THE TICKER · HEAD-TO-HEAD · CHECKED DAILY · LAST CHANGE 2026-10-26
CLAUDE HAIKU 4.5 VS GPT-6.1 TERRA
Anthropic vs OpenAI, in USD per million tokens, cross-checked daily against the public pricing dataset. Same jobs, both meters running.
Effectively a tie: for the same job (a 1,000-token prompt with a 3,000-token reply), Claude Haiku 4.5 and GPT-6.1 Terra bill within 5% of each other. Pick on quality, latency or taste — price won't settle this one.
SIDE BY SIDE
| Claude Haiku 4.5 → | GPT-6.1 Terra → | |
|---|---|---|
| Vendor | Anthropic | OpenAI |
| Input / MTok | $1.00 | $1.00 |
| Output / MTok | $5.00 | $5.00 |
| Output multiple | 5.0x | 5.0x |
| 1K prompt + 3K reply | $0.02 | $0.02 |
SAME JOB, BOTH BILLS
| Scenario | Claude Haiku 4.5 | GPT-6.1 Terra | Gap |
|---|---|---|---|
| A typical prompt | $0.0048 | $0.0048 | — |
| A 20-turn conversation | $0.02 | $0.02 | — |
| Summarizing a 10-page document | $0.02 | $0.02 | — |
| One agent run | $0.06 | $0.06 | — |
| A code review request | $0.02 | $0.02 | — |
Output sizes use the same editorial ratios as the Burn Calculator. Estimates, not invoices — and price is not a benchmark: the cheaper model is only a bargain if it does the job.
SETTLE IT WITH YOUR OWN PROMPT
Paste a real prompt into the Burn Calculator and see what it costs on Claude Haiku 4.5, GPT-6.1 Terra and the other 35 models on the board — plus how much of it is waste either way.