workhorse

Claude Sonnet 4 6 vs Gemini 2.5 Pro

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

Specifications

Feature Claude Sonnet 4 6 Gemini 2.5 Pro
Provider anthropic vertex ai-language-models
Model ID claude-sonnet-4-6 gemini-2.5-pro
Input / 1M tokens $3.00 $1.25 (58% cheaper)
Output / 1M tokens $15.00 $10.00 (33% cheaper)
Cached input / 1M $0.30 $0.13
Context window 1000kk 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 Sonnet 4 6 Gemini 2.5 Pro Winner
Small
1M in / 0.2M out
$6.00 $3.25 Gemini 2.5 Pro saves 46%
Medium
10M in / 2M out
$60.00 $32.50 Gemini 2.5 Pro saves 46%
Large
100M in / 20M out
$600 $325 Gemini 2.5 Pro saves 46%

Category winners

Cheapest input
Gemini 2.5 Pro
$1.25/M · 58% less than the other
Cheapest output
Gemini 2.5 Pro
$10.00/M · 33% less than the other
Larger context
Gemini 2.5 Pro
1049kk tokens · 5% larger window
More features
Gemini 2.5 Pro
5 / 5 capabilities

Better for…

High-volume RAG & repeated context
$0.13/M cached input — prompt caching makes repeated context retrieval significantly cheaper
Gemini 2.5 Pro
Short interactions & high-throughput APIs
$10.00/M output — 33% cheaper on output at scale
Gemini 2.5 Pro
Agentic workflows & tool use
Supports 5 of 5 tracked capabilities (vision, function calling, caching, web search, JSON schema)
Gemini 2.5 Pro
Cost-sensitive production at scale
$325/month at 100M-token scale — 46% cheaper than the alternative
Gemini 2.5 Pro

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.