Google

Gemini 3 Flash

1.05M ctxTextImageAudio Tools Reasoning

Released Dec 9, 2025 · 812B tokens this week · 2 providers

Overview

The high-throughput member of the Gemini 3 family: most of Pro quality for a small fraction of the cost. The huge context window and low latency make it a favourite for retrieval and document pipelines at scale. Multimodal input is included at the same price.

agentsreasoningtranslationmarketing

Providers

Reference data — not yet measured from live traffic

PROVIDERMAX OUTOUTPUT /MQUANT
Google AI StudioCheapest
1.05M66K$0.30$2.50330ms28599.93%Full
Google Vertex AI
1.05M66K$0.32$2.63380ms26099.88%Full

Latency p50 reflects a provider’s API endpoint responsiveness — the round-trip to its API, not per-token inference time. These figures, with throughput and uptime, are reference data until the gateway aggregates its own traffic.

Price comparison

Blended $ per 1M tokens

Gemini 3 Flash$1.95
GPT-5.2$10.94

Blended rate per 1M tokens, weighted one part prompt to three parts completion — roughly the shape of a chat workload. Your mix will move the number.

Call it

OpenAI-compatible — swap the base URL and go

curl https://model.cards/api/v1/chat/completions \
  -H "Authorization: Bearer $MODELCARDS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "google/gemini-3-flash",
    "messages": [
      { "role": "user", "content": "Summarize the tradeoffs of speculative decoding." }
    ]
  }'