronger code generation and terminal execution. | $0.675/$3.375 per MTok | 1M | Text | Available |
Gemini 3.6 Flash Flash — GA | Newest Flash-tier efficient workhorse for coding, agents, and knowledge work. | $0.675/$3.375 per MTok | 1M | Text | Available |
Gemini 3.5 Flash-Lite Flash Lite | Fast 3.5-class route for high-throughput classification, extraction, and low-latency tasks; defaults to minimal thinking. | $0.271/$2.25 per MTok | 1M | Text | Available |
Gemini 3.1 Pro Preview Flagship reasoning | Highest-quality Gemini reasoning, coding, agents, and long-context analysis. | $1.865/$11.183 <=200K; $3.73/$16.774 >200K | 1M input / 64K output | Text, code, image, video, audio, PDF inputs | Preview flagship |
Gemini 3.5 Flash Stable — GA for production | Agentic workflows, coding agents, sub-agent deployment, and long-horizon production tasks at Flash-tier cost. | $1.35/$8.10 per MTok | 1M input / 65K output | Text, image, video, audio, PDF inputs | Stable (GA) |
Gemini 3 Flash Preview Fast Gemini 3 | Low-latency multimodal apps that need stronger Gemini 3 behavior than older Flash routes. | $0.467/$2.796 per MTok (audio in: $0.933) | 1M input / 64K output | Text, image, video, audio, PDF inputs | Preview route |
Gemini 3.1 Flash Lite Preview Flash Lite | High-volume translation, classification, extraction, and batch text workloads on the Gemini 3 generation. | $0.234/$1.399 per MTok (audio in: $0.467) | 1M input / 64K output | Text, image, video, audio, PDF inputs | Preview route |
Gemini 2.5 Pro Stable Pro | Production reasoning, coding help, analysis, and complex multimodal tasks. | $1.165/$9.318 <=200K; $2.33/$13.977 >200K | 1M input / 64K output | Text, image, video, audio, PDF inputs | Stable deep reasoning |
Gemini 2.5 Flash Production Flash | Fast chat, extraction, summaries, and multimodal production traffic. | $0.281/$2.33 per MTok (audio in: $0.933) | 1M input / 64K output | Text, image, video, audio, PDF inputs | Production workhorse |
Gemini 2.5 Flash Lite Flash Lite | High-volume classification, extraction, routing, and lightweight chat flows. | $0.095/$0.374 per MTok (audio in: $0.281) | 1M input / 64K output | Text, audio inputs | Flash Lite |
How to decide which Gemini model to use
Follow these 4 rules to narrow down your choice across Pro, Flash, and Lite tiers.
Start with reasoning depth
Complex coding agents, multi-step tool use, deep document analysis, and high-accuracy output — start with Gemini 3.1 Pro or Gemini 2.5 Pro.
Then check latency and throughput needs
Production chat, support bots, real-time extraction, and high-frequency multimodal apps — compare Gemini 3 Flash or Gemini 2.5 Flash.
Then check cost sensitivity
High-volume classification, batch text processing, routing, and lightweight extraction — compare Gemini 3.1 Flash Lite or Gemini 2.5 Flash Lite.
Finally, consider mixed-complexity workflows
If the same pipeline mixes simple classification with deep reasoning steps, consider EvoLink Smart Router instead of hardcoding one Gemini model.
Smart Router →If you already know your task type, find the recommended starting point in the table below.
Choose a Gemini model by workflow: reasoning, speed, cost, and multimodal tasks
Match your primary task to the right Gemini route.
| Your task | Recommended start | Good fit if... | Watch out for |
|---|---|---|---|
| Complex reasoning and coding agents | Gemini 3.1 Pro | You need highest-quality Gemini reasoning, multi-step tool use, or deep code analysis | Compare current token rates and total usage per completed task. |
| Stable deep reasoning with multimodal | Gemini 2.5 Pro | You need production-grade reasoning with broad multimodal support and proven stability | Slightly lower capability ceiling than 3.1 Pro |
| Higher-accuracy coding and agent workflows | Gemini 3.8 Flash | You need Google’s newest Flash route for coding, agents, multimodal analysis, and 1M context | Uses more tokens than 3.7 Flash — compare cost per accepted task |
| Low-latency multimodal apps | Gemini 3 Flash | You need fast responses with Gemini 3 generation capabilities across text, image, audio, and video | Preview route — check stability requirements |
| Production chat and extraction | Gemini 2.5 Flash | You need a proven production workhorse for chat, summaries, extraction at scale | Good default for most production workloads |
| Batch text workloads | Gemini 2.5 Flash Lite | Tasks are classification, routing, or short responses where cost matters most | Limited to text and audio input only |
| Mixed-complexity text workflows | EvoLink Smart Router | Same pipeline has both simple and complex tasks across Gemini and other providers | Best when you don't want manual model routing logic |
Gemini API workflows: agents, chat, documents, and multimodal processing
See how Gemini models fit into real products, agents, and content processing pipelines.
Reasoning and coding agents
For code generation, bug fixing, multi-step tool use, and complex analysis agents. If output quality directly affects product behavior, start with Gemini 3.1 Pro. For proven stability, compare Gemini 2.5 Pro.
Production chat and support
For support bots, in-app assistants, knowledge base Q&A, and high-frequency multi-turn conversations. Start with Gemini 2.5 Flash for proven throughput, then run the same traffic through Flash Lite and compare answer quality against the current per-token rates.
Long document and multimodal analysis
For PDF analysis, video understanding, audio transcription, and multi-file research workflows. Gemini's 1M context window and native multimodal support make Pro and Flash routes strong choices.
Agent routing and mixed tasks
For workflows where classification, extraction, reasoning, and generation coexist in the same pipeline. Use EvoLink Smart Router to automatically route between Gemini and other providers via evolink/auto.
View Gemini model details
Use this page to compare, then visit individual model pages for pricing details, playground access, and integration guides.
Gemini 3.8 Flash
Newest Flash — GA
- Context
- 1M
- Pricing
- $0.675/$3.375 per MTok
Gemini 3.7 Flash
Flash — GA
- Context
- 1M
- Pricing
- $0.675/$3.375 per MTok
Gemini 3.6 Flash
Flash — GA
- Context
- 1M
- Pricing
- $0.675/$3.375 per MTok
Gemini 3.5 Flash-Lite
Flash Lite
- Context
- 1M
- Pricing
- $0.271/$2.25 per MTok
Gemini 3.1 Pro Preview
Flagship reasoning
- Context
- 1M input / 64K output
- Pricing
- $1.865/$11.183 <=200K; $3.73/$16.774 >200K
Gemini 3.5 Flash
Stable — GA for production
- Context
- 1M input / 65K output
- Pricing
- $1.35/$8.10 per MTok
Gemini 3 Flash Preview
Fast Gemini 3
- Context
- 1M input / 64K output
- Pricing
- $0.467/$2.796 per MTok (audio in: $0.933)
Gemini 3.1 Flash Lite Preview
Flash Lite
- Context
- 1M input / 64K output
- Pricing
- $0.234/$1.399 per MTok (audio in: $0.467)
Gemini 2.5 Pro
Stable Pro
- Context
- 1M input / 64K output
- Pricing
- $1.165/$9.318 <=200K; $2.33/$13.977 >200K
Gemini 2.5 Flash
Production Flash
- Context
- 1M input / 64K output
- Pricing
- $0.281/$2.33 per MTok (audio in: $0.933)
Gemini 2.5 Flash Lite
Flash Lite
- Context
- 1M input / 64K output
- Pricing
- $0.095/$0.374 per MTok (audio in: $0.281)
Access all Gemini models through one EvoLink API
All 11 Gemini routes are available through a single EvoLink API key and OpenAI-compatible endpoint. Switch between Pro, Flash, and Lite by changing the model parameter — no separate accounts or keys needed.
Switch model="gemini-3.1-pro" to model="gemini-2.5-flash" without rebuilding your integration.How to think about Gemini API cost: Pro vs Flash vs Lite
Pro routes: reasoning justifies the premium
Gemini 3.1 Pro / Gemini 2.5 Pro — Evaluate these routes for complex coding, document analysis, and multi-step reasoning; compare quality and cost per completed task.
Flash routes: best balance for production volume
Gemini 3 Flash and 2.5 Flash deliver strong multimodal capabilities at a fraction of Pro pricing. Start here for chat, summaries, and production-scale extraction before considering Pro.
Lite routes: minimize cost for simple high-volume tasks
Gemini 3.1 Flash Lite and 2.5 Flash Lite are the routes to test for classification, routing, batch text, and short responses where reasoning depth is not critical. Check each route's current per-token rate on its model page before you commit volume.
Pricing summary
Input price range: $0.095–$3.73 / 1M tokens (EvoLink).
Gemini 3.8 Flash
$0.675/$3.375 /MTok
Context: 1M
Google's newest Flash for higher-accuracy coding and agentic work — 1M context; budget for higher token use than 3.7 Flash.
Gemini 3.7 Flash
$0.675/$3.375 /MTok
Context: 1M
Gemini 3.7 Flash · Input $0.675 · Output $3.375 / 1M tokens.
Gemini 3.6 Flash
$0.675/$3.375 /MTok
Context: 1M
Efficient Flash-tier model at $0.675/$3.375 per MTok, solid for multi-step orchestration and refactoring, 1M context.
Gemini 3.5 Flash-Lite
$0.271/$2.25 /MTok
Context: 1M
Gemini 3.5 Flash-Lite · Input $0.271 · Output $2.25 / 1M tokens.
Gemini 3.1 Pro
$1.865/$11.183 — $3.73/$16.774 /MTok
Context: 1M
Flagship reasoning with 1M context. Tiered pricing: $1.865/$11.183 under 200K, $3.73/$16.774 over 200K input tokens.
Gemini 3.5 Flash
$1.35/$8.10 /MTok
Context: 1M
GA stable Flash for agentic workflows and coding at $1.35/$8.10 per MTok with 1M context and built-in reasoning.
Gemini 3 Flash
$0.467/$2.796 /MTok
Context: 1M
Gemini 3 generation Flash route at $0.467/$2.796 per MTok with 1M context.
Gemini 3.1 Flash Lite
$0.234/$1.399 /MTok
Context: 1M
Gemini 3.1 Flash Lite · Input $0.234 · Output $1.399 / 1M tokens.
Gemini 2.5 Pro
$1.165/$9.318 — $2.33/$13.977 /MTok
Context: 1M
Stable deep reasoning at $1.165/$9.318 under 200K, $2.33/$13.977 over 200K.
Gemini 2.5 Flash
$0.281/$2.33 /MTok
Context: 1M
Production workhorse at $0.281/$2.33 per MTok with full multimodal support.
Gemini 2.5 Flash Lite
$0.095/$0.374 /MTok
Context: 1M
Gemini 2.5 Flash Lite · Input $0.095 · Output $0.374 / 1M tokens.
Gemini guides and comparisons
Use these guides when you need more context before choosing a route.
Gemini 3.8 Flash vs Gemini 3.7 Flash
Compare accuracy, token consumption, pricing periods, and cost per accepted task.
How to use Gemini 3.8 Flash API
Make the first request, migrate parameters, and add production canary and rollback controls.
Gemini 3 Pro deprecation migration guide
Move old Gemini 3 Pro Preview traffic to current Gemini routes without breaking production behavior.
OpenCode integration with Gemini routes
See how to access Gemini alongside Claude and GPT models through EvoLink's unified API layer.
Gemini 3.5 Pro API Release Watch
Track public API availability, Google's official confirmation, and reported launch delays.
Gemini 3.5 Pro vs Gemini 3.5 Flash
Compare confirmed Flash data with the still-pending Pro route before choosing a model.
Gemini 4 API availability
Google has confirmed Gemini 4 pre-training; track public API status, model ID, pricing, and EvoLink route verification.
Gemini API FAQ
Everything you need to know about the product and billing.