GPT-5 mini

GA

by OpenAI · GPT-5 family · best for superseded legacy mini, migrate to GPT-5.4 nano

Cost-OptimizedMultimodal
5.8
AI Panel Score
Value 6.0/10

GPT-5 mini is the original mini-tier sibling to GPT-5, released 2025-08-07 — the model that established the family's mini pricing tier at $0.25/$2.00. It remains GA, but it occupies the rare position of being beaten on both quality and cost simultaneously: GPT-5.4 nano is cheaper ($0.20/$1.25) and scores higher on SWE-bench Pro (52.4% vs 45.7%) and GPQA Diamond (82.8% vs 81.6%). The one-sentence buyer's take: a competent legacy model with no clear advantage today — migration to GPT-5.4 nano or mini is the only correct strategic action. - Provider: OpenAI - Release: 2025-08-07 - Status: GA (superseded by GPT-5.4 mini) - Context: 400,000 tokens - Max output: 128,000 tokens - Modalities: text + image in, text out - Knowledge cutoff: 2024-05 - Headline price: $0.25 in / $2.00 out per 1M tokens

What's new

  • GPT-5 mini was the original cost-efficient mini-tier model and established the "mini" pricing tier for the family at $0.25/$2.00 with a 400K context and 128K max output. It inherited the reasoning-effort dial from GPT-5 base and shipped the Responses API tool surface (web search, file search, image generation, code interpreter, MCP). As a 2025 model it predates the GPT-5.4 generation's native computer use, apply_patch, and skills. Its defining "what's new" today is unfortunately what's behind: it is the one model in the in-scope lineup superseded on both quality and cost at once.

Benchmarks

BenchmarkScoreSource
GPQA Diamond81.6%datacamp.com 2025-08-07T00:00:00.000Z

AI Panel Review

Six personas, six verdicts — the same panel that reviews every product on TopReviewed.

Decision Maker5/10
Outperformed and out-priced at once — there's essentially no architectural rationale to start a new build here.

GPT-5 mini is in an uncomfortable position: it has been outperformed and out-priced simultaneously. GPT-5.4 nano is cheaper ($0.20 vs $0.25 input) and scores higher on SWE-bench Pro and GPQA Diamond. There is essentially no architectural rationale to start a new build on GPT-5 mini today. The only reasons to keep it are in-flight workloads where re-validation costs more than the delta, and fine-tuning (which the 5.4 generation lacks). Migration to GPT-5.4 nano or mini should be on the roadmap for any team still here.

Strategic Fit 5Vendor Risk 6Roadmap Confidence 6
Pros
  • cheap
  • fine-tuning
Cons
  • out-priced and out-performed by 5.4 nano
Right for: in-flight and fine-tuned workloads
Avoid if: starting a new build
Domain Strategist5.5/10
A model with no wedge left — every competitive axis points to GPT-5.4 nano or mini, leaving only fine-tuning and inertia.

Strategically, GPT-5 mini has no remaining wedge. On cost, GPT-5.4 nano undercuts it; on quality, both 5.4 nano and 5.4 mini beat it; on tooling, the newer generation has computer use and apply_patch. Its only differentiation is fine-tuning at the mini tier. Positioning is purely transitional, and market timing has passed entirely — it competes in 2026 as a 2025 model that its own successors have lapped on both price and capability.

Competitive Positioning 5Differentiation 5Market Timing 5
Pros
  • fine-tuning niche
Cons
  • no cost or quality wedge
Right for: fine-tuned mini deployments
Avoid if: you want any competitive edge
Finance Lead6/10
Cheap, but GPT-5.4 nano is cheaper and benchmarks better — there's no finance case to remain on it for new spend.

At $0.25/$2.00 with 90% cached discount and 50% Batch, GPT-5 mini is cheap. But GPT-5.4 nano is cheaper still — $0.20/$1.25 — and benchmarks slightly better on coding and reasoning. There is no finance case to remain for new spend. For sunk-cost in-flight workloads, run the migration math: a predictable prefix-cached pipeline typically saves 20–30% moving to GPT-5.4 nano on equivalent traffic. Plan migration within the quarter unless fine-tuning ties you here.

Cost Efficiency 6Pricing Transparency 8Value per Dollar 6
Pros
  • cheap
  • deep discounts
  • fine-tuning
Cons
  • nano is cheaper and better
Right for: sunk-cost workloads
Avoid if: optimizing new spend
Domain Practitioner6/10
Behaves like any family model at the SDK level — but GPT-5.4 nano gives the same role, cheaper, with better behavior.

At the SDK level GPT-5 mini behaves like any Responses-API model in the family. The missing pieces — computer use, apply_patch, skills — limit it from real agent work, but that was never the mini role. The honest take: GPT-5.4 nano gives the same operational role with better behavior at lower cost, and GPT-5.4 mini gives a real capability jump for ~3x the price. Either is a better target than staying. The one developer reason to remain is an existing fine-tune.

API Ergonomics 8Tool/Agent Support 6Reliability 7
Pros
  • familiar API
  • fine-tuning
  • stable
Cons
  • dominated by 5.4 nano on cost and behavior
Right for: existing fine-tunes
Avoid if: you can re-train on a newer base
Power User6/10
Invisible to ChatGPT users for nearly a year — fast and adequate where it surfaces, thin the moment depth or current knowledge is needed.

End users do not pick GPT-5 mini — it surfaces inside backend services in API-backed products. Where it does, the experience is fast and adequate for simple tasks. For anything requiring depth or current knowledge, the gaps versus the GPT-5.4 family show through quickly, and the 2024-05 cutoff is the oldest in the lineup. The model is essentially invisible to ChatGPT users; it has been routed around for almost a year.

Output Quality 6Speed 8Everyday Usefulness 6
Pros
  • fast
  • adequate for simple tasks
Cons
  • thin on depth
  • stale knowledge
Right for: simple backend tasks
Avoid if: users need current or deep answers
Skeptic5.5/10
The clearest 'migrate now' case in the lineup — its own cheaper successor beats it on the benchmarks OpenAI chose to publish.

The adversarial read is also the consensus read: GPT-5 mini is the one model where the skeptic and the vendor agree you should leave. Its own cheaper successor (GPT-5.4 nano) beats it on the two benchmarks anyone published. The 2024-05 cutoff is the lineup's oldest. The only non-inertia reason to stay is fine-tuning, and even that is a question of whether re-training on a newer base is worth it. There is no marketing claim to dispute here because OpenAI isn't really marketing this model anymore — it's a migration-continuity SKU.

Claim Accuracy 7Weakness Severity 5Hype vs Reality 6
Pros
  • honest, undisputed positioning
  • fine-tuning
Cons
  • dominated on cost and quality
  • stale
Right for: skeptics auditing a migration
Avoid if: you have any alternative

Strengths

  • Very cheap: $0.25/$2.00 with 90% cached-input discount.
  • 400K context, 128K output — generous for the tier.
  • Stable API behavior, mature SDK support.
  • Supports fine-tuning (GPT-5.4 mini does not).
  • Lower latency than GPT-5 base.

Limitations

  • Beaten on SWE-bench Pro and GPQA Diamond by GPT-5.4 nano, which is cheaper.
  • 2024-05 knowledge cutoff — oldest in the in-scope lineup.
  • No computer use, no apply_patch, no skills.
  • Superseded for both quality and cost — the rare model with no clear advantage today (except fine-tuning).
  • Not user-facing in ChatGPT default routing.

Best use cases

- In-flight production workloads that have not yet migrated. - Fine-tuning use cases at the mini tier (GPT-5.4 mini does not offer fine-tuning). - Cost-sensitive backend pipelines where migration cost still exceeds the savings (rare). - Bridge SKU during GPT-5 to GPT-5.4 family migration with staged rollout.

Buyer questions

Should I use GPT-5 mini for a new build?

No — GPT-5.4 nano is cheaper and benchmarks better; GPT-5.4 mini is a real capability jump. Pick one of them.

Is it being retired?

The base mini model is not on the deprecation list as of 2026-05-28, but it is fully superseded; treat it as migration-only.

Any reason to stay?

Fine-tuning at the mini tier (GPT-5.4 mini does not offer it) and sunk-cost in-flight workloads.

How stale is it?

The 2024-05 cutoff is ~24 months — the oldest in the in-scope lineup. Time-sensitive work needs web search.

What does migration save?

Typically 20–30% on equivalent prefix-cached traffic moving to GPT-5.4 nano, plus better quality.

Is my data used for training?

No, not by API default; enterprise opt-out and zero-retention exist.

Comparable models

**OpenAI GPT-5.4 nano** — cheaper successor at $0.20/$1.25 with better SWE-bench Pro and GPQA; the default migration target.
**OpenAI GPT-5.4 mini** — higher-capability successor at $0.75/$4.50 with computer use and a real quality jump.
**Anthropic Claude Haiku 4.5** — generational peer from the 2025 cohort; comparable role.

Model specs

Input price
$0.25 / Mtok
Output price
$2 / Mtok
Cached input
$0.03 / Mtok
Batch (in/out)
$0.13 / $1
Context window
400K tokens
Max output
128K tokens
Knowledge cutoff
2024-05
Released
2025-08-06
Modalities
text, image → text
Output speed
~150 tok/s
License
Proprietary
Clouds
Azure OpenAI, Azure AI Foundry

Does not train on API inputs by default

Last verified 2026-05-27