Side by side pricing and context for GPT-5 and Claude Sonnet 5. Rates are curated catalog values with last verified dates on each model page.
GPT-5
OpenAI frontier model for hard coding, agents, and long-context production work. Use when quality matters more than the cheapest token rate, then check cache and batch in TokenCALC before you scale.
Input $1.25 / Output $10.00 per 1M
Context 400K · Exact (o200k_base)
Claude Sonnet 5
Balanced Claude for most production apps: strong quality without Opus cost. Check the introductory vs standard rate note and re-run TokenCALC after pricing changes.
Input $2.00 / Output $10.00 per 1M
Context 1M · Approx (Anthropic family)
Quick take
- GPT-5 is cheaper on input in this catalog snapshot.
- Output rates match on this snapshot.
- Both last verified on their model pages (2026-08-02 / 2026-08-02).
Rate table
| Metric | GPT-5 | Claude Sonnet 5 |
|---|---|---|
| Input / 1M | $1.25 | $2.00 |
| Output / 1M | $10.00 | $10.00 |
| Cached input / 1M | $0.125 | $0.200 |
| Context | 400K | 1M |
| Tokenizer | Exact (o200k_base) | Approx (Anthropic family) |