Gemini 3.5 Flash API pricing and integration
Use gemini-3.5-flash on Crazyrouter. Compare live token and cache rates with request examples for the supported endpoints.
Try Gemini 3.5 Flash online
One run ≈ $0.0031 · $2 free credit on signup ≈ 650 runsGemini 3.5 Flash is available in the Playground after signup — $2 free credit, pay as you go after that.
Paste the model ID, live price, base URL and a working request straight into your coding agent.
What is Gemini 3.5 Flash?
Gemini 3.5 Flash remains available alongside the newer Flash variants. Use gemini-3.5-flash to keep an existing integration on this version. Its discount and cache-read pricing are model-specific, so check the live table when comparing a migration to Gemini 3.7 Flash or Gemini 3.8 Flash. API requests must use gemini-3.5-flash. The examples cover /v1/chat/completions and /v1beta/models/{model}:generateContent.
Works with the OpenAI SDKs, LangChain, Cursor, Cline and any tool that accepts a custom base URL.
Streaming, tools and structured output depend on the model and upstream channel. Check the required feature on your channel before production use.
The rates come from Crazyrouter's billing table; discounts vary by model.
Compare against Claude, GPT, Gemini, DeepSeek and more without juggling vendor accounts.
Gemini 3.5 Flash API quickstart
Point your OpenAI SDK at https://api.crazyrouter.com/v1 and set the model to gemini-3.5-flash. If your client speaks Gemini natively, use the second example instead.
curl https://api.crazyrouter.com/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $CRAZYROUTER_API_KEY" \
-d '{
"model": "gemini-3.5-flash",
"messages": [{"role": "user", "content": "Explain the tradeoffs of this architecture decision."}],
"stream": true
}'Show OpenAI-compatible migration example
curl "https://api.crazyrouter.com/v1beta/models/gemini-3.5-flash:generateContent" \
-H "Content-Type: application/json" \
-H "x-goog-api-key: $CRAZYROUTER_API_KEY" \
-d '{
"contents": [{"parts": [{"text": "Explain the tradeoffs of this architecture decision."}]}]
}'Estimated workload costs
Best use cases
Works with developer tools
OpenAI SDKs
Set base_url to https://api.crazyrouter.com/v1 and model to gemini-3.5-flash.
Cursor, Cline, Continue
Add Crazyrouter as a custom OpenAI-compatible provider and pick the model from the list.
LangChain / LlamaIndex
Use the OpenAI chat model class with the Crazyrouter base URL.
Gemini 3.5 Flash FAQ
What base URL do I use for Gemini 3.5 Flash?
https://api.crazyrouter.com/v1. Chat completions go to /v1/chat/completions; native Gemini requests use their usual path.
How is usage billed?
Per token, at the input/output rates shown on this page. Your balance is debited per request; there is no subscription.
Does it support streaming and function calling?
Support varies by model and upstream channel. The request example is a starting point; verify streaming, tools and structured output separately before production use.
Can I switch to another model later?
Change the model string. The same key works for every model in the Crazyrouter catalogue.
Where do I see the current price?
The pricing page lists live rates for every model, including group discounts if you are logged in.
Guides and comparisons
ComparisonGemini 3.5 Flash vs Gemini 3 Flash vs Gemini 2.5 Flash: Real API Benchmark
We tested gemini-3.5-flash, gemini-3-flash, and gemini-2.5-flash through the Crazyrouter China endpoint to compare latency, reasoning, coding, and cost behavior.
ComparisonGemini 3.5 Flash vs Claude Response-Tier Models: Which One Should Developers Use?
A practical comparison of Gemini 3.5 Flash against Claude Haiku, Sonnet, and Opus-style response tiers for latency, cost, coding, reasoning, and production API routing.
GuideGemini 3 Pro Pricing Queries: Verify the Model Version and Recheck 3.1 Pro
A current gemini-3.1-pro gateway rate check, two live JSON requests and five Decimal fixtures separate usage estimates from actual billing and untested discounts.
Podcast
AI Dev Tools: The Crazyrouter Podcast
Short episodes for developers on AI APIs, gateways, cost control and coding tools.
Latest episodes
EP196 · Oct 29, 2026 · 6:53
AI API Security Posture — Turn Controls Into Continuous Evidence
A practical guide to AI API security posture: inventory exposure, verify controls continuously, protect keys and data, constrain tools, and turn security assumptions into evidence that operators can act on.
EP195 · Oct 28, 2026 · 7:21
AI API Policy Drift — Detect When Production Rules Stop Matching Intent
A practical guide to policy drift in AI APIs: version routing and safety rules, detect stale enforcement, compare intended and observed behavior, and restore control before small gaps become incidents.
