budget

Gemini 3 Flash Preview vs Deepseek V3.2

Side-by-side pricing, context window, features, and per-use-case verdict. Data sourced from LiteLLM, updated regularly.

Specifications

Feature Gemini 3 Flash Preview Deepseek V3.2
Provider vertex ai-language-models deepseek
Model ID gemini-3-flash-preview deepseek/deepseek-v3.2
Input / 1M tokens $0.50 $0.28 (44% cheaper)
Output / 1M tokens $3.00 $0.40 (87% cheaper)
Cached input / 1M $0.05
Context window 1049kk tokens 164kk tokens
Max output 66kk tokens 164kk tokens
Vision
Function calling
Prompt caching
Web search
JSON schema

Monthly cost comparison

No cache discount applied — pure token costs at three usage scales.

Scale Gemini 3 Flash Preview Deepseek V3.2 Winner
Small
1M in / 0.2M out
$1.10 $0.36 Deepseek V3.2 saves 67%
Medium
10M in / 2M out
$11.00 $3.60 Deepseek V3.2 saves 67%
Large
100M in / 20M out
$110 $36.00 Deepseek V3.2 saves 67%

Category winners

Cheapest input
Deepseek V3.2
$0.28/M · 44% less than the other
Cheapest output
Deepseek V3.2
$0.40/M · 87% less than the other
Larger context
Gemini 3 Flash Preview
1049kk tokens · 540% larger window
More features
Gemini 3 Flash Preview
5 / 5 capabilities

Better for…

High-volume RAG & repeated context
$0.05/M cached input — prompt caching makes repeated context retrieval significantly cheaper
Gemini 3 Flash Preview
Short interactions & high-throughput APIs
$0.40/M output — 87% cheaper on output at scale
Deepseek V3.2
Long-document processing & large codebases
1049k context window vs 164k — 540% larger context
Gemini 3 Flash Preview
Agentic workflows & tool use
Supports 5 of 5 tracked capabilities (vision, function calling, caching, web search, JSON schema)
Gemini 3 Flash Preview

Deep-dive on each model

Pricing data sourced from LiteLLM and refreshed regularly. Always verify with each provider's official pricing page before making business decisions.