Gemini 3 Pro
google/gemini-3-pro
Google's flagship: 2M token context, native video and audio input.
At a glance
- · $1.25 input / $5.00 output per 1M tokens (provider list price, billed in credits)
- · Context window: 2,000,000 tokens
- · OpenAI-compatible — model: "google/gemini-3-pro" (provider: google)
- · Best for: 2M token context — largest window among top-tier models
Strengths
- +2M token context — largest window among top-tier models
- +True multimodal input: video, audio, image, text
- +Very strong on structured output and JSON-schema enforcement
Weaknesses
- −Code generation slightly behind Claude Sonnet 4.6 and GPT-5.4
- −At very long contexts, latency becomes significant
Use cases
- →Video analysis, transcription, processing hours-long recordings
- →Analyze whole book libraries in one context
- →Structured extraction with complex schemas
Alternatives in the catalog
How to call it
Drop-in OpenAI-compatible. Just swap the `model` string and you're using this model.
curl https://www.getmorecredits.com/v1/chat/completions \
-H "Authorization: Bearer $GMC_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "google/gemini-3-pro",
"messages": [{ "role": "user", "content": "Hello!" }]
}'Good for
Frequently asked questions
How much does Gemini 3 Pro cost?⌄
Input is $1.25 per million tokens; output is $5.00 per million tokens — provider list price. On getmorecredits.com you pay in credits, no subscription, no minimum spend.
What's the context window of Gemini 3 Pro?⌄
Gemini 3 Pro accepts up to 2,000,000 input tokens, with a maximum of 65,536 output tokens per response. That fits whole code repos or book-length documents into a single call.
What can Gemini 3 Pro do?⌄
Gemini 3 Pro supports image input (vision), audio input, tool calling, native JSON mode, structured output, reasoning mode. Google's flagship: 2M token context, native video and audio input.
Is Gemini 3 Pro OpenAI-compatible?⌄
Yes. On getmorecredits.com you call Gemini 3 Pro with the same request shape as OpenAI: POST /v1/chat/completions with "model": "google/gemini-3-pro". Existing OpenAI SDKs (Python, Node, etc.) work by changing the base URL and API key.