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.
- Input / output price
- $0.05 / $0.40 per 1M
- Context
- 400K tokens
- Released
- Aug 7, 2025
Paste into Claude Code, Cursor, or Codex
Help me set up the Respan gateway: fetch and follow https:/
Providers
7 routes from 6 providers, cheapest first, retired then OpenRouter last, priced per 1M tokens after gateway discounts.
| Provider | Input | Output |
|---|---|---|
Azure Foundry azure_foundry/gpt-5-nano | $0.05/M | $0.40/M |
Azure OpenAI azure_openai/gpt-5-nano | $0.05/M | $0.40/M |
Inference.net inference_net/gpt-5-nano | $0.05/M | $0.40/M |
OpenAIRetiring openai/gpt-5-nano | $0.05/M | $0.40/M |
Perplexity perplexity/gpt-5-nano | $0.05/M | $0.40/M |
OpenRouterRetired openrouter/openai/gpt-5-nano:batch | $0.025/M | $0.20/M |
OpenRouterRetired openrouter/gpt-5-nano | $0.05/M | $0.40/M |
Is a provider down? Azure OpenAI status, ChatGPT status, Perplexity status, OpenRouter status
Pricing
Averaged across 7 routes from 6 providers, in USD per 1M tokens after gateway discounts.
- Average input
- $0.05 per 1M
- Average output
- $0.37 per 1M
- Average cache read
- $0.0046 per 1M
Cost by volume
Total cost from 0 to 1T tokens on the cheapest and most expensive provider.
Throughput and latency
30-day averages from requests through the Respan gateway. Under each figure, every model on the gateway by its average, this one in blue.
Output speed
Higher is better103tokens/sacross providers
Time to first token
Lower is better9.8sacross providers
Response latency
Lower is better3.0sacross providers
Benchmarks
The Respan Index plus 14 published scores from 6 sources, each linked to where it was published.
18.8/ 100
Respan Index#138 of 176
- 138GPT-5 nano18.8
- 137DeepSeek V3.118.9
- 138DeepSeek R118.8
Published scores
| Benchmark | Score | Source | Published |
|---|---|---|---|
| SWE-bench VerifiedOpenAI | 54.7% | OpenAI | Aug 7, 2025 |
| WeirdMLHåvard Tveit Ihle | 38.1% | Håvard Tveit Ihle | Oct 5, 2026 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| GPQA DiamondEpoch AI | 69.4% | Epoch AI | Oct 5, 2026 |
| Chess PuzzlesEpoch AI | 22% | Epoch AI | Oct 28, 2026 |
| Mystery Game PuzzlesEpoch AI | 9% | Epoch AI | Oct 5, 2026 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| MATH Level 5Epoch AI | 95.2% | Epoch AI | Oct 5, 2026 |
| AIME 2025MathArena | 85% | MathArena | Sep 17, 2026 |
| OTIS Mock AIME 2024-2025Epoch AI | 81.1% | Epoch AI | Oct 5, 2026 |
| FrontierMath Tiers 1-3 v2Epoch AI | 20% | Epoch AI | Oct 5, 2026 |
| FrontierMath Tier 4 v2Epoch AI | 2.4% | Epoch AI | Oct 5, 2026 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| SimpleQA VerifiedEpoch AI | 11.7% | Epoch AI | Oct 5, 2026 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| LMArena EloLMArena | 1338 Elo · #158 of 191 | LMArena | Nov 19, 2026 |
| LMArena VisionLMArena | 1148 Elo · #85 of 91 | LMArena | Nov 19, 2026 |
How GPT compares: Claude vs GPT, Gemini vs GPT, DeepSeek vs GPT
Compare GPT-5 Nano: GPT-5 nano vs GPT-4.1 nano, GPT-5 nano vs GPT-5.4 nano, GPT-5 nano vs GPT-6.2 Astra, GPT-5 nano vs GPT-6 Astra, GPT-5 nano vs GPT-6.1 Sol, GPT-5 nano vs GPT-6.1 Terra
Apps
Use GPT-5 Nano in the tools you already run. Each guide points the app at the Respan gateway.
Setup guides for more apps are in the integration docs.
GPT-5 Nano FAQ
Short answers, built from the data on this page.
GPT-5 Nano is a model from OpenAI, released on Aug 7, 2025. 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.
On the Respan gateway, GPT-5 Nano costs from $0.025 per 1M input tokens and $0.20 per 1M output tokens on OpenRouter, after gateway discounts. Averaged across its 7 routes from 6 providers, it costs $0.05 per 1M input tokens and $0.37 per 1M output tokens.
GPT-5 Nano is available through 7 routes from 6 providers: Azure Foundry, Azure OpenAI, Inference.net, OpenAI, Perplexity, and OpenRouter.
GPT-5 Nano accepts up to 400K tokens of context on its largest provider route.
Point any OpenAI-compatible SDK at https://gateway.respan.ai/v1 with your Respan API key and set the model to "openai/gpt-5-nano". To set it up with a coding agent, copy the agent setup prompt at the top of this page.
GPT-5 Nano scores 18.8 out of 100 on the Respan Index v1.1, ranking #138 of 176 models. By category: Coding 4.2, Agents 18.5 (estimated), Reasoning 25.3, Knowledge & language 11.7, and Human preference 37.6. The Respan Index combines independent and lab-reported benchmark results into one score, using benchmark data collected by Respan.
GPT-5 Nano has 14 published benchmark scores, including SWE-bench Verified 54.7%, GPQA Diamond 69.4%, and MATH Level 5 95.2%. Each score links to where it was published; the data is collected by Respan.
Certified where it counts.
Built to meet the security and privacy standards that enterprise and healthcare teams require.
ISO 27001
The internationally recognized standard for information security management.
SOC 2
Secure, compliant management of your data across all of our systems.
GDPR
Operated under GDPR, the world's strictest standard for data privacy.
HIPAA
HIPAA compliant, with a BAA available for healthcare teams.