GPT-5 Mini
GPT-5 Mini is a compact version of GPT-5, designed to handle lighter-weight reasoning tasks. It provides the same instruction-following and safety-tuning benefits as GPT-5, but with reduced latency and cost. GPT-5 Mini is the successor to OpenAI's o4-mini model.
- Organization
- OpenAI
- Family
- gpt-mini
- Providers
- 35
- Context
- 400,000
- Output limit
- 128,000
- Knowledge
- 2024-05-30
- Release
- 2025-08-07
- Updated
- —
- Weights
- Closed
- Input
- text, image/jpeg, image/png, image/gif, image/webp
- 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 |
|---|---|---|---|---|---|---|---|---|
| 302.AI | gpt-5-mini | 400,000 | 128,000 | — / — | — | — | — | View |
| Abacus | gpt-5-mini | 400,000 | 128,000 | — / — | — | — | — | View |
| AI/ML API | openai/gpt-5-mini | 400,000 | 128,000 | — / — | — | — | — | View |
| AnyAPI | openai/gpt-5-mini | 400,000 | 128,000 | — / — | — | — | — | View |
| Cloudflare AI Gateway | openai/gpt-5-mini | 128,000 | 128,000 | — / — | — | — | — | View |
| Cortecs | gpt-5-mini | 400,000 | 128,000 | — / — | — | — | — | View |
| Databricks | databricks-gpt-5-mini | 400,000 | 128,000 | — / — | — | — | — | View |
| DevPass (LLM Gateway) | gpt-5-mini | 400,000 | 128,000 | — / — | — | — | — | View |
| DigitalOcean | openai-gpt-5-mini | 400,000 | 128,000 | — / — | — | — | — | View |
| Eden AI | openai/gpt-5-mini | 400,000 | 128,000 | — / — | — | — | — | View |
| FastRouter | openai/gpt-5-mini | 400,000 | 128,000 | — / — | — | — | — | View |
| GitHub Copilot | gpt-5-mini | 264,000 | 64,000 | — / — | — | — | — | View |
| GitLab Duo | duo-chat-gpt-5-mini | 400,000 | 128,000 | — / — | — | — | — | View |
| Helicone | gpt-5-mini | 400,000 | 128,000 | — / — | — | — | — | View |
| Impossibl | openai/gpt-5-mini | 400,000 | 128,000 | — / — | — | — | — | View |
| Jiekou.AI | gpt-5-mini | 400,000 | 128,000 | — / — | — | — | — | View |
| Kilo Gateway | openai/gpt-5-mini | 400,000 | 128,000 | — / — | — | — | — | View |
| LLM Gateway | openai/gpt-5-mini | 400,000 | 128,000 | — / — | — | — | — | View |
| LLM Gateway | azure/gpt-5-mini | 400,000 | 128,000 | — / — | — | — | — | View |
| LowRouter | auto/openai/gpt-5-mini | 400,000 | 128,000 | — / — | — | — | — | View |
| Merge Gateway | openai/gpt-5-mini | 400,000 | 128,000 | — / — | — | — | — | View |
| NanoGPT | openai/gpt-5-mini | 400,000 | 128,000 | — / — | — | — | — | View |
| NEAR AI Cloud | openai/gpt-5-mini | 400,000 | 128,000 | — / — | — | — | — | View |
| Neon | gpt-5-mini | 400,000 | 128,000 | — / — | — | — | — | View |
| Ofox | openai/gpt-5-mini | 256,000 | 32,768 | — / — | — | — | — | View |
| Azurevia OpenRouter | openai/gpt-5-mini unknown | 400,000 | 360,000 | $0.25 / $2.00 | Yes | Yes | Yes | View |
| Azurevia OpenRouter | openai/gpt-5-mini unknown | 400,000 | 360,000 | $0.275 / $2.20 | Yes | Yes | Yes | View |
| OpenAIvia OpenRouter | openai/gpt-5-mini unknown | 400,000 | 128,000 | $0.25 / $2.00 | Yes | Yes | Yes | View |
| OpenAIvia OpenRouter | openai/gpt-5-mini unknown | 400,000 | 128,000 | $0.125 / $1.00 | Yes | Yes | Yes | View |
| OrcaRouter | openai/gpt-5-mini | 400,000 | 128,000 | — / — | — | — | — | View |
| Perplexity Agent | openai/gpt-5-mini | 400,000 | 128,000 | — / — | — | — | — | View |
| Poe | openai/gpt-5-mini | 400,000 | 128,000 | — / — | — | — | — | View |
| Prime Inference | openai/gpt-5-mini | 400,000 | 128,000 | — / — | — | — | — | View |
| QiHang | gpt-5-mini | 200,000 | 64,000 | — / — | — | — | — | View |
| Requesty | gpt-5-mini@eu | 200,000 | 100,000 | — / — | — | — | — | View |
| SAP AI Core | gpt-5-mini | 400,000 | 128,000 | — / — | — | — | — | View |
| Snowflake Cortex | openai-gpt-5-mini | 272,000 | 8,192 | — / — | — | — | — | View |
| Vercel AI Gateway | openai/gpt-5-mini | 400,000 | 128,000 | — / — | — | — | — | View |
| Vercel AI Gateway | openai/gpt-5-mini-fast | 400,000 | 128,000 | — / — | — | — | — | View |
| Vivgrid | gpt-5-mini | 272,000 | 128,000 | — / — | — | — | — | 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-miniObserved - Input
- $0.25
- Output
- $2.00
- Cache read
- $0.025
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 | $0.25 | $2.00 | $0.03 | — |
| Azureazure/swedencentral | $0.275 | $2.20 | $0.033 | — |
| OpenAIopenai | $0.25 | $2.00 | $0.025 | — |
| OpenAIopenai/flex | $0.125 | $1.00 | $0.0125 | — |
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 | 4,418 ms | 6,674 ms | 9,927 ms | 20,113 ms |
| Azureazure/swedencentral | 3,405 ms | 4,435 ms | 7,026.6 ms | 7,301.64 ms |
| OpenAIopenai | 3,182 ms | 4,816 ms | 7,807.8 ms | 21,364.06 ms |
| OpenAIopenai/flex | 1,097 ms | 1,727 ms | 2,961 ms | 12,031.28 ms |
Output throughput · tokens per second
All throughput percentiles 4 endpoints
| Endpoint | P50 | P75 | P90 | P99 |
|---|---|---|---|---|
| Azureazure | 73 t/s | 100 t/s | 123 t/s | 150 t/s |
| Azureazure/swedencentral | 137 t/s | 144 t/s | 163.2 t/s | 172.16 t/s |
| OpenAIopenai | 125 t/s | 143 t/s | 157 t/s | 176 t/s |
| OpenAIopenai/flex | 71 t/s | 87 t/s | 122.9 t/s | 193.18 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-miniObserved | Design Arena | Category | Elo | Win rate | Rank |
|---|---|---|---|---|
| models | 3d | 1,042 | 36.9% | 99 |
| models | asciiart | 1,130 | 44.7% | 52 |
| models | codecategories | 1,119 | 43.5% | 90 |
| models | dataviz | 1,134 | 43.7% | 84 |
| models | gamedev | 1,137 | 46.5% | 80 |
| models | svg | 1,090 | 45.8% | 61 |
| models | uicomponent | 1,109 | 41.9% | 84 |
| models | website | 1,129 | 44.3% | 91 |
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 · codecategories | GPT-5 mini (Default)openai/gpt-5-mini-2025-08-07 | Design Arena | 1,115 Elo | Details |
| models · 3d | GPT-5 mini (Default)openai/gpt-5-mini-2025-08-07 | Design Arena | 1,037 Elo | Details |
| models · asciiart | GPT-5 mini (Default)openai/gpt-5-mini-2025-08-07 | Design Arena | 1,125 Elo | Details |
| gpqa diamond | OpenAI: GPT-5 Miniopenai/gpt-5-mini-2025-08-07 | OpenRouter | 80.808% | Details |
| models · gamedev | GPT-5 mini (Default)openai/gpt-5-mini-2025-08-07 | Design Arena | 1,130 Elo | Details |
| models · svg | GPT-5 mini (Default)openai/gpt-5-mini-2025-08-07 | Design Arena | 1,091 Elo | Details |
| models · dataviz | GPT-5 mini (Default)openai/gpt-5-mini-2025-08-07 | Design Arena | 1,131 Elo | Details |
| tau bench verified airline | OpenAI: GPT-5 Miniopenai/gpt-5-mini-2025-08-07 | OpenRouter | 70% | Details |
| models · uicomponent | GPT-5 mini (Default)openai/gpt-5-mini-2025-08-07 | Design Arena | 1,103 Elo | Details |
| Composite indices | GPT-5 mini (Medium)openai/gpt-5-mini-2025-08-07 | Artificial Analysis | Intelligence 20.6 · Coding — · Agentic — | Details |
| models · website | GPT-5 mini (Default)openai/gpt-5-mini-2025-08-07 | Design Arena | 1,125 Elo | Details |
Sources: Artificial Analysis, Design Arena and OpenRouter. Evaluation configurations and scales differ; results are not interchangeable. Updated Oct 24, 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-mini-2025-08-07 | 10–49 turns | $0.059431 | Details |
| Hermes Agent | openai/gpt-5-mini-2025-08-07 | 1 turn | $0.003574 | Details |
| Hermes Agent | openai/gpt-5-mini-2025-08-07 | 2–9 turns | $0.008735 | Details |
Source: OpenRouter, as of Oct 20, 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.
23,566,146,432 tokens
22,760,468,689 tokens
18,329,857,278 tokens
28,633,529,977 tokens
29,347,174,265 tokens
26,290,199,933 tokens
26,721,769,074 tokens
21,084,844,335 tokens
17,234,135,391 tokens
22,422,023,142 tokens
31,707,360,465 tokens
34,431,364,968 tokens
27,874,837,450 tokens
39,831,785,424 tokens
35,028,143,466 tokens
22,276,723,999 tokens
23,384,597,846 tokens
32,582,033,961 tokens
31,703,400,091 tokens
Daily observations · 19 days
| Date (UTC) | Reported tokens | Reported routes |
|---|---|---|
| Aug 25, 2026 | 31,703,400,091 | 1 |
| Aug 24, 2026 | 32,582,033,961 | 1 |
| Aug 23, 2026 | 23,384,597,846 | 1 |
| Aug 22, 2026 | 22,276,723,999 | 1 |
| Aug 21, 2026 | 35,028,143,466 | 1 |
| Aug 20, 2026 | 39,831,785,424 | 1 |
| Aug 19, 2026 | 27,874,837,450 | 1 |
| Aug 12, 2026 | 34,431,364,968 | 1 |
| Aug 11, 2026 | 31,707,360,465 | 1 |
| Aug 10, 2026 | 22,422,023,142 | 1 |
| Aug 9, 2026 | 17,234,135,391 | 1 |
| Aug 8, 2026 | 21,084,844,335 | 1 |
| Aug 7, 2026 | 26,721,769,074 | 1 |
| Aug 6, 2026 | 26,290,199,933 | 1 |
| Aug 4, 2026 | 29,347,174,265 | 1 |
| Aug 3, 2026 | 28,633,529,977 | 1 |
| Aug 1, 2026 | 18,329,857,278 | 1 |
| Jul 29, 2026 | 22,760,468,689 | 1 |
| Jul 28, 2026 | 23,566,146,432 | 1 |
Source: OpenRouter (openrouter.ai/rankings), as of Oct 24, 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-miniObserved - 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-miniopenai/gpt-5-mini-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 Mini cost?
Listed rates start at $0.125 per million input tokens and $1.00 per million output tokens. Prices vary by provider and configuration; see Pricing for details.
Which providers offer GPT-5 Mini?
There are 40 cataloged offers across 35 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: 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.
- ·
6f41dd18647f - ·
c658d1f99508 - ·
16eb66e40a79