Gemini 3.6 Flash (Batch)

google/gemini-3.6-flash-batch

A chat model with a 1M-token context window, at $0.39375 per million input tokens and $1.96875 per million output tokens.

Details

Maker: google
Kind: Chat
Context window: 1,000,000 tokens
Max output: 64,000 tokens
Input: $0.39375 per million tokens
Cached input: $0.039375 per million tokens, 90% off
Cache write: Same as input
Output: $1.96875 per million tokens
Capabilities: Reasoning, tool use, vision, file input
Takes: Text, image, pdf, video
Returns: Text
Zero data retention: Not on every provider
No training on requests: Yes, on every provider
Released: 2026-07-21
Newer model: google/gemini-3.7-flash-batchReleased later by the same maker, costs no more, and lists the same capabilities. Compare the two

Description

Gemini 3.6 Flash delivers higher quality across coding, agentic workflows, and web development with reduced token consumption and fewer model calls compared to previous model iterations.

Call it

curl

curl https://phantom.codes/v1/chat/completions \
  -H "Authorization: Bearer $PHANTOM_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "google/gemini-3.6-flash-batch",
    "messages": [
      {"role": "user", "content": "Hello"}
    ]
  }'

Set PHANTOM_KEY to your key. Any OpenAI client works with the base URL https://phantom.codes/v1.

Get a key Compare with another model