GeniusRelay
Sign upConsole

Google: Gemini 3.5 Flash Thinking

gemini-3.5-flash-thinking

CompareAPIGet an API keyGet an API key

Gemini 3.5 Flash Thinking costs $1.95 per million input tokens and $11.70 per million output tokens, supports 1.05M context, and is available through the OpenAI-compatible API.

Gemini 3.5 Flash with higher thinking enabled for harder reasoning, agentic coding, tool use, multimodal analysis, and long-context workflows. Audio input costs $3.00 per million audio tokens.

Modalities

Text + Image + Video + Audio → Text

Input / output price

$1.95 / $11.70 per 1M

Context

1.05M · max output 66K

Capabilities

ReasoningVisionLong context

Pricing

Billed per token actually used and deducted from your credits.

ItemUSD per 1M tokens
Input$1.95
Output$11.70
Cached input$0.195

Calculator

Drag the sliders to estimate what this model will cost.

Per request
$0.0152
Per day
$7.60
Per month (30 days)
$228.15

Gemini 3.5 Flash Thinking: input $1.95/M · output $11.7/M · cached input $0.195/M

Request with these settings
curl https://api.geniusrelaygpt.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "gemini-3.5-flash-thinking", "max_tokens": 800,
       "messages": [{"role": "user", "content": "…"}]}'

Code samples

OpenAI-compatible. Set the base URL to https://api.geniusrelaygpt.com/v1 and the model to gemini-3.5-flash-thinking.

curl https://api.geniusrelaygpt.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gemini-3.5-flash-thinking",
    "stream": true,
    "messages": [{"role": "user", "content": "Hello"}]
  }'

Use it in a client: Cursor · Cline · SillyTavern · Codex

Parameters

Common OpenAI parameters can be passed as-is.

temperaturetop_pmax_tokensstreamstoppresence_penaltyfrequency_penaltyseed

FAQ

How is Gemini 3.5 Flash Thinking billed?
Input is $1.95 and output is $11.70 per million tokens; cached input is $0.195. The charge for every request is listed in Usage Logs in the console.
How long is the context window?
1.05M tokens. In a long conversation every turn is billed for the full input, so keep the history under control.
Does it support streaming?
Yes. Add "stream": true to the request to receive server-sent events in the OpenAI format.
Gemini 3.5 Flash Thinking API pricing · GeniusRelay