Compare estimated cost across major LLM APIs for a given number of input and output tokens.
| Model | Provider | $/1M in | $/1M out | Est. cost this run |
|---|---|---|---|---|
| GPT-4o mini | OpenAI | $0.15 | $0.60 | $0.00270 |
| GPT-4o | OpenAI | $2.50 | $10.00 | $0.0450 |
| Gemini 3 Flash | $0.50 | $3.00 | $0.0110 | |
| Gemini 3.1 Pro | $2.00 | $12.00 | $0.0440 | |
| Claude Sonnet 5 | Anthropic | $2.00 | $10.00 | $0.0400 |
| Claude Opus 4.6 | Anthropic | $5.00 | $25.00 | $0.1000 |
10,000 input tokens and 2,000 output tokens on GPT-4o mini costs $0.15/1M × 0.01 + $0.60/1M × 0.002 = $0.0015 + $0.0012 = $0.0027. The same call on Claude Opus 4.6 costs $5.00/1M × 0.01 + $25.00/1M × 0.002 = $0.05 + $0.05 = $0.10, roughly 37x more expensive for an identical prompt and response length.
This table intentionally skips a numeric leaderboard score (MMLU, Arena ELO, etc.) next to each model. Those rankings shift week to week as providers ship updates and evaluators re-baseline — the same reason this page snapshots pricing by date instead of claiming a live feed. What tends to stay stable for longer is each provider's own tier positioning: which model they built for cheap, high-volume calls versus their hardest reasoning tasks. That's what the table below reflects.
| Model | Positioning |
|---|---|
| GPT-4o mini | OpenAI's compact, low-cost tier — built for high-volume, latency-sensitive work (classification, extraction, simple chat), not frontier reasoning. |
| GPT-4o | OpenAI's general-purpose multimodal flagship at this pricing snapshot — handles vision, reasoning, and coding in one model. |
| Gemini 3 Flash | Google's fast, cost-efficient tier with a large context window — suited to high-throughput or long-document workloads over peak reasoning depth. |
| Gemini 3.1 Pro | Google's higher-capability tier — stronger multi-step reasoning and multimodal handling than Flash, at a proportionally higher cost. |
| Claude Sonnet 5 | Anthropic's balanced mid-tier — positioned for coding and agentic tool-use workloads where cost-per-call matters at scale. |
| Claude Opus 4.6 | Anthropic's highest-capability tier — reserved for the hardest reasoning/coding tasks, priced well above Sonnet accordingly. |
For a live, frequently-updated numeric comparison, see LMArena's leaderboard (head-to-head human preference voting) or Artificial Analysis's MMLU-Pro leaderboard (standardized benchmark scoring) — both update far more often than a static page like this one could stay accurate.
Pricing is a point-in-time snapshot, not a live feed, and providers change rates without much notice. This is not a guarantee of billing accuracy. Confirm current rates directly with each provider before relying on these figures for budgeting.