Arena Elo 1250Human-preference rating · LMArena (shown where the model is ranked)
Capabilities
7-day heat trend
−19.3%Pricing breakdown
Typical 3:1 output-to-input mix, per 1M tokens
Estimated monthly cost by workload
Market position
- Cheaper than 43% of tracked models
- Faster than 87% of tracked models
- Efficiency rank: #75 of 1105
Best suited for
Mixed text, image, audio and document workloads that benefit from one model across modalities.
About gpt-5.1
Azure OpenAI deployment reference for GPT-5.1; actual deployment name, API version, and region are customer-specific.
gpt-5.1 is a Multimodal model from Azure OpenAI (US). HotON.ai tracks it at $0.00 per 1M input tokens and $0.00 per 1M output tokens, with a 400K-token context window, ~167 tokens/sec throughput and 96.8% availability. Its composite efficiency score is 92/100 at an estimated $0.000 per successful task.
Compare gpt-5.1
Related market news
Frequently asked questions
How much does gpt-5.1 cost per 1M tokens?+
gpt-5.1 is tracked at $0.00 per 1M input tokens and $0.00 per 1M output tokens. A typical 3:1 output-to-input workload blends to roughly $0.00 per 1M tokens. Figures are illustrative demo data.
What is gpt-5.1 best for?+
Mixed text, image, audio and document workloads that benefit from one model across modalities.
How fast is gpt-5.1?+
gpt-5.1 delivers about 167 tokens/sec with 96.8% tracked availability, suitable for latency-sensitive, real-time applications.
Is gpt-5.1 cheaper than other AI models?+
Within the HotON.ai tracked set, gpt-5.1 is cheaper than 43% of models on input price and ranks #75 of 1105 by overall efficiency.
Related models
Pricing is real (via the TestKey catalog, updated daily). Quality (Arena Elo) is real where the model is ranked on LMArena. Speed, availability and efficiency are modeled estimates.