ModelRefs / GPT-5 Nano by OpenAI — Benchmarks, Pricing & Review (2026)

GPT-5 Nano by OpenAI — Benchmarks, Pricing & Review (2026)

GPT-5 Nano (OpenAI): GPT-5 Nano is OpenAI's smallest and most affordable GPT-5 family model, designed for edge deployments and ultra-high-throughput pipeline…

What this reference supports

GPT-5 Nano is the smallest hosted member of OpenAI's GPT-5 API family, positioned for very high-volume, latency- and cost-sensitive workloads that still benefit from the family's instruction-following and tool-use surface. The central implementation decision is where Nano's quality ceiling makes it the right routing target versus GPT-5 Mini.

GPT-5 Nano is attributed to OpenAI in ModelRefs' canonical registry. Tracked modalities: Text input and output, Image input. Primary use cases considered on ModelRefs: High-throughput classification, extraction, and summarization pipelines; Latency-critical assistants and routing layers with measured quality floors.

This ModelRefs profile is Provisional and pending review — decision-support material, not a final or universal ranking. Confirm current behavior, access, pricing, limits, licensing, and lifecycle in OpenAI's own documentation, and evaluate GPT-5 Nano on representative workloads before implementation.

Benchmark & Evaluation

ModelRefs does not yet hold qualifying sourced benchmark evidence for GPT-5 Nano, so its benchmark coverage is incomplete. Treat any benchmark discussion as provisional and confirm results on representative workloads before selecting it.

  • No benchmark score is imported into this editorial record. Provider-reported evaluations support scoped notes only; canonical score records are governed separately with their own provenance.
  • System-card evaluations are reported at family and variant level with methodology caveats; no variant result is transferred by this record.

Implementation considerations

  • Establish task-level quality floors before routing volume to Nano; small-variant behavior on hard inputs diverges from family-level claims.
  • Pin dated snapshots and re-evaluate when defaults advance; cost savings can be erased by retry loops if quality is marginal.
  • Hosted through eligible OpenAI API endpoints.
  • Verify current model status, endpoint support, quotas, and rates for the exact account before rollout.

Risks and limitations

  • Hosted-model behavior, quotas, pricing, and data controls can change without a client-side version pin unless a dated snapshot is used.
  • Provider-reported capabilities require task-specific evaluation before production reliance.

Source coverage

This reference is Provisional. Model behavior, access, pricing, limits, and lifecycle can change; verify the linked provider documentation and run task-specific evaluations before implementation.

Known coverage gaps:

  • Variant-specific independent evaluations are not attached.
  • Task-level routing evidence versus GPT-5 Mini is incomplete.

Sources

Continue your research

Use these connected ModelRefs sections to compare alternatives, inspect implementation paths, and review the evidence and governance boundaries relevant to GPT-5 Nano by OpenAI — Benchmarks, Pricing & Review (2026).