OpenAI: GPT-5 Mini
Small GPT-5 for responsive agents, coding help, and everyday automation
Sources
Same model, different sources. Our first-party rate is listed first, then router and aggregator rows stay separate so you can see the spread instead of a single blended number.
| Source | Provider | Input | Output | Cache read | Context |
|---|---|---|---|---|---|
| models.devcheapestgpt-5-mini | QiHang | $0.04 | $0.29 | $0 | 200K |
| OpenRouteropenai/gpt-5-mini:batch | OpenRouter | $0.125 | $1 | $0.0125 | 400K |
| models.devopenai/gpt-5-mini | Poe | $0.2273 | $1.82 | $0.0227 | 400K |
| models.devgpt-5-mini | Jiekou.AI | $0.2375 | $1.90 | $0.0237 | 400K |
| LiteLLMdatabricks-gpt-5-mini | N/A | $0.25 | $2 | $0.025 | N/A |
| LiteLLMdatabricks/databricks-gpt-5-mini | N/A | $0.25 | $2 | $0.025 | N/A |
| models.devopenai/gpt-5-mini | AI/ML API | $0.25 | $2 | $0.025 | 400K |
| models.devopenai/gpt-5-mini | Cloudflare | $0.25 | $2 | $0.025 | 128K |
| models.devopenai/gpt-5-mini | Eden AI | $0.25 | $2 | $0.025 | 400K |
| models.devopenai/gpt-5-mini | FastRouter | $0.25 | $2 | $0.025 | 400K |
| models.devopenai/gpt-5-mini | Impossibl | $0.25 | $2 | $0.025 | 400K |
| models.devopenai/gpt-5-mini | Kilo Gateway | $0.25 | $2 | $0.025 | 400K |
| models.devopenai/gpt-5-mini | LLM Gateway | $0.25 | $2 | $0.025 | 400K |
| models.devopenai/gpt-5-mini | Merge Gateway | $0.25 | $2 | $0.025 | 400K |
| models.devopenai/gpt-5-mini | NanoGPT | $0.25 | $2 | $0.025 | 400K |
| models.devopenai/gpt-5-mini | NEAR AI Cloud | $0.25 | $2 | $0.025 | 400K |
| models.devopenai/gpt-5-mini | Ofox | $0.25 | $2 | $0.03 | 256K |
| models.devgpt-5-mini | OpenAI | $0.25 | $2 | $0.025 | 400K |
| OpenRouteropenai/gpt-5-mini | OpenRouter | $0.25 | $2 | $0.025 | 400K |
| models.devopenai/gpt-5-mini | OrcaRouter | $0.25 | $2 | $0.025 | 400K |
| models.devopenai/gpt-5-mini | Perplexity | $0.25 | $2 | $0.025 | 400K |
| models.devopenai/gpt-5-mini | Prime Inference | $0.25 | $2 | $0 | 400K |
| models.devopenai/gpt-5-mini | Vercel AI Gateway | $0.25 | $2 | $0.025 | 400K |
| models.devgpt-5-mini | 302.AI | $0.25 | $2 | $0.025 | 400K |
| models.devgpt-5-mini | Abacus | $0.25 | $2 | $0.025 | 400K |
| models.devgpt-5-mini | Azure | $0.25 | $2 | $0.025 | 400K |
| models.devgpt-5-mini | Azure | $0.25 | $2 | $0.025 | 400K |
| models.devgpt-5-mini | GitHub Copilot | $0.25 | $2 | $0.025 | 264K |
| models.devgpt-5-mini | Helicone | $0.25 | $2 | $0.025 | 400K |
| models.devgpt-5-mini | DevPass (LLM Gateway) | $0.25 | $2 | $0.025 | 400K |
| models.devgpt-5-mini | Neon | $0.25 | $2 | $0.025 | 400K |
| models.devgpt-5-mini | SAP AI Core | $0.25 | $2 | $0.025 | 400K |
| models.devgpt-5-mini | Vivgrid | $0.25 | $2 | $0.03 | 272K |
| models.devdatabricks-gpt-5-mini | Databricks | $0.25 | $2 | $0.025 | 400K |
| models.devopenai-gpt-5-mini | DigitalOcean | $0.25 | $2 | $0.025 | 400K |
| models.devopenai-gpt-5-mini | Snowflake Cortex | $0.25 | $2 | $0.03 | 272K |
| models.devauto/openai/gpt-5-mini | LowRouter | $0.25 | $2 | $0.025 | 400K |
| LiteLLMgpt-5-mini | N/A | $0.25 | $2 | $0.025 | N/A |
| LiteLLMopenai.gpt-5-mini | N/A | $0.25 | $2 | $0.025 | N/A |
| LiteLLMoci/openai.gpt-5-mini | N/A | $0.25 | $2 | $0.025 | N/A |
| LiteLLMperplexity/openai/gpt-5-mini | N/A | $0.25 | $2 | $0.025 | N/A |
| LiteLLMreplicate/openai/gpt-5-mini | N/A | $0.25 | $2 | $0.025 | N/A |
| LiteLLMazure/eu/gpt-5-mini | N/A | $0.275 | $2.20 | $0.0275 | N/A |
| LiteLLMeu/gpt-5-mini | N/A | $0.275 | $2.20 | $0.0275 | N/A |
| LiteLLMus/gpt-5-mini | N/A | $0.275 | $2.20 | $0.0275 | N/A |
| models.devgpt-5-mini | Cortecs | $0.279 | $2.19 | $0.056 | 400K |
| LiteLLMopenai-gpt-5-mini | N/A | $0.3 | $1.20 | $0.03 | N/A |
| LiteLLMsnowflake/openai-gpt-5-mini | N/A | $0.3 | $1.20 | $0.03 | N/A |
Capabilities
- Reasoning
- Tool calling
- Structured output
- Attachments
- In: text
- In: image
- In: pdf
- In: file
- Out: text
Scores
Sparse coverage on purpose. Missing a score means we have not linked one yet, not that the model is unranked. Hover or tap the i next to any score for its source. Full boards on /benchmarks.
- AA intelligence20.6i
- AA coding0i
- AA agentic0i
Arena rows are community-vote Elo from Arena AI, Artificial Analysis indices arrive via OpenRouter, and launch-eval figures are collected from vendor announcements, analyst writeups, and community benchmarks. Full boards and credits on /benchmarks.
See what this model costs you
The app reads the sessions your tools already wrote and prices this model's tokens at the published API rate. Free on your computer.