ModelPriceWatch.com
Last scan 2026-08-15 Models tracked 205 Providers 31 Cheapest paid Granite 4.0 H Micro $0.017/Mtok in Every price links to its source

GPT-4.1 mini vs Gemini 2.5 Flash

Side-by-side comparison of API pricing, specs, benchmarks, and capabilities

GPT-4.1 mini is 17.6% cheaper on blended cost ($0.700 vs $0.850/Mtok)
Specification
Overview
StatusCurrent budget Deprecated budget
Released Apr 14, 2025 Jun 17, 2025
Pricing per million tokens
Input $0.400/Mtok $0.300/Mtok
Output $1.60/Mtok $2.50/Mtok
Blended avg $0.700/Mtok $0.850/Mtok
Cached input $0.100/Mtok
Specifications
Context window 1M tokens 1M tokens
Parameters Proprietary Proprietary
Speed (TPS)
Modalities
Input
textimage
textimageaudiovideo
Benchmarks source: Vellum LLM Leaderboard
Avg benchmark score 55.7 50.2
Perf / dollar 79.6 59.1
GPQA Diamond 65 78.3
SWE-Bench Verified 30 vendor 38
Humanity's Last Exam 12 vendor 12.1
ARC-AGI 2 15 vendor 15
AIME 2025 40 vendor 78
MMMLU 78.5 78
MATH 500 70 vendor 72
Terminal-Bench 2.1 16.9
LiveCodeBench 63.5
BFCL 70 vendor
HumanEval 23.6
Independent composite scores each on its own scale — not part of the average above
LMSYS Chatbot Arena 1382.8 ELO 1410.2 ELO
AA Intelligence Index 14.8
AA Agentic Index 1.8
AA-Omniscience Index (−100–100) -53.6
Providers
Available from
OpenAI — $0.400/$1.60/Mtok
Google — $0.300/$2.50/Mtok

Cost at scale

1M tokens · 50/50 input/output
Projected cost of GPT-4.1 mini vs Gemini 2.5 Flash at increasing token volumes
VolumeGPT-4.1 miniGemini 2.5 FlashSavings
1M tokens $0.7 $0.85 $0.15 (17.6%)
10M tokens $7 $8.5 $1.5 (17.6%)
100M tokens $70 $85 $15 (17.6%)
1000M tokens $700 $850 $150 (17.6%)

When to pick which

distilled from the pricing and spec data above
Pick GPT-4.1 mini if…
  • cost dominates: $0.700/Mtok blended vs $0.850 — 17.6% less on the same 50/50 token mix
  • your workload re-reads context (agents, RAG, long chats): cached input costs $0.100/Mtok — 75% off its list input price, a discount Gemini 2.5 Flash doesn't offer
  • raw capability matters more than price: 55.7 vs 50.2 average benchmark score
Pick Gemini 2.5 Flash if…
  • this pairing gives Gemini 2.5 Flash no edge on price, context, cache discount, or measured performance — pick it only for qualitative fit (ecosystem, compliance, model behavior on your prompts)

Price movement

recorded changes since we began tracking each model · last checked Aug 15, 2026
Recorded price changes for GPT-4.1 mini and Gemini 2.5 Flash — how many moves, the direction and date of the latest one, and its old → new prices per million tokens
Model Changes Latest move Old → new $/M
GPT-4.1 mini 0 — no move Stable since we began tracking — no change recorded
Gemini 2.5 Flash 2 price rise on Jul 4, 2026 $0.075/$0.3 → $0.3/$2.5/Mtok
Only Gemini 2.5 Flash has changed price since we began tracking; GPT-4.1 mini has held steady. See all recent price moves → MODELPRICEWATCH.COM · 2026-08-15
Try GPT-4.1 mini on OpenAI

The cheaper option here — GPT-4.1 mini costs $0.700/Mtok blended on OpenAI.

Get API key →

Summary

GPT-4.1 mini by OpenAI costs $0.400/Mtok input and $1.60/Mtok output, with a 1M-token context window. It supports text, image input.

Gemini 2.5 Flash by Google costs $0.300/Mtok input and $2.50/Mtok output, with a 1M-token context window. It supports text, image, audio, video input.

On a blended cost basis, GPT-4.1 mini is 17.6% cheaper than Gemini 2.5 Flash.

On benchmarks, GPT-4.1 mini scores higher (55.7 vs 50.2) on average. In terms of value, GPT-4.1 mini has better performance per dollar (79.6 vs 59.1).

Note: Pricing is per million tokens. Actual costs vary with usage patterns, prompt caching, and batch discounts. Always verify against official provider pricing pages.

More comparisons

pairs sharing a model with this page