OpenAI vs Claude, compared on real cost. We ran every model from both on the same example workload (chatbot, 100k requests/mo, 70% cached) so the prices line up directly. The lowest-cost model across both is GPT-5.4 nano ($52.3/mo). Full table and verdict below.
At the budget end, OpenAI is the lower-cost option on this workload: OpenAI's cheapest (GPT-5.4 nano) is $52.3/mo vs Claude's (Claude Haiku 4.5) $224/mo.
At the top end, OpenAI's flagship GPT-5.5 runs $1,270/mo vs Claude's Claude Fable 5 at $2,240/mo. Largest verified context window — OpenAI: 1M tokens; Claude: 1M tokens.
Both are priced by the same engine, so compare your own workload in the calculator — the cheaper choice flips with your token mix and cache share.
Every model from both providers on one example workload (100k requests/mo, 2,000 input / 300 output tokens, 70% cached), cheapest first. The single lowest-cost model is highlighted.
| Model | $ input /1M | $ output /1M | $ cached /1M | ≈ $/mo * |
|---|---|---|---|---|
| GPT-5.4 nanoBUDGETOpenAI | $0.20 | $1.25 | $0.02 | $52.3 |
| GPT-5.4 miniMIDOpenAI | $0.75 | $4.50 | $0.075 | $190.5 |
| Claude Haiku 4.5BUDGETAnthropic | $1 | $5 | $0.10 | $224 |
| GPT-5.4FRONTIEROpenAI | $2.50 | $15 | $0.25 | $635 |
| Claude Sonnet 4.6MIDAnthropic | $3 | $15 | $0.30 | $672 |
| Claude Opus 4.8FRONTIERAnthropic | $5 | $25 | $0.50 | $1,120 |
| GPT-5.5FRONTIEROpenAI | $5 | $30 | $0.50 | $1,270 |
| Claude Fable 5FRONTIERAnthropic | $10 | $50 | $1 | $2,240 |
| GPT-5.5 ProFRONTIEROpenAI | $30 | $180 | — | $11,400 |
* Same engine as the calculator. See OpenAI pricing · Claude pricing in full.