← Models

GPT-5 nano

OpenAI · GPT-5

Older ultra-low-cost GPT-5 tier now mainly useful for compatibility after GPT-5.4 nano became the recommended fresh-build route.

Part of GPT family · Other versions: GPT-5.6 Luna , GPT-5.6 Terra , GPT-5.6 Sol , GPT-5.5 Pro , GPT-5.5 , GPT-Rosalind , GPT-5.4 mini , GPT-5.4 nano , GPT-5.4 Pro , GPT-5.4 , GPT-5.3 , GPT-5.3-Codex , GPT-5.2-Codex , GPT-5.2 Pro , GPT-5.2 , GPT-5-Codex , GPT-5 mini , GPT-5 , GPT-4.1 , GPT-4o mini Transcribe , GPT-4o mini TTS , GPT-4o Transcribe , Computer Use Preview , GPT-4o mini , GPT-4o
Type
language
Context
400K tokens
Max Output
128K tokens
Status
legacy
Input
$0.05/1M tok
Output
$0.4/1M tok
API Access
Yes
License
proprietary
high-throughput low-cost classification automation tool-use
Released August 2025 · Updated June 8, 2026

Overview

Freshness note: Model capabilities, limits, and pricing can change quickly. This profile is a point-in-time snapshot last verified on June 8, 2026.

GPT-5 nano is a budget-first GPT-5 family tier intended for large-scale operational workloads. It is useful when latency and per-request cost dominate, and tasks are structured enough to avoid needing deep multi-step reasoning. OpenAI still lists it for API use, but its current docs now recommend GPT-5.4 nano for most new speed- and cost-sensitive builds.

Capabilities

The model works well for classification, routing, normalization, lightweight extraction, and short transformation tasks. It can also support simple coding and templated content tasks when instructions are precise.

Technical Details

GPT-5 nano sits at the high-throughput edge of the older GPT-5 lineup with a 400K context window, 128K max output, image input, and support for common Responses API tools. Teams should design prompts and guardrails for determinism and brevity to maximize cost-performance.

Pricing & Access

Available through OpenAI API channels where GPT-5 variants are exposed. Published text-token pricing remains 0.05per1Minputtokens,0.05 per 1M input tokens, 0.005 per 1M cached input tokens, and $0.40 per 1M output tokens. For new deployments, GPT-5 nano is best treated as the older ultra-cheap baseline that now sits below GPT-5.4 nano.

Best Use Cases

Ideal for preprocessing pipelines, event labeling, ticket triage, content normalization, and background automation where very high request volume is expected.

Comparisons

Compared with GPT-5.4 nano, GPT-5 nano is cheaper but less capable on current coding and tool-heavy workloads. Compared with GPT-5 mini, GPT-5 nano prioritizes cost and throughput over richer reasoning depth. Compared with Gemini 2.5 Flash-Lite, tradeoffs are primarily ecosystem, latency, and output-style preferences.