Skip to main content
gemini-3-flash is Google’s fast, low-cost Gemini — multimodal, with a 200K-token context window. It is the value tier of the Gemini 3 family: cheap enough for high-volume chat and OCR-style vision, with grounding for fresh facts. Pricing: 0.50/1Minput,0.50 / 1M input, 3.00 / 1M output — see the rate card.

​
Protocols

ProtocolPath
Gemini NativePOST https://llm.bytespike.ai/v1beta/models/gemini-3-flash:generateContent
OpenAI Chat Completions (shim)POST https://llm.bytespike.ai/v1/chat/completions
Anthropic Messages (translated)POST https://llm.bytespike.ai/v1/messages
For the OpenAI shim, the gateway translates the request body to Gemini’s generateContent shape behind the scenes. From the client side, you write standard openai-SDK code.

​
Quickstart

curl https://llm.bytespike.ai/v1/chat/completions \
  -H "Authorization: Bearer $BYTESPIKE_API_KEY" \
  -H "content-type: application/json" \
  -d '{
    "model": "gemini-3-flash",
    "messages": [{ "role": "user", "content": "Hello, ByteSpike." }]
  }'

​
Capabilities

CapabilitySupported
Chat Completions (shim)✅
Streaming (SSE)✅
Vision (image input)✅
Tools / function calling✅ parallel
JSON mode✅
Grounding (web search)✅
Context window200K tokens

​
When to use

  • High-volume cheap chat — the lowest-cost Gemini 3 tier for general Q&A and drafting.
  • High-volume vision — OCR-style tasks on receipts / invoices / screenshots.
  • Fresh-fact tasks at low cost — grounding (Google Search) is supported on Flash.
When not to use:
  • Harder reasoning — gemini-3-5-flash adds headroom at modest extra cost.
  • 1M-context jobs — gemini-3-5-flash and gemini-3-1-pro carry the long-context window.

​
Next