OpenAI
GPT-5 Mini
Best ValueOpenAI's small-but-smart model and the best value in the GPT-5 family. At $0.25/$2.00 per 1M tokens it costs 7× less than GPT-5.2 while delivering an AA Intelligence Index of 41 — higher than Claude Haiku and Gemini Flash. The 400K context window and multimodal input make it a strong default for cost-sensitive production pipelines.
Context window
400K tokens
API (blended)
$0.69/1M
Consumer access
Free (limited) / $8/mo
Multimodal
Yes
Score Breakdown
62.8/100 → 6.3/10Intelligence, Reliability, Speed, and Context are field-relative — scores shift as models are added. Accessibility and Trust are absolute checklists. Full methodology →
Strengths
- +Best price-to-performance in the GPT-5 family: AA Intelligence Index 41 at $0.69/1M blended
- +GPQA Diamond 82.8% and HLE 19.7% (AA-measured) — strong science reasoning for a small model
- +τ²-bench 68.4% and LiveCodeBench 83.8% (AA-measured) — solid coding and tool use
- +400K context — handles very long documents at a fraction of GPT-5.2's cost
- +Multimodal input: image understanding alongside text
- +75 t/s output speed (AA-measured) — faster than GPT-5.2
Weaknesses
- -Lower reasoning ceiling than GPT-5.2 — not suitable for complex multi-step tasks
- -No MCP support
- -Less reliable on nuanced instruction-following vs larger GPT-5 variants
Best for
Not ideal for
Pricing details
Subscription plans
API pricing
Prices verified February 2026. LLM pricing changes frequently — verify at the provider's site before budgeting.
Last updated: February 27, 2026