Scheduled for retirement on Feb 9, 2027. Still available at the prices below until then.
Context
5M
Max output
128K
Serving providers
8
Cheapest input
$0.05 /1M
On-demand listed rates, OpenRouter routed quotes and Vercel reseller quotes. Enterprise commitments (committed-use discounts, provisioned throughput, negotiated rates) can be materially lower.
Benchmarks
independent evaluations · source: Artificial AnalysisSpeed & latency
Output speed
196 t/s
tokens / second
Time to first token
66.02s
latency
Headline indices
Individual benchmarks · click a row for effort variants
| Benchmark | Best score | Effort | Cost / task | |||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| CritPt | 0% | minimal | — | |||||||||||||||||
| ||||||||||||||||||||
| GPQA Diamond | 68% | default | — | |||||||||||||||||
| ||||||||||||||||||||
| Humanity's Last Exam | 9% | default | — | |||||||||||||||||
| ||||||||||||||||||||
| IFBench | 68% | default | — | |||||||||||||||||
| ||||||||||||||||||||
| LiveCodeBench | 79% | default | — | |||||||||||||||||
| ||||||||||||||||||||
| Long-Context Reasoning | 45% | default | — | |||||||||||||||||
| ||||||||||||||||||||
| MMLU-ProFrozen Aug 18, 2026 | 78% | default | — | |||||||||||||||||
| ||||||||||||||||||||
| MMMU-Pro | 61% | default | — | |||||||||||||||||
| ||||||||||||||||||||
| Omniscience | -25.8 | medium | — | |||||||||||||||||
| ||||||||||||||||||||
| Omniscience Accuracy | 0.2 | default | — | |||||||||||||||||
| ||||||||||||||||||||
| Omniscience Non Hallucination | 0.5 | medium | — | |||||||||||||||||
| ||||||||||||||||||||
| SciCodeArtificial Analysis did not report this score in its latest run on Oct 14, 2026 | 37% | — | — | |||||||||||||||||
| ||||||||||||||||||||
| TerminalBench Hard | 17% | medium | — | |||||||||||||||||
| ||||||||||||||||||||
| τ²-bench | 37% | default | — | |||||||||||||||||
| ||||||||||||||||||||
Artificial Analysis last published scores for this benchmark on Aug 18, 2026. Scores here are frozen at that date, and models released since are not on it.
Pricing by serving provider
standard tier · per 1M tokens · click a provider to expandInput pricing runs from $0.05 to $0.15 per 1M tokens across 8 providers, so the dearest route costs 200% more than the cheapest for the same model.
| Serving provider | Input /1M | Output /1M | Endpoints | |||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| DatabricksCheapest | $0.05 | $0.40 | 1 | |||||||||||||||||
Standarddatabricks/databricks-gpt-5-nano
| ||||||||||||||||||||
| Azure | $0.05 | $0.40 | 1 | |||||||||||||||||
Standardazure/gpt-5-nano
| ||||||||||||||||||||
| OCI | $0.05 | $0.40 | 1 | |||||||||||||||||
Standardoci/openai.gpt-5-nano
| ||||||||||||||||||||
| OpenAI | $0.05 | $0.40 | 1 | |||||||||||||||||
Standardgpt-5-nano
| ||||||||||||||||||||
| OpenRouter | $0.05 | $0.40 | 1 | |||||||||||||||||
Standardopenai/gpt-5-nano
| ||||||||||||||||||||
| Replicate | $0.05 | $0.40 | 1 | |||||||||||||||||
Standardreplicate/openai/gpt-5-nano
| ||||||||||||||||||||
| VercelVercel reseller quote | $0.05 | $0.40 | 1 | |||||||||||||||||
Standardopenai/gpt-5-nano
| ||||||||||||||||||||
| Snowflake | $0.15 | $0.60 | 1 | |||||||||||||||||
Standardsnowflake/openai-gpt-5-nano
| ||||||||||||||||||||
| Snowflake is dearest at $0.15 / $0.60 | ||||||||||||||||||||
Price history
listed seller prices, input and output per 1M tokens Input Output
Cost calculator
estimate your monthly spend on this model$42
estimated / month
Model IDs
copy the exact identifier for your platformopenai/gpt-5-nano:batchopenai/gpt-5-nanodatabricks/databricks-gpt-5-nanooci/openai.gpt-5-nanoreplicate/openai/gpt-5-nanoopenai/gpt-5-nanogpt-5-nanoopenai/gpt-5-nanoazure/gpt-5-nanosnowflake/openai-gpt-5-nano
Frequently asked questions
GPT-5 Nano pricing, context and availabilityIs GPT-5 Nano still available?
Yes. GPT-5 Nano is scheduled for retirement on 2027-02-09.
How much does GPT-5 Nano cost?
GPT-5 Nano costs $0.05 per 1M input tokens from Databricks, and $0.40 per 1M output tokens from Databricks. Across 8 serving providers, input prices range from $0.05 to $0.15 per 1M tokens.
What is the context window of GPT-5 Nano?
GPT-5 Nano accepts up to 5M tokens of context and can return up to 128K output tokens.
Which providers serve GPT-5 Nano?
GPT-5 Nano is available from 8 serving providers, each with its own pricing and model ID. Databricks is currently the cheapest.
What can GPT-5 Nano do?
GPT-5 Nano supports image input (vision), tool use, reasoning, prompt caching, structured output and web search.
Other OpenAI models
compare pricing across the OpenAI lineupPopular comparisons
head-to-head pages featuring GPT-5 Nano Listed prices from LiteLLM, OpenRouter and Vercel · last checked Oct 14, 2026
Every weekday
AI moves fast. Here's your debrief.
News, analysis, tools, and more.
For people who build with AI