GPT-5 Nano
GPT-5-Nano is the smallest and fastest variant in the GPT-5 system, optimized for developer tools, rapid interactions, and ultra-low latency environments. While limited in reasoning depth compared to its larger counterparts, it retains key instruction-following and safety features. It is the successor to GPT-4.1-nano and offers a lightweight option for cost-sensitive or real-time applications.
- Organization
- OpenAI
- Family
- gpt-nano
- Providers
- 20
- Context
- 400,000
- Output limit
- 128,000
- Knowledge
- 2024-05-30
- Release
- 2025-08-07
- Updated
- 2025-08-07
- Weights
- Closed
- Input
- text, image
- Output
- text
- Capabilities
- Tools, Reasoning, Structured
Providers
Compare every cataloged offer for this model, including its provider, route, token limits, price, and capabilities.
| Provider | Model ID | Context | Output | Input / output · 1M | Reasoning | Tools | Structured | Details |
|---|---|---|---|---|---|---|---|---|
| Abacus | gpt-5-nano | 400,000 | 128,000 | $0.05 / $0.40 | Yes | Yes | Yes | View |
| Cloudflare AI Gateway | openai/gpt-5-nano | 128,000 | 128,000 | $0.05 / $0.40 | Yes | Yes | Yes | View |
| Cortecs | gpt-5-nano | 400,000 | 128,000 | $0.06 / $0.439 | Yes | Yes | No | View |
| Databricks | databricks-gpt-5-nano | 400,000 | 128,000 | $0.05 / $0.40 | Yes | Yes | Yes | View |
| DevPass (LLM Gateway) | gpt-5-nano | 400,000 | 128,000 | $0.05 / $0.40 | Yes | Yes | Yes | View |
| Eden AI | openai/gpt-5-nano | 400,000 | 128,000 | $0.05 / $0.40 | Yes | Yes | Yes | View |
| Impossibl | openai/gpt-5-nano | 400,000 | 128,000 | $0.05 / $0.40 | Yes | Yes | Yes | View |
| Kilo Gateway | openai/gpt-5-nano | 400,000 | 128,000 | $0.05 / $0.40 | Yes | Yes | Yes | View |
| LLM Gateway | openai/gpt-5-nano | 400,000 | 128,000 | $0.05 / $0.40 | Yes | Yes | Yes | View |
| LLM Gateway | azure/gpt-5-nano | 400,000 | 128,000 | $0.05 / $0.40 | Yes | Yes | Yes | View |
| Merge Gateway | openai/gpt-5-nano | 400,000 | 128,000 | $0.05 / $0.40 | Yes | Yes | Yes | View |
| NanoGPT | openai/gpt-5-nano | 400,000 | 128,000 | $0.05 / $0.40 | Yes | No | No | View |
| NEAR AI Cloud | openai/gpt-5-nano | 400,000 | 128,000 | $0.05 / $0.40 | Yes | Yes | Yes | View |
| Neon | gpt-5-nano | 400,000 | 128,000 | $0.05 / $0.40 | Yes | Yes | Yes | View |
| Ofox | openai/gpt-5-nano | 400,000 | 128,000 | $0.04 / $0.32 | No | Yes | Yes | View |
| Azurevia OpenRouter | openai/gpt-5-nano unknown | 400,000 | 360,000 | $0.055 / $0.44 | Yes | Yes | Yes | View |
| Azurevia OpenRouter | openai/gpt-5-nano unknown | 400,000 | 360,000 | $0.05 / $0.40 | Yes | Yes | Yes | View |
| OpenAIvia OpenRouter | openai/gpt-5-nano unknown | 400,000 | 128,000 | $0.05 / $0.40 | Yes | Yes | Yes | View |
| OpenAIvia OpenRouter | openai/gpt-5-nano unknown | 400,000 | 128,000 | $0.025 / $0.20 | Yes | Yes | Yes | View |
| OrcaRouter | openai/gpt-5-nano | 400,000 | 128,000 | $0.05 / $0.40 | Yes | Yes | Yes | View |
| Pioneer | gpt-5-nano | 400,000 | 128,000 | $0.05 / $0.40 | Yes | Yes | Yes | View |
| Requesty | gpt-5-nano@eu | 200,000 | 100,000 | $0.055 / $0.44 | Yes | Yes | Yes | View |
| SAP AI Core | gpt-5-nano | 400,000 | 128,000 | $0.05 / $0.40 | Yes | Yes | Yes | View |
| Snowflake Cortex | openai-gpt-5-nano | 272,000 | 8,192 | — / — | Yes | Yes | Yes | View |
Prices and limits apply to each offer. A dash means the value is not provided. OpenRouter offers show the hosting provider and routing channel separately.
Pricing
Compare token rates and cache charges across available routes and hosting configurations.
Lowest listed input and output prices across the offers above; they may belong to different providers. These are base rates, before conditional pricing, discounts or additional fees.
openai/gpt-5-nanoObserved - Input
- $0.05
- Output
- $0.40
- Cache read
- $0.005
Additional fees and pricing conditions
- web search
- $0.01 / search
Hosting prices through OpenRouter All endpoints and cache rates
| Endpoint | Input / 1M | Output / 1M | Cache read / 1M | Cache write / 1M |
|---|---|---|---|---|
| Azureazure/swedencentral | $0.055 | $0.44 | $0.011 | — |
| Azureazure | $0.05 | $0.40 | $0.01 | — |
| OpenAIopenai | $0.05 | $0.40 | $0.005 | — |
| OpenAIopenai/flex | $0.025 | $0.20 | $0.0025 | — |
Each row is a hosting configuration. Open an offer in Providers for its full pricing conditions and additional fees. Endpoint observations may differ from the routing catalog's base price.
Performance
Review reported latency and output-throughput percentiles from the latest observed rolling window.
Time to first token · milliseconds
All latency percentiles 4 endpoints
| Endpoint | P50 | P75 | P90 | P99 |
|---|---|---|---|---|
| Azureazure/swedencentral | 867 ms | 1,032 ms | 1,694 ms | 3,473.8 ms |
| Azureazure | 1,931.5 ms | 2,853.25 ms | 4,079.2 ms | 7,609.73 ms |
| OpenAIopenai | 2,602.5 ms | 5,418.25 ms | 8,275.5 ms | 14,286.07 ms |
| OpenAIopenai/flex | 1,092 ms | 1,694 ms | 2,404.9 ms | 3,732.45 ms |
Output throughput · tokens per second
All throughput percentiles 4 endpoints
| Endpoint | P50 | P75 | P90 | P99 |
|---|---|---|---|---|
| Azureazure/swedencentral | 167 t/s | 180.25 t/s | 194 t/s | 217.94 t/s |
| Azureazure | 117 t/s | 161 t/s | 200 t/s | 258.06 t/s |
| OpenAIopenai | 115 t/s | 137 t/s | 155 t/s | 178 t/s |
| OpenAIopenai/flex | 141 t/s | 198 t/s | 233 t/s | 275 t/s |
Percentiles describe the observed request distribution. These are snapshots of a rolling window, not a historical time series.
Uptime
Compare successful request rates across the latest 5-minute, 30-minute, and 24-hour observations.
Reported by OpenRouter at the time of collection; rate-limited requests are excluded. A dash means no measurement was reported. This is not a live availability check.
Benchmarks
Review attributed evaluation results on each source's original scale.
openai/gpt-5-nanoObserved | Design Arena | Category | Elo | Win rate | Rank |
|---|---|---|---|---|
| models | 3d | 981 | 36.3% | 108 |
| models | codecategories | 1,090 | 48% | 96 |
| models | dataviz | 1,064 | 46.2% | 101 |
| models | gamedev | 1,057 | 46.5% | 100 |
| models | uicomponent | 1,073 | 51.9% | 96 |
| models | website | 1,108 | 48.9% | 97 |
Sources: Artificial Analysis and Design Arena, via OpenRouter. Scores retain their original scales and are not OpenAI Suite ratings.
Detailed evaluations
| Evaluation | Configuration | Source | Results | Details |
|---|---|---|---|---|
| models · dataviz | GPT-5 nano (Default)openai/gpt-5-nano-2025-08-07 | Design Arena | 1,064 Elo | Details |
| gpqa diamond | OpenAI: GPT-5 Nanoopenai/gpt-5-nano-2025-08-07 | OpenRouter | 70.455% | Details |
| tau bench verified airline | OpenAI: GPT-5 Nanoopenai/gpt-5-nano-2025-08-07 | OpenRouter | 46.622% | Details |
| models · gamedev | GPT-5 nano (Default)openai/gpt-5-nano-2025-08-07 | Design Arena | 1,057 Elo | Details |
| models · 3d | GPT-5 nano (Default)openai/gpt-5-nano-2025-08-07 | Design Arena | 981 Elo | Details |
| models · uicomponent | GPT-5 nano (Default)openai/gpt-5-nano-2025-08-07 | Design Arena | 1,073 Elo | Details |
| models · codecategories | GPT-5 nano (Default)openai/gpt-5-nano-2025-08-07 | Design Arena | 1,090 Elo | Details |
| models · website | GPT-5 nano (Default)openai/gpt-5-nano-2025-08-07 | Design Arena | 1,108 Elo | Details |
Sources: Artificial Analysis, Design Arena and OpenRouter. Evaluation configurations and scales differ; results are not interchangeable. Updated Oct 4, 2026.
Apps & session costs
Compare observed median session costs for applications using this model, grouped by conversation length.
| Application | Model route | Turns | Median cost / session | Details |
|---|---|---|---|---|
| Hermes Agent | openai/gpt-5-nano-2025-08-07 | 2–9 turns | $0.002225 | Details |
| Hermes Agent | openai/gpt-5-nano-2025-08-07 | 1 turn | $0.000633 | Details |
Source: OpenRouter, as of Oct 2, 2026. Published under CC BY 4.0. These are observed costs per session, not token prices or a forecast for your workload. Apps are compared separately.
Activity
Daily prompt and completion tokens reported for this model's routes in OpenRouter's top 50. Missing days have no published value.
21,458,152,006 tokens
19,216,594,348 tokens
Daily observations · 2 days
| Date (UTC) | Reported tokens | Reported routes |
|---|---|---|
| Jul 16, 2026 | 19,216,594,348 | 1 |
| Jul 14, 2026 | 21,458,152,006 | 1 |
Source: OpenRouter (openrouter.ai/rankings), as of Oct 4, 2026. CC BY 4.0. Totals include only individually published routes. Tokenizers differ by provider; the aggregated “other” category is never assigned to a model.
Technical details & API
Explore specifications, supported parameters, reasoning controls, and API identifiers for each OpenRouter route.
openai/gpt-5-nanoObserved - Context
- 400,000
- Maximum output
- 128,000
- Tokenizer
- GPT
- Input
- text, image, file
- Output
- text
- Moderation
- Yes
- Knowledge cutoff
- 2024-05-31
- Added to OpenRouter
- 2025-08-07
https://openrouter.ai/api/v1openai/gpt-5-nanoopenai/gpt-5-nano-2025-08-07Reasoning
- Required
- Yes
- Enabled by default
- Not reported
- Default effort
- medium
- Supported efforts
- high, medium, low, minimal
Supported parameters
include_reasoningmax_completion_tokensmax_tokensreasoningreasoning_effortresponse_formatseedstructured_outputstool_choicetoolsverbosity
Frequently asked questions
Answers based on the model metadata and serving offers currently in the catalog.
How much does GPT-5 Nano cost?
Listed rates start at $0.025 per million input tokens and $0.20 per million output tokens. Prices vary by provider and configuration; see Pricing for details.
Which providers offer GPT-5 Nano?
There are 24 cataloged offers across 20 providers. Compare model IDs, prices and limits in Providers.
What is the context window?
The cataloged model context is 400,000 tokens. Each serving endpoint may apply a different limit.
Does it support tools and structured output?
Tool calling: Yes. Structured output: Yes. Support can vary by endpoint.
Catalog history · 2 recorded revisions
Metadata observations since this model was first cataloged. These are not model release versions.
- ·
1fafe6b3b636 - ·
2eaa84297560