GPT-4o mini
GPT-4o mini is OpenAI's newest model after GPT-4 Omni, supporting both text and image inputs with text outputs.
As their most advanced small model, it is many multiples more affordable than other recent frontier models, and more than 60% cheaper than GPT-3.5 Turbo. It maintains SOTA intelligence, while being significantly more cost-effective.
GPT-4o mini achieves an 82% score on MMLU and presently ranks higher than GPT-4 on chat preferences common leaderboards.
Check out the launch announcement to learn more.
#multimodal
- Organization
- OpenAI
- Family
- gpt-mini
- Providers
- 24
- Context
- 128,000
- Output limit
- 16,384
- Knowledge
- 2023-09
- Release
- 2024-07-18
- Updated
- —
- Weights
- Closed
- Input
- text, image/jpeg, image/png, image/gif, image/webp, application/pdf
- Output
- text
- Capabilities
- —
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-4o-mini | 128,000 | 16,384 | — / — | — | — | — | View |
| AI/ML API | openai/gpt-4o-mini | 128,000 | 16,384 | — / — | — | — | — | View |
| Azure | gpt-4o-mini | 128,000 | 16,384 | — / — | — | — | — | View |
| Cloudflare AI Gateway | openai/gpt-4o-mini | 128,000 | 16,384 | — / — | — | — | — | View |
| Cortecs | gpt-4o-mini | 128,000 | 16,000 | — / — | — | — | — | View |
| CrossModel | openai/gpt-4o-mini | 128,000 | 16,384 | — / — | — | — | — | View |
| DevPass (LLM Gateway) | gpt-4o-mini | 128,000 | 16,384 | — / — | — | — | — | View |
| DigitalOcean | openai-gpt-4o-mini | 128,000 | 16,384 | — / — | — | — | — | View |
| Eden AI | openai/gpt-4o-mini | 128,000 | 16,384 | — / — | — | — | — | View |
| Helicone | gpt-4o-mini | 128,000 | 16,384 | — / — | — | — | — | View |
| Impossibl | openai/gpt-4o-mini | 128,000 | 16,384 | — / — | — | — | — | View |
| Kilo Gateway | openai/gpt-4o-mini-fast | 128,000 | 16,384 | — / — | — | — | — | View |
| Kilo Gateway | openai/gpt-4o-mini | 128,000 | 16,384 | — / — | — | — | — | View |
| Kilo Gateway | openai/gpt-4o-mini-2024-07-18 | 128,000 | 16,384 | — / — | — | — | — | View |
| LLM Gateway | openai/gpt-4o-mini | 128,000 | 16,384 | — / — | — | — | — | View |
| LLM Gateway | azure/gpt-4o-mini | 128,000 | 16,384 | — / — | — | — | — | View |
| LowRouter | auto/openai/gpt-4o-mini | 128,000 | 16,384 | — / — | — | — | — | View |
| Merge Gateway | openai/gpt-4o-mini | 128,000 | 16,384 | — / — | — | — | — | View |
| NanoGPT | openai/gpt-4o-mini | 128,000 | 16,384 | — / — | — | — | — | View |
| Ofox | openai/gpt-4o-mini | 128,000 | 16,384 | — / — | — | — | — | View |
| OpenRouter | openai/gpt-4o-mini-2024-07-18 | 128,000 | 16,384 | — / — | — | — | — | View |
| Azurevia OpenRouter | openai/gpt-4o-mini unknown | 128,000 | 16,384 | $0.165 / $0.66 | No | No | Yes | View |
| Azurevia OpenRouter | openai/gpt-4o-mini unknown | 128,000 | 16,384 | $0.15 / $0.60 | No | No | Yes | View |
| OpenAIvia OpenRouter | openai/gpt-4o-mini unknown | 128,000 | 16,384 | $0.15 / $0.60 | No | Yes | Yes | View |
| OrcaRouter | openai/gpt-4o-mini | 128,000 | 16,384 | — / — | — | — | — | View |
| Poe | openai/gpt-4o-mini | 124,096 | 4,096 | — / — | — | — | — | View |
| Prime Inference | openai/gpt-4o-mini | 128,000 | 16,384 | — / — | — | — | — | View |
| Requesty | gpt-4o-mini@eu | 128,000 | 16,000 | — / — | — | — | — | View |
| Venice AI | openai-gpt-4o-mini-2024-07-18 | 128,000 | 16,384 | — / — | — | — | — | View |
| Vercel AI Gateway | openai/gpt-4o-mini-fast | 128,000 | 16,384 | — / — | — | — | — | View |
| Vercel AI Gateway | openai/gpt-4o-mini | 128,000 | 16,384 | — / — | — | — | — | 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-4o-miniObserved - Input
- $0.15
- Output
- $0.60
- Cache read
- $0.075
Hosting prices through OpenRouter All endpoints and cache rates
| Endpoint | Input / 1M | Output / 1M | Cache read / 1M | Cache write / 1M |
|---|---|---|---|---|
| Azureazure/swedencentral | $0.165 | $0.66 | $0.0825 | — |
| Azureazure | $0.15 | $0.60 | $0.075 | — |
| OpenAIopenai | $0.15 | $0.60 | $0.075 | — |
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 3 endpoints
| Endpoint | P50 | P75 | P90 | P99 |
|---|---|---|---|---|
| Azureazure/swedencentral | 735 ms | 817 ms | 907.2 ms | 1,218.68 ms |
| Azureazure | 1,394.5 ms | 1,653.25 ms | 1,906 ms | 3,376.54 ms |
| OpenAIopenai | 555 ms | 621 ms | 708 ms | 1,588.44 ms |
Output throughput · tokens per second
All throughput percentiles 3 endpoints
| Endpoint | P50 | P75 | P90 | P99 |
|---|---|---|---|---|
| Azureazure/swedencentral | 96 t/s | 106.5 t/s | 125 t/s | 132.7 t/s |
| Azureazure | 57 t/s | 71 t/s | 82 t/s | 103 t/s |
| OpenAIopenai | 85 t/s | 108 t/s | 124 t/s | 145 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-4o-miniObserved 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 |
|---|---|---|---|---|
| Composite indices | GPT-4o miniopenai/gpt-4o-mini | Artificial Analysis | Intelligence — · Coding 11.4 · Agentic — | Details |
| tau bench verified airline | OpenAI: GPT-4o-miniopenai/gpt-4o-mini | OpenRouter | 30.667% | Details |
| gpqa diamond | OpenAI: GPT-4o-miniopenai/gpt-4o-mini | OpenRouter | 43.603% | Details |
Sources: Artificial Analysis, Design Arena and OpenRouter. Evaluation configurations and scales differ; results are not interchangeable. Updated Nov 14, 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-4o-mini | 2–9 turns | $0.003385 | Details |
| Hermes Agent | openai/gpt-4o-mini | 10–49 turns | $0.033361 | Details |
| Hermes Agent | openai/gpt-4o-mini | 1 turn | $0.00095 | Details |
Source: OpenRouter, as of Nov 9, 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.
32,881,995,719 tokens
33,664,202,059 tokens
34,697,717,276 tokens
37,779,475,582 tokens
34,444,105,097 tokens
30,700,118,517 tokens
26,319,378,523 tokens
35,594,703,703 tokens
36,397,681,040 tokens
36,548,432,744 tokens
35,590,098,729 tokens
33,227,906,195 tokens
25,862,652,268 tokens
32,410,566,376 tokens
35,185,682,502 tokens
32,711,218,391 tokens
33,666,012,348 tokens
41,385,452,908 tokens
48,101,380,955 tokens
Daily observations · 19 days
| Date (UTC) | Reported tokens | Reported routes |
|---|---|---|
| Sep 16, 2026 | 48,101,380,955 | 1 |
| Sep 8, 2026 | 41,385,452,908 | 1 |
| Sep 4, 2026 | 33,666,012,348 | 1 |
| Sep 2, 2026 | 32,711,218,391 | 1 |
| Sep 1, 2026 | 35,185,682,502 | 1 |
| Aug 31, 2026 | 32,410,566,376 | 1 |
| Aug 30, 2026 | 25,862,652,268 | 1 |
| Aug 28, 2026 | 33,227,906,195 | 1 |
| Aug 27, 2026 | 35,590,098,729 | 1 |
| Aug 26, 2026 | 36,548,432,744 | 1 |
| Aug 25, 2026 | 36,397,681,040 | 1 |
| Aug 24, 2026 | 35,594,703,703 | 1 |
| Aug 23, 2026 | 26,319,378,523 | 1 |
| Aug 22, 2026 | 30,700,118,517 | 1 |
| Aug 21, 2026 | 34,444,105,097 | 1 |
| Aug 20, 2026 | 37,779,475,582 | 1 |
| Aug 19, 2026 | 34,697,717,276 | 1 |
| Aug 18, 2026 | 33,664,202,059 | 1 |
| Aug 17, 2026 | 32,881,995,719 | 1 |
Source: OpenRouter (openrouter.ai/rankings), as of Nov 14, 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-4o-miniObserved - Context
- 128,000
- Maximum output
- 16,384
- Tokenizer
- GPT
- Input
- text, image, file
- Output
- text
- Moderation
- Yes
- Knowledge cutoff
- 2023-10-31
- Added to OpenRouter
- 2024-07-18
https://openrouter.ai/api/v1openai/gpt-4o-miniopenai/gpt-4o-miniSupported parameters
frequency_penaltylogit_biaslogprobsmax_completion_tokensmax_tokenspredictionpresence_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_logprobstop_pweb_search_options
Frequently asked questions
Answers based on the model metadata and serving offers currently in the catalog.
How much does GPT-4o mini cost?
Listed rates start at $0.15 per million input tokens and $0.60 per million output tokens. Prices vary by provider and configuration; see Pricing for details.
Which providers offer GPT-4o mini?
There are 31 cataloged offers across 24 providers. Compare model IDs, prices and limits in Providers.
What is the context window?
The cataloged model context is 128,000 tokens. Each serving endpoint may apply a different limit.
Does it support tools and structured output?
Tool calling: Not reported. Structured output: Not reported. Support can vary by endpoint.
Catalog history · 3 recorded revisions
Metadata observations since this model was first cataloged. These are not model release versions.
- ·
70af3d198391 - ·
9d3a23eb6f8a - ·
87b0ce2e0337