GPT/Fast / Budget

GPT 5 Mini

GPT 5 Mini is GPT's fastest and most affordable model, priced at $0.25/MTok input and $2.00/MTok output with a 272K context window. Backfilled on 2026-09-23. Prices confirmed by the provider pricing page and the LiteLLM cross-check. Release date not published in a machine-readable source. Not yet benchmarked, so never recommended.

Input $/MTok

$0.25

Output $/MTok

$2.00

Context window

272K

Cache read discount

90% off

GPT 5 Mini pricing breakdown

RateInput $/MTokOutput $/MTok
Standard$0.25$2.00
Cached read (90% off input)$0.03-
Cached write (no surcharge)$0.25-
Batch (50% off)$0.13$1.00

All rates in USD per million tokens. Prices verified against provider documentation.

GPT 5 Mini task benchmarks

Confidence scores (0-100) and cross-provider rank for each task type. Rank 1 is best across all 72 models.

Not benchmarked. The third-party benchmark source used for confidence scores does not cover GPT models yet. Scores will appear here once independent benchmarks are published.

GPT 5 Mini cost by use case

Estimated cost per API call using default token counts for each workload.

Use caseInput tokensOutput tokensCost / call
Code Generation2,0004,000$0.008500
Unit Test Generation3,0005,000$0.0108
SQL Generation1,5001,000$0.002375
API Generation3,0006,000$0.0128
Code Refactoring4,0004,000$0.009000
Code Review5,0002,000$0.005250
PR Review8,0003,000$0.008000
Security Review6,0002,500$0.006500
Bug Detection5,0002,000$0.005250
Document Summarization10,0001,000$0.004500
PDF Summarization15,0001,500$0.006750
Meeting Notes8,0002,000$0.006000

Monthly cost projections

Projected monthly spend at different call volumes, using code generation as a representative workload (2,000 input / 4,000 output tokens per call).

Calls / monthWithout cachingWith caching (90% read discount)
1K$8.5$8.18
10K$85$81.85
100K$850$818.5
500K$4,250$4,092.5
1M$8,500$8,185

Caching estimate assumes 70% of input tokens are cache reads. Your actual cache hit rate will depend on prompt structure and reuse.

Fast / Budget alternatives to GPT 5 Mini

Same-tier models from other providers, sorted by input price.

ModelProviderInput $/MTokOutput $/MTokInput savings
Gemini 2.5 Flash-LiteGemini$0.10$0.4060% cheaper
Gemini 3.1 Flash-LiteGemini$0.25$1.50Same price
Gemini 3.5 Flash-LiteGemini$0.30$2.5020% more
Gemini 2.5 FlashGemini$0.30$2.5020% more
Gemini 3 FlashGemini$0.50$3.00100% more
Gemini 3.6 FlashGemini$0.75$3.75200% more
Gemini 3.7 FlashGemini$0.75$3.75200% more
Gemini 3.8 FlashGemini$0.75$3.75200% more
Claude Haiku 4.5Claude$1.00$5.00300% more
Gemini Robotics ER 2Gemini$1.00$5.00300% more
Grok Build 0.1Grok$1.00$2.00300% more
Gemini 2.5 Computer UseGemini$1.25$10.00400% more
Gemini 3.5 FlashGemini$1.50$9.00500% more
Gemini Omni 1.1 FlashGemini$1.50$9.00500% more
Gemini Omni FlashGemini$1.50$9.00500% more

Other GPT models

Track your GPT 5 Mini spend

See exactly how much you spend on GPT 5 Mini and where you can save. Two-line wrapper install, no API keys shared.