GPT-5 nano
GPT-5 nano is a high throughput model that excels at simple instruction or classification tasks.
text + image + file → text · made by OpenAI
$0.05→$0.4per Mtok in / out
OpenAI · 12 sellers
Sold by 24 ways
| Seller | Lane | Rate |
|---|---|---|
| Microsoft Azure AI cloud | batch | $0.025per Mtok in$0.0025per Mtok cachedprices.azure.com · read 2026-08-24 |
| Databricks cloud | standard | $0.05per Mtok in$0.4per Mtok out$0.005per Mtok cached$0.05per Mtok cache writemodels.dev · read 2026-09-16 |
| DigitalOcean cloud | standard | $0.05per Mtok in$0.4per Mtok out$0.005per Mtok cachedmodels.dev · read 2026-09-16 |
| Microsoft Azure AI cloud | standard | $0.05per Mtok in$0.4per Mtok out$0.01per Mtok cachedmodels.dev · read 2026-09-16 |
| OpenAI api | standard | $0.05per Mtok in$0.4per Mtok out$0.005per Mtok cacheddevelopers.openai.com · read 2026-08-24 |
| Oracle Cloud Infrastructure cloud | standard | $0.05per Mtok in$0.4per Mtok outraw.githubusercontent.com · read 2026-09-16 |
| Snowflake Cortex cloud | standard | $0.15per Mtok in$0.6per Mtok outraw.githubusercontent.com · read 2026-09-16 |
| Requesty 3 ways | $0.022per Mtok in$0.18per Mtok out$0.0022per Mtok cached | |
| Requesty aggregatornot on the seller's list today | openai flex | $0.022per Mtok in$0.18per Mtok out$0.0022per Mtok cachedrouter.requesty.ai · read 2026-08-25 |
| Requesty aggregatornot on the seller's list today | azure eastus2 | $0.045per Mtok in$0.36per Mtok out$0.0045per Mtok cachedrouter.requesty.ai · read 2026-08-25 |
| Requesty aggregatornot on the seller's list today | azure francecentral | $0.05per Mtok in$0.4per Mtok out$0.005per Mtok cachedrouter.requesty.ai · read 2026-08-25 |
| Requesty aggregatornot on the seller's list today | azure swedencentral | $0.05per Mtok in$0.4per Mtok out$0.005per Mtok cachedrouter.requesty.ai · read 2026-08-25 |
| Requesty aggregator | openai | $0.05per Mtok in$0.4per Mtok out$0.005per Mtok cachedrouter.requesty.ai · read 2026-09-16 |
| Requesty aggregator | openai-responses | $0.05per Mtok in$0.4per Mtok out$0.005per Mtok cachedrouter.requesty.ai · read 2026-08-28 |
| Requesty aggregator | azure | $0.055per Mtok in$0.44per Mtok out$0.0055per Mtok cachedrouter.requesty.ai · read 2026-09-15 |
| Nous Research 2 ways | $0.05per Mtok in$0.4per Mtok out$0.01per Mtok cached | |
| Nous Research aggregator | batch | $0.025per Mtok in$0.2per Mtok out$0.0025per Mtok cachedinference-api.nousresearch.com · read 2026-09-12 |
| Nous Research aggregator | standard | $0.05per Mtok in$0.4per Mtok out$0.01per Mtok cachedinference-api.nousresearch.com · read 2026-09-12 |
| OpenRouter 5 ways | $0.05per Mtok in$0.4per Mtok out$0.005per Mtok cached | |
| OpenRouter aggregator | batch | $0.025per Mtok in$0.2per Mtok out$0.0025per Mtok cachedopenrouter.ai · read 2026-08-24 |
| OpenRouter aggregator | openai/flex | $0.025per Mtok in$0.2per Mtok out$0.0025per Mtok cachedopenrouter.ai · read 2026-08-25 |
| OpenRouter aggregator | standard | $0.05per Mtok in$0.4per Mtok out$0.005per Mtok cachedopenrouter.ai · read 2026-08-24 |
| OpenRouter aggregator | azure | $0.05per Mtok in$0.4per Mtok out$0.01per Mtok cachedopenrouter.ai · read 2026-08-25 |
| OpenRouter aggregator | azure/swedencentral | $0.055per Mtok in$0.44per Mtok out$0.011per Mtok cachedopenrouter.ai · read 2026-08-25 |
| ElectronHub aggregator | standard | $0.05per Mtok in$0.4per Mtok outapi.electronhub.ai · read 2026-09-16 |
| Inference.net aggregator | standard | $0.05per Mtok in$0.4per Mtok out$0.005per Mtok cachedapi.inference.net · read 2026-09-16 |
| Vercel AI Gateway aggregator | standard | $0.05per Mtok in$0.4per Mtok out$0.005per Mtok cachedai-gateway.vercel.sh · read 2026-08-25 |
Measured 36 standings
| Place | Board | Metric | Score |
|---|---|---|---|
| 14thof 108 | Math level 5 — Epoch AI | mean_score (medium) | 95.242 |
| 24thof 109 | Berkeley Function-Calling Leaderboard (BFCL) V4 | Overall Acc (fc) | 51.45 |
| 26thof 38 | Vpct — Epoch AI | Correct (high) | 0.372 |
| 41stof 42 | Fictionlivebench — Epoch AI | 120k token score (medium) | 0.219 |
| 46thof 81 | Forecastbench — Epoch AI | Overall score | 59.1 |
| 49thof 64 | Proofbench — Epoch AI | Accuracy (high) | 12 |
| 55thof 222 | Chess puzzles — Epoch AI | mean_score (high) | 27 |
| 56thof 72 | Frontiermath tier 4 — Epoch AI | mean_score (medium) | 2.083 |
| 57thof 62 | Frontiermath tier 4 v2 — Epoch AI | mean_score (high) | 2.439 |
| 60thof 101 | FrontierMath (Tiers 1-3) | mean_score (high) | 8.276 |
| 62ndof 105 | Vectara Hallucination Leaderboard | Hallucination Rate | 10.5 |
| 70thof 112 | Ale bench — Epoch AI | Performance (high) | 718.67 |
| 77thof 106 | Frontiermath tiers 1 3 v2 — Epoch AI | mean_score (high) | 20 |
| 77thof 80 | Simpleqa verified — Epoch AI | mean_score (high) | 11.7 |
| 102ndof 127 | Mystery game puzzles — Epoch AI | mean_score (medium) | 9 |
| 103rdof 290 | OTIS Mock AIME 2024-2025 | mean_score (high) | 81.111 |
| 105thof 152 | LMArena · Vision | Score (Elo) (high) | 1146 |
| 107thof 161 | Dtbench — Epoch AI | Accuracy (high) | 62.67 |
| 115thof 123 | Lmca — Epoch AI | Score (high) | 7.93 |
| 121stof 150 | Design Arena · uicomponent (models) | Elo | 1081 |
| 122ndof 170 | Weirdml — Epoch AI | Accuracy (high) | 38.06 |
| 124thof 156 | Design Arena · codecategories (models) | Elo | 1100 |
| 125thof 162 | Design Arena · website (models) | Elo | 1114 |
| 127thof 152 | Design Arena · dataviz (models) | Elo | 1071 |
| 127thof 155 | Design Arena · gamedev (models) | Elo | 1068 |
| 131stof 147 | Design Arena · 3d (models) | Elo | 993 |
| 162ndof 227 | Arc agi 2 — Epoch AI | Score (high) | 2.61 |
| 163rdof 232 | ARC-AGI-2 (Semi-Private) | Score (%) (high) | 2.61 |
| 169thof 202 | Terminalbench — Epoch AI | Accuracy mean | 0.218 |
| 171stof 205 | ARC-AGI-1 (Public Eval) | Score (%) (high) | 29.67 |
| 176thof 216 | ARC-AGI-2 (Public Eval) | Score (%) (high) | 0.3 |
| 176thof 313 | GPQA Diamond | mean_score (high) | 69.444 |
| 192ndof 230 | ARC-AGI-1 (Semi-Private) | Score (%) (medium) | 20.71 |
| 204thof 244 | Arc agi — Epoch AI | Score (medium) | 20.71 |
| 222ndof 402 | LMArena · Text | Score (Elo) (high) | 1337 |
| 453rdof 656 | Epoch capabilities index — Epoch AI | ECI Score (high) | 139.42 |
About
GPT-5 nano — a text model from OpenAI, sold by 12 companies from $0.05 in and $0.4 out per million tokens, placed 14th of 108 on Math level 5 — Epoch AI.
It takes text, images and files and returns text, with a context window of 400,000 tokens. It was published in 2025, trained on material up to May 2024. Its sellers say it can reason step by step and call a tool. The catalogue files it under reasoning and agents. Twelve companies sell it. The cheapest is $0.05 in and $0.4 out per million tokens at Databricks. Beside the standard rate there are batch, separately routed, regional and flex lanes. It has been measured on 36 boards, and stands best at 14th of 108 on Math level 5 — Epoch AI.
Every current figure
- Maker
- OpenAI
- Register
- model
- Takes
- text + image + file
- Returns
- text
- Context
- 400,000 tokens
- Published
- 2025
- Knowledge to
- May 2024
- Licence
- not read
- Sellers
- 12
- Price
- $0.05 in and $0.4 out per million tokens — Databricks
- Boards
- 36
- Best place
- 14th of 108 — Math level 5 — Epoch AI
Known as 12 names
GPT-5-nano-2025-08-07 (FC)GPT 5 Nanoopenai/gpt-5-nanoopenai/gpt-5-nano:batchgpt-5-nanoazure/gpt-5-nanoazure/gpt-5-nano@eastus2azure/gpt-5-nano@francecentralazure/gpt-5-nano@swedencentralopenai-responses/gpt-5-nanoopenai/gpt-5-nano:flexOpenAI: GPT-5 Nano (batch)