OpenAI · Model profile
GPT-5 mini (high)
Intelligence, Performance & Price Analysis
Source: Canonical slug: gpt-5-mini · Canonical model registry at build time
Routing verdict
Strong general-purpose model
Suitable for most production tasks, but high-volume or repetitive work should still be compared against cheaper routes.
GPT-5 mini (high) summary metrics
- Intelligence
- 25 scoreGPT-5 mini (high) scores 25 on the Artificial Analysis Intelligence Index, placing it above average among other reasoning models in a similar price tier (median: 15).
- Speed
- 98.4 output tokens/secGPT-5 mini (high) generates output at 98.4 tokens per second (based on OpenAI's API), which is below average compared to other reasoning models in a similar price tier (median: 99.0 t/s).
- Latency
- 119.34s TTFTGPT-5 mini (high) has a time to first token (TTFT) of 119.34s (based on OpenAI's API), which is at the higher end compared to other reasoning models in a similar price tier (median: 1.96s).
- Input Price
- $0.25 / 1M tokensGPT-5 mini (high) costs $0.25 per 1M input tokens (better than average, median: $0.25) and $2.00 per 1M output tokens (at the higher end, median: $0.87), based on OpenAI's API.
- Output Price
- $2.00 / 1M tokensGPT-5 mini (high) costs $0.25 per 1M input tokens (better than average, median: $0.25) and $2.00 per 1M output tokens (at the higher end, median: $0.87), based on OpenAI's API.
- Verbosity
- 60M Output tokens from Intelligence Index 3 out of 4 units for Verbosity . Compa
Assessment
Routing verdict and task fit
| Workload | Rating | Notes |
|---|---|---|
| Complex reasoning & agentic workflows | Optimal | Intelligence score 25 supports capable reasoning, but very hard tasks may benefit from higher-tier models. |
| High-volume chat & customer-facing | Optimal | Output speed 98.4 tokens/sec is adequate for chat. |
| Latency-sensitive applications | Viable | TTFT 119.34s — latency may be noticeable in interactive use. |
| Cost-sensitive pipelines | Viable | Output pricing at $2.00 is premium. Route high-volume simple tasks to cheaper alternatives. |
Evidence
Evidence charts
AA-Omniscience Index
AA-Omniscience Index (higher is better) measures knowledge reliability and hallucination. It rewards correct answers, penalizes hallucinations, and has no penalty for refusing to answer. Scores range from -100 to 100, where 0 means as many correct as incorrect answers, and negative scores mean more incorrect than correct. · Evaluation results measured independently by Artificial Analysis
- Claude Fable 5 (with fallback)40.1
- Gemini 3.5 Flash22.7
- GPT-5.5 (xhigh)20.1
- Grok 4.3 (high)18.3
- Kimi K2.66.4
- Muse Spark4.1
- GLM-5.2 (max)4
- MiMo-V2.5-Pro3.6
- Qwen3.7 Plus2.4
- MiniMax-M31.4
- MiniMax-M2.70.683
- Nemotron 3 Ultra-0.833
- DeepSeek V4 Pro (max)-10
- Gemini 3.1 Flash-Lite-15.5
- GPT-5 mini (high) (this model)-17.2
- Qwen3.6 35B A3B-21.4
- DeepSeek V4 Flash (max)-22.9
- Nex-N2-Pro-27.6
- GPT-5.4 nano (xhigh)-29.6
- GLM-4.7-34.6
| Model | AA-Omniscience Index |
|---|---|
| Claude Fable 5 (with fallback) | 40.1 |
| Gemini 3.5 Flash | 22.7 |
| GPT-5.5 (xhigh) | 20.1 |
| Grok 4.3 (high) | 18.3 |
| Kimi K2.6 | 6.4 |
| Muse Spark | 4.1 |
| GLM-5.2 (max) | 4 |
| MiMo-V2.5-Pro | 3.6 |
| Qwen3.7 Plus | 2.4 |
| MiniMax-M3 | 1.4 |
| MiniMax-M2.7 | 0.683 |
| Nemotron 3 Ultra | -0.833 |
| DeepSeek V4 Pro (max) | -10 |
| Gemini 3.1 Flash-Lite | -15.5 |
| GPT-5 mini (high) (this model) | -17.2 |
| Qwen3.6 35B A3B | -21.4 |
| DeepSeek V4 Flash (max) | -22.9 |
| Nex-N2-Pro | -27.6 |
| GPT-5.4 nano (xhigh) | -29.6 |
| GLM-4.7 | -34.6 |
Published benchmark dataset · Retrieved
Method and source
- Methodology
- Independent test run by Artificial Analysis on dedicated hardware.
- Chart interpretation
- Each bar is one model measured the same way, so this model can be read against the others. The chart lists its source and retrieval date.
Artificial Analysis Intelligence Index by Open Weights / Proprietary
Artificial Analysis Intelligence Index v4.1 incorporates 9 evaluations: GDPval-AA v2, 𝜏³-Banking, Terminal-Bench v2.1, SciCode, Humanity's Last Exam, GPQA Diamond, CritPt, AA-Omniscience, AA-LCR · Evaluation results measured independently by Artificial Analysis
- Claude Fable 5 (with fallback)59.9
- GPT-5.5 (xhigh)54.8
- GLM-5.2 (max)51.1
- Gemini 3.5 Flash50.2
- MiniMax-M344.4
- DeepSeek V4 Pro (max)44.3
- Kimi K2.644.2
- Muse Spark43.1
- MiMo-V2.5-Pro42.2
- Nex-N2-Pro41
- DeepSeek V4 Flash (max)40.3
- Qwen3.7 Plus39
- GPT-5.4 nano (xhigh)38.2
- MiniMax-M2.738.1
- Nemotron 3 Ultra37.8
- Grok 4.3 (high)37.6
- GLM-4.733.7
- Qwen3.6 35B A3B31.6
- Ring-2.6-1T30.6
- Step 3.7 Flash29.7
| Model | Artificial Analysis Intelligence Index by Open Weights / Proprietary |
|---|---|
| Claude Fable 5 (with fallback) | 59.9 |
| GPT-5.5 (xhigh) | 54.8 |
| GLM-5.2 (max) | 51.1 |
| Gemini 3.5 Flash | 50.2 |
| MiniMax-M3 | 44.4 |
| DeepSeek V4 Pro (max) | 44.3 |
| Kimi K2.6 | 44.2 |
| Muse Spark | 43.1 |
| MiMo-V2.5-Pro | 42.2 |
| Nex-N2-Pro | 41 |
| DeepSeek V4 Flash (max) | 40.3 |
| Qwen3.7 Plus | 39 |
| GPT-5.4 nano (xhigh) | 38.2 |
| MiniMax-M2.7 | 38.1 |
| Nemotron 3 Ultra | 37.8 |
| Grok 4.3 (high) | 37.6 |
| GLM-4.7 | 33.7 |
| Qwen3.6 35B A3B | 31.6 |
| Ring-2.6-1T | 30.6 |
| Step 3.7 Flash | 29.7 |
Published benchmark dataset · Retrieved
Method and source
- Methodology
- Independent test run by Artificial Analysis on dedicated hardware.
- Benchmark interpretation
- Higher values indicate stronger overall capability. Bars show how models compare on composite intelligence metrics.
Artificial Analysis Intelligence Index
Artificial Analysis Intelligence Index v4.1 incorporates 9 evaluations: GDPval-AA v2, 𝜏³-Banking, Terminal-Bench v2.1, SciCode, Humanity's Last Exam, GPQA Diamond, CritPt, AA-Omniscience, AA-LCR · Evaluation results measured independently by Artificial Analysis
- Claude Fable 5 (with fallback)59.9
- GPT-5.5 (xhigh)54.8
- GLM-5.2 (max)51.1
- Gemini 3.5 Flash50.2
- MiniMax-M344.4
- DeepSeek V4 Pro (max)44.3
- Kimi K2.644.2
- Muse Spark43.1
- MiMo-V2.5-Pro42.2
- Nex-N2-Pro41
- DeepSeek V4 Flash (max)40.3
- Qwen3.7 Plus39
- GPT-5.4 nano (xhigh)38.2
- MiniMax-M2.738.1
- Nemotron 3 Ultra37.8
- Grok 4.3 (high)37.6
- GLM-4.733.7
- Qwen3.6 35B A3B31.6
- Ring-2.6-1T30.6
- Step 3.7 Flash29.7
| Model | Artificial Analysis Intelligence Index |
|---|---|
| Claude Fable 5 (with fallback) | 59.9 |
| GPT-5.5 (xhigh) | 54.8 |
| GLM-5.2 (max) | 51.1 |
| Gemini 3.5 Flash | 50.2 |
| MiniMax-M3 | 44.4 |
| DeepSeek V4 Pro (max) | 44.3 |
| Kimi K2.6 | 44.2 |
| Muse Spark | 43.1 |
| MiMo-V2.5-Pro | 42.2 |
| Nex-N2-Pro | 41 |
| DeepSeek V4 Flash (max) | 40.3 |
| Qwen3.7 Plus | 39 |
| GPT-5.4 nano (xhigh) | 38.2 |
| MiniMax-M2.7 | 38.1 |
| Nemotron 3 Ultra | 37.8 |
| Grok 4.3 (high) | 37.6 |
| GLM-4.7 | 33.7 |
| Qwen3.6 35B A3B | 31.6 |
| Ring-2.6-1T | 30.6 |
| Step 3.7 Flash | 29.7 |
Published benchmark dataset · Retrieved
Method and source
- Methodology
- Independent test run by Artificial Analysis on dedicated hardware.
- Benchmark interpretation
- Higher values indicate stronger overall capability. Bars show how models compare on composite intelligence metrics.
Intelligence
Artificial Analysis Intelligence Index · Higher is better · Evaluation results measured independently by Artificial Analysis
- Claude Fable 5 (with fallback)59.9
- GPT-5.5 (xhigh)54.8
- GLM-5.2 (max)51.1
- Gemini 3.5 Flash50.2
- MiniMax-M344.4
- DeepSeek V4 Pro (max)44.3
- Kimi K2.644.2
- Muse Spark43.1
- Nemotron 3 Ultra37.8
- Grok 4.3 (high)37.6
- GPT-5 mini (high) (this model)25.3
- gpt-oss-120b (high)23.8
| Model | Intelligence |
|---|---|
| Claude Fable 5 (with fallback) | 59.9 |
| GPT-5.5 (xhigh) | 54.8 |
| GLM-5.2 (max) | 51.1 |
| Gemini 3.5 Flash | 50.2 |
| MiniMax-M3 | 44.4 |
| DeepSeek V4 Pro (max) | 44.3 |
| Kimi K2.6 | 44.2 |
| Muse Spark | 43.1 |
| Nemotron 3 Ultra | 37.8 |
| Grok 4.3 (high) | 37.6 |
| GPT-5 mini (high) (this model) | 25.3 |
| gpt-oss-120b (high) | 23.8 |
Published benchmark dataset · Retrieved
Method and source
- Methodology
- Independent test run by Artificial Analysis on dedicated hardware.
- Benchmark interpretation
- Higher values indicate stronger overall capability. Bars show how models compare on composite intelligence metrics.
Output Speed
Output tokens per second · Higher is better · Evaluation results measured independently by Artificial Analysis
- Step 3.7 Flash410 t/s
- NVIDIA Nemotron 3 Super364 t/s
- Gemini 3.1 Flash-Lite347 t/s
- gpt-oss-120b (high)314 t/s
- Nemotron 3 Ultra250 t/s
- GLM-5.2 (max)218 t/s
- Gemini 3.5 Flash192 t/s
- Qwen3.6 35B A3B166 t/s
- Grok 4.3 (high)164 t/s
- GPT-5.4 nano (xhigh)153 t/s
- Ring-2.6-1T136 t/s
- GLM-4.7126 t/s
- DeepSeek V4 Flash (max)112 t/s
- MiniMax-M399 t/s
- GPT-5 mini (high) (this model)98 t/s
- Nex-N2-Pro92 t/s
- GPT-5.5 (xhigh)88 t/s
- Kimi K2.676 t/s
- DeepSeek V4 Pro (max)72 t/s
- Claude Fable 5 (with fallback)71 t/s
| Model | Output Speed |
|---|---|
| Step 3.7 Flash | 410 t/s |
| NVIDIA Nemotron 3 Super | 364 t/s |
| Gemini 3.1 Flash-Lite | 347 t/s |
| gpt-oss-120b (high) | 314 t/s |
| Nemotron 3 Ultra | 250 t/s |
| GLM-5.2 (max) | 218 t/s |
| Gemini 3.5 Flash | 192 t/s |
| Qwen3.6 35B A3B | 166 t/s |
| Grok 4.3 (high) | 164 t/s |
| GPT-5.4 nano (xhigh) | 153 t/s |
| Ring-2.6-1T | 136 t/s |
| GLM-4.7 | 126 t/s |
| DeepSeek V4 Flash (max) | 112 t/s |
| MiniMax-M3 | 99 t/s |
| GPT-5 mini (high) (this model) | 98 t/s |
| Nex-N2-Pro | 92 t/s |
| GPT-5.5 (xhigh) | 88 t/s |
| Kimi K2.6 | 76 t/s |
| DeepSeek V4 Pro (max) | 72 t/s |
| Claude Fable 5 (with fallback) | 71 t/s |
Published benchmark dataset · Retrieved
Method and source
- Methodology
- Independent test run by Artificial Analysis on dedicated hardware.
- Output speed context
- Speed should be read together with latency and cost; fast output does not always mean better user-perceived performance.
Speed
Output tokens per second · Higher is better · Evaluation results measured independently by Artificial Analysis
- gpt-oss-120b (high)314 t/s
- Nemotron 3 Ultra250 t/s
- GLM-5.2 (max)218 t/s
- Gemini 3.5 Flash192 t/s
- Grok 4.3 (high)164 t/s
- MiniMax-M399 t/s
- GPT-5 mini (high) (this model)98 t/s
- GPT-5.5 (xhigh)88 t/s
- Kimi K2.676 t/s
- DeepSeek V4 Pro (max)72 t/s
- Claude Fable 5 (with fallback)71 t/s
| Model | Speed |
|---|---|
| gpt-oss-120b (high) | 314 t/s |
| Nemotron 3 Ultra | 250 t/s |
| GLM-5.2 (max) | 218 t/s |
| Gemini 3.5 Flash | 192 t/s |
| Grok 4.3 (high) | 164 t/s |
| MiniMax-M3 | 99 t/s |
| GPT-5 mini (high) (this model) | 98 t/s |
| GPT-5.5 (xhigh) | 88 t/s |
| Kimi K2.6 | 76 t/s |
| DeepSeek V4 Pro (max) | 72 t/s |
| Claude Fable 5 (with fallback) | 71 t/s |
Published benchmark dataset · Retrieved
Method and source
- Methodology
- Independent test run by Artificial Analysis on dedicated hardware.
- Output speed context
- Speed should be read together with latency and cost; fast output does not always mean better user-perceived performance.
End-to-End Response Time
Seconds to output 500 tokens, including reasoning model 'thinking' time · Lower is better · Evaluation results measured independently by Artificial Analysis
- Gemini 3.1 Flash-Lite1.44 s
- Step 3.7 Flash1.22 s
- NVIDIA Nemotron 3 Super1.37 s
- gpt-oss-120b (high)1.59 s
- GPT-5.4 nano (xhigh)3.27 s
- Nemotron 3 Ultra2 s
- GLM-5.2 (max)2.3 s
- GLM-4.73.97 s
- Ring-2.6-1T3.67 s
- Grok 4.3 (high)3.05 s
- MiniMax-M35.05 s
- Nex-N2-Pro5.42 s
- Gemini 3.5 Flash2.6 s
- Qwen3.6 35B A3B3.02 s
- MiMo-V2.5-Pro9.52 s
- Qwen3.7 Plus9.91 s
- GLM-4.610.18 s
- DeepSeek V4 Flash (max)4.46 s
- MiniMax-M2.79.79 s
- Kimi K2.66.56 s
| Model | End-to-End Response Time |
|---|---|
| Gemini 3.1 Flash-Lite | 1.44 s |
| Step 3.7 Flash | 1.22 s |
| NVIDIA Nemotron 3 Super | 1.37 s |
| gpt-oss-120b (high) | 1.59 s |
| GPT-5.4 nano (xhigh) | 3.27 s |
| Nemotron 3 Ultra | 2 s |
| GLM-5.2 (max) | 2.3 s |
| GLM-4.7 | 3.97 s |
| Ring-2.6-1T | 3.67 s |
| Grok 4.3 (high) | 3.05 s |
| MiniMax-M3 | 5.05 s |
| Nex-N2-Pro | 5.42 s |
| Gemini 3.5 Flash | 2.6 s |
| Qwen3.6 35B A3B | 3.02 s |
| MiMo-V2.5-Pro | 9.52 s |
| Qwen3.7 Plus | 9.91 s |
| GLM-4.6 | 10.18 s |
| DeepSeek V4 Flash (max) | 4.46 s |
| MiniMax-M2.7 | 9.79 s |
| Kimi K2.6 | 6.56 s |
Published benchmark dataset · Retrieved
Method and source
- Methodology
- Independent test run by Artificial Analysis on dedicated hardware.
- Chart interpretation
- Each bar is one model measured the same way, so this model can be read against the others. The chart lists its source and retrieval date.
Latency: Time To First Answer Token
Seconds to first answer token received · Accounts for reasoning model 'thinking' time · Evaluation results measured independently by Artificial Analysis
- Gemini 3.1 Flash-Lite0 s
- Step 3.7 Flash4.88 s
- GPT-5.4 nano (xhigh)0 s
- NVIDIA Nemotron 3 Super5.5 s
- gpt-oss-120b (high)6.37 s
- Nemotron 3 Ultra9.09 s
- GLM-5.2 (max)9.19 s
- GLM-4.715.87 s
- Ring-2.6-1T14.68 s
- Grok 4.3 (high)0 s
- MiniMax-M320.19 s
- Nex-N2-Pro21.66 s
- Gemini 3.5 Flash0 s
- Qwen3.6 35B A3B32.57 s
- MiMo-V2.5-Pro38.08 s
- Qwen3.7 Plus39.64 s
- GLM-4.640.7 s
- MiniMax-M2.748.19 s
- DeepSeek V4 Flash (max)50.09 s
- Kimi K2.658.43 s
| Model | Latency: Time To First Answer Token |
|---|---|
| Gemini 3.1 Flash-Lite | 0 s |
| Step 3.7 Flash | 4.88 s |
| GPT-5.4 nano (xhigh) | 0 s |
| NVIDIA Nemotron 3 Super | 5.5 s |
| gpt-oss-120b (high) | 6.37 s |
| Nemotron 3 Ultra | 9.09 s |
| GLM-5.2 (max) | 9.19 s |
| GLM-4.7 | 15.87 s |
| Ring-2.6-1T | 14.68 s |
| Grok 4.3 (high) | 0 s |
| MiniMax-M3 | 20.19 s |
| Nex-N2-Pro | 21.66 s |
| Gemini 3.5 Flash | 0 s |
| Qwen3.6 35B A3B | 32.57 s |
| MiMo-V2.5-Pro | 38.08 s |
| Qwen3.7 Plus | 39.64 s |
| GLM-4.6 | 40.7 s |
| MiniMax-M2.7 | 48.19 s |
| DeepSeek V4 Flash (max) | 50.09 s |
| Kimi K2.6 | 58.43 s |
Published benchmark dataset · Retrieved
Method and source
- Methodology
- Independent test run by Artificial Analysis on dedicated hardware.
- Latency considerations
- Latency includes thinking / reasoning time when applicable. Lower is better for interactive use cases.
Context Window
Context window: tokens limit · Higher is better · Evaluation results measured independently by Artificial Analysis
- Gemini 3.5 Flash1M
- Claude Fable 5 (with fallback)1M
- GLM-5.2 (max)1M
- DeepSeek V4 Pro (max)1M
- Grok 4.3 (high)1M
- MiniMax-M31M
- MiMo-V2.5-Pro1M
- DeepSeek V4 Flash (max)1M
- Qwen3.7 Plus1M
- NVIDIA Nemotron 3 Super1M
- Gemini 3.1 Flash-Lite1M
- GPT-5.5 (xhigh)922k
- GPT-5 mini (high) (this model)400k
- GPT-5.4 nano (xhigh)400k
- Nemotron 3 Ultra262.1k
- Muse Spark262.1k
- Qwen3.6 35B A3B262.1k
- Ring-2.6-1T262.1k
- Step 3.7 Flash262.1k
- Nex-N2-Pro262k
| Model | Context Window |
|---|---|
| Gemini 3.5 Flash | 1M |
| Claude Fable 5 (with fallback) | 1M |
| GLM-5.2 (max) | 1M |
| DeepSeek V4 Pro (max) | 1M |
| Grok 4.3 (high) | 1M |
| MiniMax-M3 | 1M |
| MiMo-V2.5-Pro | 1M |
| DeepSeek V4 Flash (max) | 1M |
| Qwen3.7 Plus | 1M |
| NVIDIA Nemotron 3 Super | 1M |
| Gemini 3.1 Flash-Lite | 1M |
| GPT-5.5 (xhigh) | 922k |
| GPT-5 mini (high) (this model) | 400k |
| GPT-5.4 nano (xhigh) | 400k |
| Nemotron 3 Ultra | 262.1k |
| Muse Spark | 262.1k |
| Qwen3.6 35B A3B | 262.1k |
| Ring-2.6-1T | 262.1k |
| Step 3.7 Flash | 262.1k |
| Nex-N2-Pro | 262k |
Published benchmark dataset · Retrieved
Method and source
- Methodology
- Independent test run by Artificial Analysis on dedicated hardware.
- Context window sizing
- Larger context windows enable complex multi-turn tasks but may increase latency and cost for long inputs.
Cost per Intelligence Index Task
Weighted average cost (USD) per Artificial Analysis Intelligence Index task, segmented by token type. Lower is better · Evaluation results measured independently by Artificial Analysis
- GPT-5 mini (high) (this model)0.0039
- Gemma 4 26B A4B0.00194
- MiMo-V2.5-Pro0.00466
- Gemini 3.1 Flash-Lite0.00306
- DeepSeek V4 Pro (max)0.0063
- Qwen3.7 Plus0.00434
- gpt-oss-120b (high)0.00454
- MiniMax-M30.0139
- GPT-5.4 nano (xhigh)0.00899
- Grok 4.3 (high)0.0101
- Qwen3.6 35B A3B0.0213
- NVIDIA Nemotron 3 Super0.00577
- Nemotron 3 Ultra0.0209
- GLM-4.60.0144
- GLM-4.70.0157
- Ring-2.6-1T0.0239
- Kimi K2.60.0216
- MiMo-V2-Flash0.00812
- GLM-5.2 (max)0.0268
- Gemini 3.5 Flash0.0884
| Model | Cost per Intelligence Index Task |
|---|---|
| GPT-5 mini (high) (this model) | 0.0039 |
| Gemma 4 26B A4B | 0.00194 |
| MiMo-V2.5-Pro | 0.00466 |
| Gemini 3.1 Flash-Lite | 0.00306 |
| DeepSeek V4 Pro (max) | 0.0063 |
| Qwen3.7 Plus | 0.00434 |
| gpt-oss-120b (high) | 0.00454 |
| MiniMax-M3 | 0.0139 |
| GPT-5.4 nano (xhigh) | 0.00899 |
| Grok 4.3 (high) | 0.0101 |
| Qwen3.6 35B A3B | 0.0213 |
| NVIDIA Nemotron 3 Super | 0.00577 |
| Nemotron 3 Ultra | 0.0209 |
| GLM-4.6 | 0.0144 |
| GLM-4.7 | 0.0157 |
| Ring-2.6-1T | 0.0239 |
| Kimi K2.6 | 0.0216 |
| MiMo-V2-Flash | 0.00812 |
| GLM-5.2 (max) | 0.0268 |
| Gemini 3.5 Flash | 0.0884 |
Published benchmark dataset · Retrieved
Method and source
- Methodology
- Independent test run by Artificial Analysis on dedicated hardware.
- Benchmark interpretation
- Higher values indicate stronger overall capability. Bars show how models compare on composite intelligence metrics.
- Cost pressure
- Ethen Gateway should route away from this model when the task is simple, repetitive, or likely to generate many output tokens.
Cost per Task
Weighted average cost (USD) per Intelligence Index task · Lower is better · Evaluation results measured independently by Artificial Analysis
- GPT-5 mini (high) (this model)$0.029
- DeepSeek V4 Pro (max)$0.045
- gpt-oss-120b (high)$0.061
- MiniMax-M3$0.125
- Grok 4.3 (high)$0.139
- Nemotron 3 Ultra$0.244
- Kimi K2.6$0.346
- GLM-5.2 (max)$0.370
- Gemini 3.5 Flash$0.586
- GPT-5.5 (xhigh)$0.863
- Claude Fable 5 (with fallback)$2.75
| Model | Cost per Task |
|---|---|
| GPT-5 mini (high) (this model) | $0.029 |
| DeepSeek V4 Pro (max) | $0.045 |
| gpt-oss-120b (high) | $0.061 |
| MiniMax-M3 | $0.125 |
| Grok 4.3 (high) | $0.139 |
| Nemotron 3 Ultra | $0.244 |
| Kimi K2.6 | $0.346 |
| GLM-5.2 (max) | $0.370 |
| Gemini 3.5 Flash | $0.586 |
| GPT-5.5 (xhigh) | $0.863 |
| Claude Fable 5 (with fallback) | $2.75 |
Published benchmark dataset · Retrieved
Method and source
- Methodology
- Independent test run by Artificial Analysis on dedicated hardware.
- Cost pressure
- Ethen Gateway should route away from this model when the task is simple, repetitive, or likely to generate many output tokens.
Cost to Run Artificial Analysis Intelligence Index
Cost (USD) to run all evaluations in the Artificial Analysis Intelligence Index · Evaluation results measured independently by Artificial Analysis
- Gemma 4 26B A4B2.3
- Gemini 3.1 Flash-Lite4.1
- gpt-oss-120b (high)3.5
- MiMo-V2.5-Pro6.7
- GPT-5 mini (high) (this model)6.4
- Qwen3.7 Plus5.5
- DeepSeek V4 Pro (max)7.2
- MiniMax-M314.5
- NVIDIA Nemotron 3 Super5.4
- GPT-5.4 nano (xhigh)8.9
- Grok 4.3 (high)12.5
- GLM-4.615.6
- Qwen3.6 35B A3B164.7
- MiMo-V2-Flash11.4
- Nemotron 3 Ultra33.5
- Ring-2.6-1T23.5
- GLM-4.716.6
- GLM-5.2 (max)32.9
- Kimi K2.625
- Gemini 3.5 Flash114
| Model | Cost to Run Artificial Analysis Intelligence Index |
|---|---|
| Gemma 4 26B A4B | 2.3 |
| Gemini 3.1 Flash-Lite | 4.1 |
| gpt-oss-120b (high) | 3.5 |
| MiMo-V2.5-Pro | 6.7 |
| GPT-5 mini (high) (this model) | 6.4 |
| Qwen3.7 Plus | 5.5 |
| DeepSeek V4 Pro (max) | 7.2 |
| MiniMax-M3 | 14.5 |
| NVIDIA Nemotron 3 Super | 5.4 |
| GPT-5.4 nano (xhigh) | 8.9 |
| Grok 4.3 (high) | 12.5 |
| GLM-4.6 | 15.6 |
| Qwen3.6 35B A3B | 164.7 |
| MiMo-V2-Flash | 11.4 |
| Nemotron 3 Ultra | 33.5 |
| Ring-2.6-1T | 23.5 |
| GLM-4.7 | 16.6 |
| GLM-5.2 (max) | 32.9 |
| Kimi K2.6 | 25 |
| Gemini 3.5 Flash | 114 |
Published benchmark dataset · Retrieved
Method and source
- Methodology
- Independent test run by Artificial Analysis on dedicated hardware.
- Benchmark interpretation
- Higher values indicate stronger overall capability. Bars show how models compare on composite intelligence metrics.
- Cost pressure
- Ethen Gateway should route away from this model when the task is simple, repetitive, or likely to generate many output tokens.
Pricing: Cache Hit, Input, and Output
Price (USD per M Tokens) · Evaluation results measured independently by Artificial Analysis
- Input
- Output
- Cache Hit
- MiMo-V2-Flash$0.400
- DeepSeek V4 Flash (max)$0.423
- Gemma 4 26B A4B$0.615
- gpt-oss-120b (high)$0.900
- NVIDIA Nemotron 3 Super$1.17
- DeepSeek V4 Pro (max)$1.31
- MiMo-V2.5-Pro$1.31
- Step 3.7 Flash$1.39
- GPT-5.4 nano (xhigh)$1.47
- MiniMax-M3$1.56
- MiniMax-M2.7$1.56
- Qwen3.7 Plus$1.64
- Qwen3.6 35B A3B$1.73
- Gemini 3.1 Flash-Lite$1.77
- GPT-5 mini (high) (this model)$2.27
- GLM-4.6$2.75
- Ring-2.6-1T$2.80
- GLM-4.7$3.33
- Nex-N2-Pro$3.25
- Nemotron 3 Ultra$3.60
| Model | Input | Output | Cache Hit | Total |
|---|---|---|---|---|
| MiMo-V2-Flash | $0.100 | $0.300 | Not published | $0.400 |
| DeepSeek V4 Flash (max) | $0.140 | $0.280 | $0.0028 | $0.423 |
| Gemma 4 26B A4B | $0.130 | $0.400 | $0.085 | $0.615 |
| gpt-oss-120b (high) | $0.150 | $0.600 | $0.150 | $0.900 |
| NVIDIA Nemotron 3 Super | $0.250 | $0.775 | $0.143 | $1.17 |
| DeepSeek V4 Pro (max) | $0.435 | $0.870 | $0.0036 | $1.31 |
| MiMo-V2.5-Pro | $0.435 | $0.870 | $0.0036 | $1.31 |
| Step 3.7 Flash | $0.200 | $1.15 | $0.040 | $1.39 |
| GPT-5.4 nano (xhigh) | $0.200 | $1.25 | $0.020 | $1.47 |
| MiniMax-M3 | $0.300 | $1.20 | $0.060 | $1.56 |
| MiniMax-M2.7 | $0.300 | $1.20 | $0.060 | $1.56 |
| Qwen3.7 Plus | $0.400 | $1.16 | $0.080 | $1.64 |
| Qwen3.6 35B A3B | $0.248 | $1.49 | Not published | $1.73 |
| Gemini 3.1 Flash-Lite | $0.250 | $1.50 | $0.025 | $1.77 |
| GPT-5 mini (high) (this model) | $0.250 | $2.00 | $0.025 | $2.27 |
| GLM-4.6 | $0.550 | $2.20 | Not published | $2.75 |
| Ring-2.6-1T | $0.300 | $2.50 | Not published | $2.80 |
| GLM-4.7 | $0.600 | $2.20 | $0.525 | $3.33 |
| Nex-N2-Pro | $0.500 | $2.50 | $0.250 | $3.25 |
| Nemotron 3 Ultra | $0.675 | $2.67 | $0.250 | $3.60 |
Published benchmark dataset · Retrieved
Method and source
- Methodology
- Independent test run by Artificial Analysis on dedicated hardware.
- Chart interpretation
- Each bar is one model measured the same way, so this model can be read against the others. The chart lists its source and retrieval date.
Time per Intelligence Index Task
Weighted average decode time (minutes) per task; excludes TTFT and overhead time · Lower is better · Evaluation results measured independently by Artificial Analysis
- Gemini 3.1 Flash-Lite0.946
- NVIDIA Nemotron 3 Super1.1
- Nemotron 3 Ultra1.4
- Grok 4.3 (high)1.6
- GPT-5 mini (high) (this model)1.8
- Step 3.7 Flash1.9
- gpt-oss-120b (high)1.9
- Gemini 3.5 Flash2.2
- GLM-4.72.5
- Qwen3.6 35B A3B2.6
- GLM-5.2 (max)2.8
- Ring-2.6-1T2.9
- GPT-5.5 (xhigh)3
- MiniMax-M33.9
- Claude Fable 5 (with fallback)4.8
- Nex-N2-Pro4.8
- MiniMax-M2.75.5
- GLM-4.65.9
- MiMo-V2.5-Pro6.1
- DeepSeek V4 Flash (max)6.3
| Model | Time per Intelligence Index Task |
|---|---|
| Gemini 3.1 Flash-Lite | 0.946 |
| NVIDIA Nemotron 3 Super | 1.1 |
| Nemotron 3 Ultra | 1.4 |
| Grok 4.3 (high) | 1.6 |
| GPT-5 mini (high) (this model) | 1.8 |
| Step 3.7 Flash | 1.9 |
| gpt-oss-120b (high) | 1.9 |
| Gemini 3.5 Flash | 2.2 |
| GLM-4.7 | 2.5 |
| Qwen3.6 35B A3B | 2.6 |
| GLM-5.2 (max) | 2.8 |
| Ring-2.6-1T | 2.9 |
| GPT-5.5 (xhigh) | 3 |
| MiniMax-M3 | 3.9 |
| Claude Fable 5 (with fallback) | 4.8 |
| Nex-N2-Pro | 4.8 |
| MiniMax-M2.7 | 5.5 |
| GLM-4.6 | 5.9 |
| MiMo-V2.5-Pro | 6.1 |
| DeepSeek V4 Flash (max) | 6.3 |
Published benchmark dataset · Retrieved
Method and source
- Methodology
- Independent test run by Artificial Analysis on dedicated hardware.
- Benchmark interpretation
- Higher values indicate stronger overall capability. Bars show how models compare on composite intelligence metrics.
Output Tokens per Intelligence Index Task
Weighted average number of output tokens used to run one task in the Artificial Analysis Intelligence Index · Evaluation results measured independently by Artificial Analysis
- GPT-5 mini (high) (this model)1,948.8
- Muse Spark2,857.2
- Grok 4.3 (high)4,032
- GPT-5.5 (xhigh)3,572.5
- MiniMax-M2.77,874.3
- GLM-4.66,527.7
- Gemini 3.1 Flash-Lite2,038.4
- Gemma 4 26B A4B4,853.5
- MiMo-V2.5-Pro5,359.6
- Qwen3.7 Plus3,737.2
- Nemotron 3 Ultra7,796.7
- GLM-4.77,151.4
- MiniMax-M311,623.4
- NVIDIA Nemotron 3 Super7,442.1
- MiMo-V2-Flash27,074.7
- Ring-2.6-1T9,565.1
- Gemini 3.5 Flash9,819.4
- Nex-N2-Pro6,165.3
- Qwen3.6 35B A3B14,331.6
- Claude Fable 5 (with fallback)7,695.8
| Model | Output Tokens per Intelligence Index Task |
|---|---|
| GPT-5 mini (high) (this model) | 1,948.8 |
| Muse Spark | 2,857.2 |
| Grok 4.3 (high) | 4,032 |
| GPT-5.5 (xhigh) | 3,572.5 |
| MiniMax-M2.7 | 7,874.3 |
| GLM-4.6 | 6,527.7 |
| Gemini 3.1 Flash-Lite | 2,038.4 |
| Gemma 4 26B A4B | 4,853.5 |
| MiMo-V2.5-Pro | 5,359.6 |
| Qwen3.7 Plus | 3,737.2 |
| Nemotron 3 Ultra | 7,796.7 |
| GLM-4.7 | 7,151.4 |
| MiniMax-M3 | 11,623.4 |
| NVIDIA Nemotron 3 Super | 7,442.1 |
| MiMo-V2-Flash | 27,074.7 |
| Ring-2.6-1T | 9,565.1 |
| Gemini 3.5 Flash | 9,819.4 |
| Nex-N2-Pro | 6,165.3 |
| Qwen3.6 35B A3B | 14,331.6 |
| Claude Fable 5 (with fallback) | 7,695.8 |
Published benchmark dataset · Retrieved
Method and source
- Methodology
- Independent test run by Artificial Analysis on dedicated hardware.
- Benchmark interpretation
- Higher values indicate stronger overall capability. Bars show how models compare on composite intelligence metrics.
Specifications
Architecture and limits
| Specification | Value | Source |
|---|---|---|
| Model type | Proprietary | faq |
| Reasoning | Yes | faq |
| Input modalities | GPT-5 mini (high) supports text and image input. | faq |
| Output modalities | GPT-5 mini (high) supports text output. | faq |
| Context window | 400k tokens | faq |
| Open weights / source | No, GPT-5 mini (high) is proprietary. The model weights are not publicly available. | faq |
| Parameters | GPT-5 mini (high) is a proprietary model and OpenAI has not disclosed the model size or parameter count. | faq |
| Knowledge cutoff | GPT-5 mini (high) has a knowledge cutoff of May 2024. The model's training data includes information up to this date. | faq |
| API availability | Yes, GPT-5 mini (high) is available via API through 3 providers. | faq |
Method
Methodology & Provenance
This page is rendered from the normalized profile and page JSON for GPT-5 mini (high).
Benchmark values are preserved as normalized; only layout, disclosure ordering, and typography are adjusted for readability.
Questions
Model FAQ and technical disclosures
Models
Related
- 01OpenAIOther OpenAI models in the catalog.
- 02LeaderboardsCertified metric ranks, when published.