Gemini 3.1 Flash Lite (Batch)

google/gemini-3.1-flash-lite-batch

A chat model with a 1M-token context window, at $0.13125 per million input tokens and $0.7875 per million output tokens.

Details

Maker: google
Kind: Chat
Context window: 1,000,000 tokens
Max output: 65,000 tokens
Input: $0.13125 per million tokens
Cached input: $0.01575 per million tokens, 88% off
Cache write: Same as input
Output: $0.7875 per million tokens
Capabilities: Reasoning, tool use, vision, file input
Takes: Text, image, pdf
Returns: Text
Zero data retention: Not on every provider
No training on requests: Yes, on every provider
Released: 2026-05-07

Description

Gemini 3.1 Flash Lite outperforms 2.5 Flash Lite on overall quality and lands close to 2.5 Flash performance across key capability areas. It is a workhorse model for high-volume use cases, with improvements across audio input/ASR, RAG snippet ranking, translation, data extraction, and code completion.

Call it

curl

curl https://phantom.codes/v1/chat/completions \
  -H "Authorization: Bearer $PHANTOM_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "google/gemini-3.1-flash-lite-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