gemini-3.5-flash-lite

AliasGemini 3.5 Flash Lite
by GoogleText

Gemini 3.5 Flash Lite API by Google on TTAPI supports Gemini chat completions and native generateContent requests, with documented token billing and request examples.

Last updated:
InputMessagesGemini request formats
Models11listed in current documentation
FlowSync + SSEstream is optional for chat
Price40% offofficial
gemini-3.5-flash-liteExample conversation
You

Write concise empty-state copy for a dashboard with no completed generations yet. Keep the answer practical for a gemini-3.5-flash-lite integration.

gemini-3.5-flash-lite logo
gemini-3.5-flash-lite

State what will appear here, offer one clear next action, and reassure the user that completed jobs and downloadable results will be retained in this workspace. This example is tailored to the gemini-3.5-flash-lite model page.

Examples

A request and response, in context

01 · UX copygemini-3.5-flash-lite
You

Write concise empty-state copy for a dashboard with no completed generations yet. Keep the answer practical for a gemini-3.5-flash-lite integration.

gemini-3.5-flash-lite logo
gemini-3.5-flash-lite

State what will appear here, offer one clear next action, and reassure the user that completed jobs and downloadable results will be retained in this workspace. This example is tailored to the gemini-3.5-flash-lite model page.

02 · Incident analysisgemini-3.5-flash-lite
You

Give a blameless incident-analysis outline for a spike in failed generation requests. Keep the answer practical for a gemini-3.5-flash-lite integration.

gemini-3.5-flash-lite logo
gemini-3.5-flash-lite

Capture impact and timeline, separate facts from hypotheses, identify contributing system conditions, list corrective actions with owners, and define the signal that proves each fix worked. This example is tailored to the gemini-3.5-flash-lite model page.

03 · Testing strategygemini-3.5-flash-lite
You

Propose a focused test strategy for an API client that creates and fetches async jobs. Keep the answer practical for a gemini-3.5-flash-lite integration.

gemini-3.5-flash-lite logo
gemini-3.5-flash-lite

Cover validation failures, accepted submissions, retries, timeouts, duplicate callbacks, terminal success and failure states, and one end-to-end contract test against a controlled environment. This example is tailored to the gemini-3.5-flash-lite model page.

Capabilities

What you can build with gemini-3.5-flash-lite

Prompt driven generation

Submit a concise prompt and get production-ready responses output through one TTAPI job.

Core controls only

Keep integration simple with prompt, model, output settings, and callback handling.

Async result flow

Use polling or webhook callbacks so long-running generations do not block your UI.

Ready for product UI

Return Gemini results that can be displayed, stored, or passed into downstream workflows.

Pricing

Token billing rules

One key and one balance across supported text models.

Gemini 3.5 Flash Lite token pricingOfficial pricing

USD per 1 million tokens after TTAPI's 40% channel discount.

TierInput / 1MCached input / 1MOutput / 1M
Standard$0.18$0.018$1.50
API request

Requests by operation

Switch between operation-specific endpoints and request fields.

Gemini

Gemini Completions

Chat-compatible format. Send messages and model in the body; stream is an optional boolean.

POSThttps://api.ttapi.io/gemini/chat/completions

Headers

TT-API-KEYstringrequired

Your TTAPI API key.

Content-Typestringrequired

Use application/json.

Body

messagesobject[]required

Conversation messages with role and content, as documented by TTAPI.

messages[].rolestringoptional

Role of this conversation message, for example user.

messages[].contentstringoptional

Text content of this conversation message.

modelstringrequired

Supported Gemini model identifier. Use the model ID shown in the request example.

streambooleanoptional

Enable server-sent events for progressive responses. Defaults to false.

Open this TTAPI channel documentation
Integrate

Integrate the selected channel

Choose a channel and operation, then copy the matching endpoint, request body, and code sample.

Gemini

Gemini Completions integration

POST https://api.ttapi.io/gemini/chat/completions

curl --request POST \
  --url https://api.ttapi.io/gemini/chat/completions \
  --header "TT-API-KEY: $TTAPI_KEY" \
  --header 'Content-Type: application/json' \
  --data '{"model":"gemini-3.5-flash-lite","messages":[{"role":"user","content":"Review this migration plan and identify the three highest risks."}],"stream":false}'