open-source

Deepseek V3 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 Deepseek V3 Gemini 2.5 Pro
Provider deepseek vertex ai-language-models
Model ID deepseek/deepseek-v3 gemini-2.5-pro
Input / 1M tokens $0.27 (78% cheaper) $1.25
Output / 1M tokens $1.10 (89% cheaper) $10.00
Cached input / 1M $0.07 $0.13
Context window 66kk tokens 1049kk tokens
Max output 8kk 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 Deepseek V3 Gemini 2.5 Pro Winner
Small
1M in / 0.2M out
$0.49 $3.25 Deepseek V3 saves 85%
Medium
10M in / 2M out
$4.90 $32.50 Deepseek V3 saves 85%
Large
100M in / 20M out
$49.00 $325 Deepseek V3 saves 85%

Category winners

Cheapest input
Deepseek V3
$0.27/M · 78% less than the other
Cheapest output
Deepseek V3
$1.10/M · 89% less than the other
Larger context
Gemini 2.5 Pro
1049kk tokens · 1500% larger window
More features
Gemini 2.5 Pro
5 / 5 capabilities

Better for…

High-volume RAG & repeated context
$0.07/M cached input — prompt caching makes repeated context retrieval significantly cheaper
Deepseek V3
Short interactions & high-throughput APIs
$1.10/M output — 89% cheaper on output at scale
Deepseek V3
Long-document processing & large codebases
1049k context window vs 66k — 1500% larger context
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

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.