Which is cheaper, Gemini 3.5 Flash-Lite or Inkling-Small?

Gemini 3.5 Flash-Lite lists at $0.3 input and $2.5 output per 1M tokens; Inkling-Small at $0.3 and $1.2. Inkling-Small is 1.6x cheaper per token at list price.

Which has the larger context window?

Gemini 3.5 Flash-Lite accepts 1.0M tokens and Inkling-Small 1M tokens.

DemoBook a demo Dashboard

AI Gateway overview

Models

Specs, pricing, and capabilities for every model on the Respan gateway.

Gemini 3.5 Flash-Lite vs Inkling-Small

Inkling-Small scores 28.1 on the Respan Index (#69), ahead of Gemini 3.5 Flash-Lite at 27.7 (#71). Gemini 3.5 Flash-Lite leads on 7 of the 11 benchmarks both report. Inkling-Small is 1.6x cheaper per token at list price. Gemini 3.5 Flash-Lite has the larger context window (1.0M tokens).

Gemini 3.5 Flash-LiteGoogle

Respan Index: 27.7 (#71)
Input / output per 1M: $0.3 / $2.5
Blended price per 1M: $0.85
Context window: 1.0M
Max output: 66K
Input: text, vision, audio
Released: 2026-07-21

Prices and providers on Respan

Inkling-SmallThinking Machines Lab

Respan Index: 28.1 (#69)
Input / output per 1M: $0.3 / $1.2
Blended price per 1M: $0.525
Context window: 1M
Max output

Respan Index by category

Coding6.5 Gemini 3.5 Flash-Lite6.9 Inkling-Small
Agents43.9 Gemini 3.5 Flash-Lite44.6 Inkling-Small
Reasoning17.3 Gemini 3.5 Flash-Lite

Benchmarks both report

Benchmark	Gemini 3.5 Flash-Lite	Inkling-Small
Chess Puzzles (Epoch AI)	22%	18%
FrontierMath Tier 4 v2 (Epoch AI)	0%	17.1%
FrontierMath Tiers 1-3 v2 (Epoch AI)	26%	46.3%
GPQA Diamond	83.3%	88.5%

FAQ

Compare other models

Gemini 3.5 Flash-Lite vs Inkling-Small: benchmarks, price and context | Respan

Models

Models

Respan Index by category

Benchmarks both report

FAQ

Is Gemini 3.5 Flash-Lite better than Inkling-Small?

Which is cheaper, Gemini 3.5 Flash-Lite or Inkling-Small?

Which has the larger context window?

Compare other models