Google model
Gemini 3.5 Flash API
Send google/gemini-3.5-flash when you want this exact Flash id, not Lite. It lists 1,000,000 tokens at 1.50 / 9. Gemini 3.5 Flash Lite publishes the same window at 0.30 / 2.50. If price is the question, start with Lite. This id publishes a $0.15 per 1M cached-input rate.
Function CallingStructured Outputs
What is Gemini 3.5 Flash API in NextModel?
Send google/gemini-3.5-flash when you want this exact Flash id, not Lite. It lists 1,000,000 tokens at 1.50 / 9. Gemini 3.5 Flash Lite publishes the same window at 0.30 / 2.50. If price is the question, start with Lite. This id publishes a $0.15 per 1M cached-input rate.
Gemini 3.5 Flash via NextModel: 1M-token context; $1.50 / 1M tokens in / $9 / 1M tokens out per 1M tokens. Capabilities: streaming, tool, json.
Best use cases
- Gemini tool or structured-output jobs that must stay on the 3.5 Flash id.
- 1,000,000 token work you have already decided is not a Lite job.
- A higher list-price Gemini beside 2.5 Flash, which is 0.30 / 2.50.
When not to use
- You only needed the long window. Lite lists it cheaper.
- You need measured cache-hit benchmarks. Only the $0.15 / 1M cached-input rate is published.
- You wanted the preview id. That is google/gemini-3-flash-preview at 0.5 / 3.
OpenAI-compatible code example
request.sh
curl https://api.nextmodel.app/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $NEXTMODEL_API_KEY" \
-d '{"model":"google/gemini-3.5-flash","messages":[{"role":"user","content":"Reply with OK."}]}'Switching models only changes the model field.
Similar alternatives
GoogleCatalog
Gemini 3.1 Flash-Lite via NextModel: 1M-token context; $0.25 / 1M tokens in / $1.50 / 1M tokens out per 1M tokens. Capabilities: streaming, tool, json.
Best forimage understanding, multimodal chat
StreamingTool callingJSON modeVision
Platform curatedCurated and maintained in the NextModel catalog
OpenAICatalog
GPT-Chat Latest via NextModel: 400k-token context; $5 / 1M tokens in / $30 / 1M tokens out per 1M tokens. Capabilities: streaming, tool, json.
Best forimage understanding, multimodal chat
StreamingTool callingJSON modeVision
Platform curatedCurated and maintained in the NextModel catalog
QwenCatalog
Qwen3.7 Plus via NextModel: 1M-token context; Starting at $0.3 / 1M tokens in / $1.18 / 1M tokens out per 1M tokens. Capabilities: streaming, tool, json.
Best forimage understanding, multimodal chat
StreamingTool callingJSON modeVision
Platform curatedCurated and maintained in the NextModel catalog
Reading
Articles that explain Gemini 3.5 Flash
Gemini 3.5 Flash is listed on NextModel: 1,048,576 context, no cache row
Listed price, 1,000,000 context, and the published $0.15 / 1M cached-input rate.
Zhao Yu'an
How to estimate AI API cost before you ship
Unit price is not monthly spend.
Lin Qiming
LLM Gateway: Compare Options and Alternatives
Call it through the same OpenAI-compatible endpoint.
Zhao Yu'an
FAQ
Gemini 3.5 Flash API questions
What model id do I send for Gemini 3.5 Flash?
Send google/gemini-3.5-flash to https://api.nextmodel.app/v1.
How is Lite different on paper?
Same 1,000,000 token window. Lite is 0.30 / 2.50. This id is 1.50 / 9. Quality delta unpublished.
CacheSafety?
A $0.15 / 1M cached-input rate is published for this exact id.
Start now
Ready to start building?
Passwordless signup, pay-as-you-go billing, and one OpenAI-compatible endpoint for every model. Create your key and send your first request in minutes.