Side by side pricing and context for GPT-5 Nano and Claude Haiku 4.5. Rates are curated catalog values with last verified dates on each model page.
GPT-5 Nano
Cheapest GPT-5 family tier for classification, routing, and ultra-high QPS text jobs. Use when Mini is still too expensive and Exact OpenAI counts matter for budgeting.
Input $0.050 / Output $0.400 per 1M
Context 128K · Exact (o200k_base)
Claude Haiku 4.5
Fast, cheaper Claude for high-volume chat and light tasks. Strong Anthropic budget pick. Token counts are Approx in-browser.
Input $1.00 / Output $5.00 per 1M
Context 200K · Approx (Anthropic family)
Quick take
- GPT-5 Nano is cheaper on input in this catalog snapshot.
- GPT-5 Nano is cheaper on output in this catalog snapshot.
- Both last verified on their model pages (2026-08-02 / 2026-08-02).
Rate table
| Metric | GPT-5 Nano | Claude Haiku 4.5 |
|---|---|---|
| Input / 1M | $0.050 | $1.00 |
| Output / 1M | $0.400 | $5.00 |
| Cached input / 1M | $0.0050 | $0.100 |
| Context | 128K | 200K |
| Tokenizer | Exact (o200k_base) | Approx (Anthropic family) |