GPT: Mini Latest API
OpenAI's GPT: Mini Latest costs $0.75 per million input tokens and $4.5 per million output tokens from 1 supplier. Each request through the OpenAI-compatible API goes to the offer with the lowest estimated charge that meets your rules.
- Providers compete for each request. The exchange ranks the offers that meet your rules by estimated charge. It fixes your maximum charge before the first token, and you pay for the tokens that the model uses.
- The OpenAI and Anthropic APIs. Use the OpenAI or Anthropic SDK that you have. Set the base URL and your key, and send gpt-mini-latest as the model.
- Your data rules. Send x-liquid-retention: none and only offers whose provider does not keep your content compete for the request.
About GPT: Mini Latest
GPT: Mini Latest is a language model from OpenAI. It takes text, files and images and gives text. The largest offer takes 400,000 input tokens. It has 1 supplier on this exchange now.
Facts
- Model name
- gpt-mini-latest
- Maker
- OpenAI
- Context window
- 400K tokens
- Input price
- $0.75 per million tokens
- Output price
- $4.5 per million tokens
- Suppliers
- 1 supplier
- Regions
- us
Providers
- Architect: us, declared precision provider-managed, $0.75 input and $4.5 output per million tokens, $0.075 cache read per million tokens, 400K tokens of context
Request
curl https://router.inference.ai.exchange/v1/chat/completions \
-H "Authorization: Bearer $LIQUID_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "gpt-mini-latest",
"messages": [{"role":"user","content":"Say hello."}]
}'Questions
- What is GPT: Mini Latest?
- GPT: Mini Latest is a language model from OpenAI.
- How much does GPT: Mini Latest cost?
- Offers now ask $0.75 per million input tokens and $4.5 per million output tokens. A job pays for the tokens it uses. The exchange picks the cheapest eligible offer.
- What is the context length of GPT: Mini Latest?
- The largest offer takes 400,000 input tokens. A smaller offer can take less. The exchange skips an offer that cannot take your message.
- What can GPT: Mini Latest do?
- Its providers list Documents, Vision, Reasoning effort, JSON object, JSON schema, Frequency penalty, Logit bias, Log probabilities, Min-p sampling, Presence penalty, Repetition penalty, Seed, Stop sequences, Top-k sampling, Top-p sampling, Text, Tools.
- What inputs and outputs does GPT: Mini Latest support?
- Text · Files · Images → Text.
- Which providers serve GPT: Mini Latest?
- It has 1 supplier now, with 1 offer. The table above ranks them by the cost of one agent-mix job.
- How do I call GPT: Mini Latest?
- Send "gpt-mini-latest" as the model in an OpenAI or Anthropic request. The API section links to setup steps for each client.
- When was GPT: Mini Latest listed?
- The exchange first listed it on 10/10/2026. This is not its release date.