Scheduled for retirement on May 15, 2027. Still available at the prices below until then.
Context
410K
Max output
128K
Serving providers
5
Cheapest input
$1.25 /1M
On-demand listed rates, OpenRouter routed quotes and Vercel reseller quotes. Enterprise commitments (committed-use discounts, provisioned throughput, negotiated rates) can be materially lower.
Benchmarks
independent evaluations · source: Artificial AnalysisSpeed & latency
Output speed
117 t/s
tokens / second
Time to first token
35.59s
latency
Headline indices
Individual benchmarks · click a row for effort variants
| Benchmark | Best score | Effort | Cost / task | |||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| CritPt | 5% | default | — | |||||||||||||||||
| ||||||||||||||||||||
| GDPval v2Frozen Aug 18, 2026 | 992.8 | default | — | |||||||||||||||||
| ||||||||||||||||||||
| GPQA Diamond | 87% | default | — | |||||||||||||||||
| ||||||||||||||||||||
| Humanity's Last Exam | 28% | default | — | |||||||||||||||||
| ||||||||||||||||||||
| IFBench | 73% | default | — | |||||||||||||||||
| ||||||||||||||||||||
| LiveCodeBench | 87% | default | — | |||||||||||||||||
| ||||||||||||||||||||
| Long-Context Reasoning | 80% | default | — | |||||||||||||||||
| ||||||||||||||||||||
| MMLU-ProFrozen Aug 18, 2026 | 87% | default | — | |||||||||||||||||
| ||||||||||||||||||||
| MMMU-Pro | 75% | default | — | |||||||||||||||||
| ||||||||||||||||||||
| Omniscience | 5.4 | default | — | |||||||||||||||||
| ||||||||||||||||||||
| Omniscience Accuracy | 0.4 | default | — | |||||||||||||||||
| ||||||||||||||||||||
| Omniscience Non Hallucination | 0.5 | default | — | |||||||||||||||||
| ||||||||||||||||||||
| SciCodeArtificial Analysis did not report this score in its latest run on Oct 14, 2026 | 43% | — | — | |||||||||||||||||
| ||||||||||||||||||||
| TerminalBench Hard | 45% | default | — | |||||||||||||||||
| ||||||||||||||||||||
| TerminalBench v2.1 | 52% | default | — | |||||||||||||||||
| ||||||||||||||||||||
| τ-bench Banking | 16% | default | — | |||||||||||||||||
| τ²-bench | 82% | default | — | |||||||||||||||||
| ||||||||||||||||||||
Artificial Analysis last published scores for this benchmark on Sep 9, 2026. Scores here are frozen at that date, and models released since are not on it.
Artificial Analysis last published scores for this benchmark on Aug 18, 2026. Scores here are frozen at that date, and models released since are not on it.
Pricing by serving provider
standard tier · per 1M tokens · click a provider to expand| Serving provider | Input /1M | Output /1M | Endpoints | |||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| DatabricksCheapest | $1.25 | $10.00 | 1 | |||||||||||||||||
Standarddatabricks/databricks-gpt-5-1
| ||||||||||||||||||||
| Azure | $1.25 | $10.00 | 1 | |||||||||||||||||
Standardazure/global/gpt-5.1
| ||||||||||||||||||||
| Gmi | $1.25 | $10.00 | 1 | |||||||||||||||||
Standardgmi/openai/gpt-5.1
| ||||||||||||||||||||
| OpenAI | $1.25 | $10.00 | 1 | |||||||||||||||||
Standardgpt-5.1
| ||||||||||||||||||||
| OpenRouter | $1.25 | $10.00 | 1 | |||||||||||||||||
Standardopenai/gpt-5.1
| ||||||||||||||||||||
| OpenRouter (batch) | $0.625 | $5.00 | 1 | |||||||||||||||||
Batchopenai/gpt-5.1:batch
| ||||||||||||||||||||
Price history
listed seller prices, input and output per 1M tokens Input Output
Cost calculator
estimate your monthly spend on this model$1,050
estimated / month
Model IDs
copy the exact identifier for your platformopenai/gpt-5.1:batchdatabricks/databricks-gpt-5-1gmi/openai/gpt-5.1openai/gpt-5.1gpt-5.1azure/global/gpt-5.1
Frequently asked questions
GPT-5.1 pricing, context and availabilityIs GPT-5.1 still available?
Yes. GPT-5.1 is scheduled for retirement on 2027-05-15.
How much does GPT-5.1 cost?
GPT-5.1 costs $1.25 per 1M input tokens from Databricks, and $10.00 per 1M output tokens from Databricks. Across 5 serving providers, input prices range from $1.25 to $1.25 per 1M tokens.
What is the context window of GPT-5.1?
GPT-5.1 accepts up to 410K tokens of context and can return up to 128K output tokens.
Which providers serve GPT-5.1?
GPT-5.1 is available from 5 serving providers, each with its own pricing and model ID. Databricks is currently the cheapest.
What can GPT-5.1 do?
GPT-5.1 supports image input (vision), tool use, reasoning, prompt caching, structured output and web search.
Other OpenAI models
compare pricing across the OpenAI lineupPopular comparisons
head-to-head pages featuring GPT-5.1 Listed prices from LiteLLM, OpenRouter and Vercel · last checked Oct 14, 2026
Every weekday
AI moves fast. Here's your debrief.
News, analysis, tools, and more.
For people who build with AI