budget

Claude Haiku 4 5 vs Gemini 3 Flash Preview

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

Specifications

Feature Claude Haiku 4 5 Gemini 3 Flash Preview
Provider anthropic vertex ai-language-models
Model ID claude-haiku-4-5 gemini-3-flash-preview
Input / 1M tokens $1.00 $0.50 (50% cheaper)
Output / 1M tokens $5.00 $3.00 (40% cheaper)
Cached input / 1M $0.10 $0.05
Context window 200kk tokens 1049kk tokens
Max output 64kk tokens 66kk 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 Claude Haiku 4 5 Gemini 3 Flash Preview Winner
Small
1M in / 0.2M out
$2.00 $1.10 Gemini 3 Flash Preview saves 45%
Medium
10M in / 2M out
$20.00 $11.00 Gemini 3 Flash Preview saves 45%
Large
100M in / 20M out
$200 $110 Gemini 3 Flash Preview saves 45%

Category winners

Cheapest input
Gemini 3 Flash Preview
$0.50/M · 50% less than the other
Cheapest output
Gemini 3 Flash Preview
$3.00/M · 40% less than the other
Larger context
Gemini 3 Flash Preview
1049kk tokens · 424% 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
$3.00/M output — 40% cheaper on output at scale
Gemini 3 Flash Preview
Long-document processing & large codebases
1049k context window vs 200k — 424% 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.