open-source

Llama 4 Maverick 17b 128e Instruct 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 Llama 4 Maverick 17b 128e Instruct Gemini 2.5 Pro
Provider groq vertex ai-language-models
Model ID groq/meta-llama/llama-4-maverick-17b-128e-instruct gemini-2.5-pro
Input / 1M tokens $0.20 (84% cheaper) $1.25
Output / 1M tokens $0.60 (94% cheaper) $10.00
Cached input / 1M $0.13
Context window 131kk 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 Llama 4 Maverick 17b 128e Instruct Gemini 2.5 Pro Winner
Small
1M in / 0.2M out
$0.32 $3.25 Llama 4 Maverick 17b 128e Instruct saves 90%
Medium
10M in / 2M out
$3.20 $32.50 Llama 4 Maverick 17b 128e Instruct saves 90%
Large
100M in / 20M out
$32.00 $325 Llama 4 Maverick 17b 128e Instruct saves 90%

Category winners

Cheapest input
Llama 4 Maverick 17b 128e Instruct
$0.20/M · 84% less than the other
Cheapest output
Llama 4 Maverick 17b 128e Instruct
$0.60/M · 94% less than the other
Larger context
Gemini 2.5 Pro
1049kk tokens · 700% 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
$0.60/M output — 94% cheaper on output at scale
Llama 4 Maverick 17b 128e Instruct
Long-document processing & large codebases
1049k context window vs 131k — 700% 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.