Model comparison

Gemini 3.1 Pro Preview vs Llama 4 Maverick

Compare Gemini 3.1 Pro Preview vs Llama 4 Maverick API pricing: input/output token costs, cache pricing, context windows, workload estimates, and routing fit.

Gemini 3.1 Pro Preview

gemini · gemini/gemini-3.1-pro-preview

Input
$2
Output
$12
Context
1M

Llama 4 Maverick

deepinfra · deepinfra/meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8

Input
$0.15
Output
$0.6
Context
1M

Quick take

Llama 4 Maverick has the lower input price at $0.15 per 1M input tokens. Llama 4 Maverick is cheaper for the example blended workload below. Gemini 3.1 Pro Preview has the larger context window at 1M tokens.

Choose Gemini 3.1 Pro Preview if...

  • Gemini 3.1 Pro Preview is stronger when the same large prompt or document is reused because it supports prompt caching.
  • Gemini 3.1 Pro Preview is required if images, screenshots, or visual documents are part of the workflow.

Choose Llama 4 Maverick if...

  • Llama 4 Maverick is the better default for cost-sensitive traffic and repeated high-volume calls.
  • Llama 4 Maverick gives more room for long generated answers, reports, or code output.

Example workload cost

Estimates use input tokens plus 20% output tokens. They exclude provider discounts, cache hits, and tool/search surcharges.

Workload Gemini 3.1 Pro Preview Llama 4 Maverick Cheaper
1M input + 200K output $4.40 $0.27 Llama 4 Maverick
10M input + 2M output $44.00 $2.70 Llama 4 Maverick
100M input + 20M output $440.00 $27.00 Llama 4 Maverick

Context, output, and capability fit

Gemini 3.1 Pro Preview provides the larger context window. Check max output separately when the task needs long reports, code generation, or full-document rewrites.

Gemini 3.1 Pro Preview max output
65.5K
Llama 4 Maverick max output
1M
Gemini 3.1 Pro Preview features
prompt caching, function calling, vision
Llama 4 Maverick features
function calling

Risk notes for Gemini 3.1 Pro Preview

  • Preview or beta model: verify availability and pricing before production rollout.

Risk notes for Llama 4 Maverick

  • No prompt caching in this snapshot: repeated long-context calls may be more expensive.

Routing tags

frontierpreviewreasoninglong-contextmultimodalenterprise-ragragopen-weightcodingagentslocal-open

Related comparisons