← tokenmark
claude-sonnet-4-6 vs gpt-5-mini — cost comparison
Anthropic Claude claude-sonnet-4-6 vs OpenAI gpt-5-mini — list pricing, worked examples, interactive calculator. Verified 2026-05-15.
TL;DR. gpt-5-mini is cheaper on both input (6.0×) and output (7.5×).
Headline pricing
| claude-sonnet-4-6 | gpt-5-mini |
|---|
| Input / 1M tokens | $3.00 | $0.50 |
| Output / 1M tokens | $15.00 | $2.00 |
| Cache write / 1M tokens | $3.75 | — |
| Cache read / 1M tokens | $0.30 | $0.05 |
Sources: Anthropic Claude, OpenAI. Verified 2026-05-15. Re-verify before relying on these numbers for budget commits.
Worked examples (per call, list pricing)
| Workload shape | claude-sonnet-4-6 | gpt-5-mini | Cheaper |
|---|
| 1k in + 500 out (tool call) | $0.0105 | $0.0015 | gpt-5-mini (7.0× cheaper) |
| 10k in + 1k out (RAG) | $0.0450 | $0.0070 | gpt-5-mini (6.4× cheaper) |
| 100k in + 1k out (long doc) | $0.315 | $0.0520 | gpt-5-mini (6.1× cheaper) |
| 2k in + 4k out (long gen) | $0.0660 | $0.0090 | gpt-5-mini (7.3× cheaper) |
Interactive calculator
How to choose between claude-sonnet-4-6 and gpt-5-mini
- Quality first. Cost only matters if both models clear your quality bar. Run a 30-call eval on real prompts before committing to the cheaper option. If quality is unequal, the price difference is a distraction.
- Match price to call shape. claude-sonnet-4-6 costs
$3.00 in / $15.00 out. gpt-5-mini costs $0.50 in / $2.00 out. Workloads that are completion-heavy weigh output prices more.
- Caching changes the math. claude-sonnet-4-6 cache-read is $0.30 (10× off input). gpt-5-mini cache-read is $0.05. If your prompts have a stable prefix, the model with the better cache discount typically wins on re-use.
- Latency may matter more than dollars. Some providers are 5-10× faster at the same price tier. If you're below a few thousand calls/day, latency UX usually beats price.
Track what you're actually spending on each
Wrap your provider client with tokenmark to get per-call cost attribution across providers and models. No platform, no signup — JSONL log on disk you can query via CLI or MCP.
npm i tokenmark
Try in-browser →
Hosted analyzer →
Related comparisons
Anthropic Claude full pricing · OpenAI full pricing · All-provider comparison
About this page. Built and maintained by an autonomous AI agent under KS Elevated Solutions LLC. Pricing data comes from each provider's published pricing page, verified 2026-05-15; the same table is bundled in the
tokenmark npm package. No fabricated reviews, ratings, or social proof. See full
AI disclosure.