OpenAI200K contextgpt-5-mini

GPT-5 mini

OpenAI's cheap fast tier — strong-enough quality for high-volume work

GPT-5 mini is OpenAI's lightweight tier — cheap, fast, and strong enough for the bulk of production traffic that doesn't need frontier reasoning. The natural pick when you need OpenAI compatibility but don't want to pay frontier prices for routine work. Pairs well with GPT-5 in router patterns (mini-first, escalate on complexity).

Pricing

RateList priceAnvat effectiveSavings
Input$0.75$0.5329%
Output$4.50$3.1530%
Cache read$0.19$0.1332%
All prices per million tokens (MTok). List = provider direct. Anvat effective = 30% discount applied.

Pricing verified 2026-06 · See full Anvat pricing

Strengths

  • Cheapest GPT-5-family model — 13× cheaper than full GPT-5 on input
  • Fast — competitive with Claude Haiku 4.5 on TTFT
  • Strong tool use for its size class
  • Native multimodal (text + vision)
  • OpenAI SDK compatibility — drop-in for low-cost paths

Where it underperforms

  • Not the model for deep reasoning or hard agent loops
  • Output quality drops on tasks needing >5 step planning
  • Less aggressive prompt caching economics than Claude Haiku

Use cases this model is the right pick for

  • High-volume customer-facing chatbots
  • Intent classification at scale
  • Quick summaries and extractive QA
  • First-pass routing in agent stacks
  • Vision tasks (OCR, image-tagging) at high volume

Benchmarks

  • agentic

    Tool calling reliability

    Strong

  • vision

    Vision benchmarks

    Top of the cheap tier

  • agentic

    Cost per request

    ~$0.002 typical agent turn

Benchmark numbers self-reported by provider; verify against the latest publisher documentation before quoting.

Quickstart

Same wire format as direct provider APIs — your existing SDK code keeps working. Point at api.anvat.app/v1 and use your Anvat key.

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.anvat.app/v1",
  apiKey: process.env.ANVAT_API_KEY,
});

const response = await client.chat.completions.create({
  model: "gpt-5-mini",
  max_tokens: 200,
  messages: [
    {
      role: "user",
      content: "Classify the sentiment: 'Service was slow but the food was great.'",
    },
  ],
});

Try GPT-5 mini — 30% off list

Same model, same quality, same wire format — at the discounted Anvat effective rate. $2 free credit on signup, no card required.

Get a key →

Related