Scheduled for retirement on Feb 9, 2027. Still available at the prices below until then.
Context
1M
Max output
128K
Serving providers
9
Cheapest input
$0.25 /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
155 t/s
tokens / second
Time to first token
49.51s
latency
Headline indices
Individual benchmarks · click a row for effort variants
| Benchmark | Best score | Effort | Cost / task | |||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Automation Bench | 0.1 | default | — | |||||||||||||||||
| CritPt | 1% | medium | — | |||||||||||||||||
| ||||||||||||||||||||
| GDPval v2Frozen Aug 18, 2026 | 935.1 | default | — | |||||||||||||||||
| ||||||||||||||||||||
| GPQA Diamond | 83% | default | — | |||||||||||||||||
| ||||||||||||||||||||
| Humanity's Last Exam | 21% | default | — | |||||||||||||||||
| ||||||||||||||||||||
| IFBench | 75% | default | — | |||||||||||||||||
| ||||||||||||||||||||
| LiveCodeBench | 84% | default | — | |||||||||||||||||
| ||||||||||||||||||||
| Long-Context Reasoning | 72% | default | — | |||||||||||||||||
| ||||||||||||||||||||
| MMLU-ProFrozen Aug 18, 2026 | 84% | default | — | |||||||||||||||||
| ||||||||||||||||||||
| MMMU-Pro | 70% | default | — | |||||||||||||||||
| ||||||||||||||||||||
| Omniscience | -11.0 | medium | — | |||||||||||||||||
| ||||||||||||||||||||
| Omniscience Accuracy | 0.2 | default | — | |||||||||||||||||
| ||||||||||||||||||||
| Omniscience Non Hallucination | 0.6 | medium | — | |||||||||||||||||
| ||||||||||||||||||||
| SciCode | 39% | default | — | |||||||||||||||||
| ||||||||||||||||||||
| Terminal Bench40 | 0 | default | — | |||||||||||||||||
| ||||||||||||||||||||
| TerminalBench Hard | 33% | default | — | |||||||||||||||||
| ||||||||||||||||||||
| TerminalBench v2.1 | 4% | default | — | |||||||||||||||||
| ||||||||||||||||||||
| τ-bench Banking | 15% | default | — | |||||||||||||||||
| τ²-bench | 71% | medium | — | |||||||||||||||||
| ||||||||||||||||||||
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 expandInput pricing runs from $0.25 to $0.30 per 1M tokens across 9 providers, so the dearest route costs 20% more than the cheapest for the same model.
| Serving provider | Input /1M | Output /1M | Endpoints | |||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| DatabricksCheapest | $0.25 | $2.00 | 1 | |||||||||||||||||
Standarddatabricks/databricks-gpt-5-mini
| ||||||||||||||||||||
| Azure | $0.25 | $2.00 | 1 | |||||||||||||||||
Standardazure/gpt-5-mini
| ||||||||||||||||||||
| Github Copilot | $0.25 | $2.00 | 1 | |||||||||||||||||
Standardgithub_copilot/gpt-5-mini
| ||||||||||||||||||||
| OCI | $0.25 | $2.00 | 1 | |||||||||||||||||
Standardoci/openai.gpt-5-mini
| ||||||||||||||||||||
| OpenAI | $0.25 | $2.00 | 1 | |||||||||||||||||
Standardgpt-5-mini
| ||||||||||||||||||||
| OpenRouter | $0.25 | $2.00 | 1 | |||||||||||||||||
Standardopenai/gpt-5-mini
| ||||||||||||||||||||
| Replicate | $0.25 | $2.00 | 1 | |||||||||||||||||
Standardreplicate/openai/gpt-5-mini
| ||||||||||||||||||||
| VercelVercel reseller quote | $0.25 | $2.00 | 1 | |||||||||||||||||
Standardopenai/gpt-5-mini
| ||||||||||||||||||||
| Vercel is dearest at $0.45 / $3.60 | ||||||||||||||||||||
Price history
listed seller prices, input and output per 1M tokens Input Output
Cost calculator
estimate your monthly spend on this model$210
estimated / month
Model IDs
copy the exact identifier for your platformopenai/gpt-5-mini:batchopenai/gpt-5-minidatabricks/databricks-gpt-5-minioci/openai.gpt-5-minireplicate/openai/gpt-5-miniopenai/gpt-5-miniopenai/gpt-5-minigpt-5-miniazure/gpt-5-minigithub_copilot/gpt-5-minisnowflake/openai-gpt-5-miniopenai/gpt-5-mini-fastopenai/gpt-5-mini
Frequently asked questions
GPT-5 Mini pricing, context and availabilityIs GPT-5 Mini still available?
Yes. GPT-5 Mini is scheduled for retirement on 2027-02-09.
How much does GPT-5 Mini cost?
GPT-5 Mini costs $0.25 per 1M input tokens from Databricks, and $1.20 per 1M output tokens from Snowflake. Across 9 serving providers, input prices range from $0.25 to $0.30 per 1M tokens.
What is the context window of GPT-5 Mini?
GPT-5 Mini accepts up to 1M tokens of context and can return up to 128K output tokens.
Which providers serve GPT-5 Mini?
GPT-5 Mini is available from 9 serving providers, each with its own pricing and model ID. Databricks is currently the cheapest.
What can GPT-5 Mini do?
GPT-5 Mini 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 Mini 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