Home › Compare › GPT-6.1 Terra vs GPT-5.4 mini
GPT-6.1 Terra vs GPT-5.4 mini
A straight cost comparison of GPT-6.1 Terra (OpenAI) and GPT-5.4 mini (OpenAI), per 1,000,000 tokens, verified November 2026.
Rate-by-rate comparison
| Metric | GPT-6.1 Terra | GPT-5.4 mini | Winner |
|---|---|---|---|
| Input / 1M | $1 | $0.75 | GPT-5.4 mini |
| Cached input / 1M | $0.05 | $0.075 | GPT-6.1 Terra |
| Cache write / 1M | $1.25 | — | GPT-5.4 mini |
| Output / 1M | $5 | $4.50 | GPT-5.4 mini |
| Context window | 1,050,000 | 400,000 | GPT-6.1 Terra |
| Batch API | Yes | Yes | Tie |
| Long-context tier | > 272,000 | None | — |
For per-token metrics, the lower number wins. For context window and batch support, the higher or broader option wins. A dash means the provider does not publish that rate: a missing cache-write fee means writes are not billed per token, while a missing cached-input rate means cache hits bill at the full input rate.
Blended cost: 1M input + 250K output
| Model | Blended cost | Difference |
|---|---|---|
| GPT-6.1 Terra | $2.25 | +$0.375 |
| GPT-5.4 mini | $1.88 | Cheaper |
Ten workloads, two bills
The same two models, priced across ten workloads that differ only in their input:output ratio. Nothing else changes — no retries, no system prompt, no middleware.
| Workload | GPT-6.1 Terra | GPT-5.4 mini | Winner |
|---|---|---|---|
| Classification 100K reqs · 500 in / 10 out | $55 | $42 | GPT-5.4 mini |
| Data extraction 10K reqs · 2K in / 200 out | $30 | $24 | GPT-5.4 mini |
| Support chat 1K reqs · 4K in / 600 out | $7 | $5.70 | GPT-5.4 mini |
| Code review 2K reqs · 8K in / 1.5K out | $31 | $25.50 | GPT-5.4 mini |
| Summarisation 1K reqs · 20K in / 1K out | $25 | $19.50 | GPT-5.4 mini |
| Agent loop 5K reqs · 12K in / 2K out | $110 | $90 | GPT-5.4 mini |
| Translation 500 reqs · 15K in / 15K out | $45 | $39.38 | GPT-5.4 mini |
| Long-document QA 200 reqs · 120K in / 800 out | $24.80 | $18.72 | GPT-5.4 mini |
| Cached RAG 1K reqs · 50K in (45K cached) / 1K out | $12.30 | $11.66 | GPT-5.4 mini |
| Nightly batch 10K reqs · 10K in / 2K out | $100 | $82.50 | GPT-5.4 mini |
GPT-6.1 Terra wins 0 of 10, GPT-5.4 mini wins 10 of 10. The winner is set by the token mix, not by the headline rate.
Where the two bills cross over
GPT-5.4 mini is cheaper on both sides of the mix: $0.75 vs $1 per million input tokens, and $4.50 vs $5 per million output. No input:output ratio reverses that, so on price alone the other model never becomes the better choice — it has to win on context, latency or output quality.
Cost at four scales
The same support-chat workload (4K input, 600 output per request) at four monthly volumes.
| Requests / month | GPT-6.1 Terra | GPT-5.4 mini | Difference |
|---|---|---|---|
| 100 | $0.70 | $0.57 | GPT-5.4 mini cheaper by $0.13 |
| 1,000 | $7 | $5.70 | GPT-5.4 mini cheaper by $1.30 |
| 10,000 | $70 | $57 | GPT-5.4 mini cheaper by $13 |
| 100,000 | $700 | $570 | GPT-5.4 mini cheaper by $130 |
What caching does to each bill
Caching only helps the part of the prompt that repeats. This is the support-chat workload (1,000 requests, 4,000 input tokens each) with an increasing share of that prompt served from a warm cache, written once on the first request.
| Cached share of the prompt | GPT-6.1 Terra | GPT-5.4 mini | Winner |
|---|---|---|---|
| 0% | $7 | $5.70 | GPT-5.4 mini |
| 50% | $5.10 | $4.35 | GPT-5.4 mini |
| 80% | $3.96 | $3.54 | GPT-5.4 mini |
| 95% | $3.39 | $3.14 | GPT-5.4 mini |
Both models publish a cached-read rate, so the discount is comparable: GPT-6.1 Terra reads cache at $0.05 per million, GPT-5.4 mini at $0.075.
Which one should you pick?
GPT-6.1 Terra wins on none of the ten workloads above, while GPT-5.4 mini wins on classification, data extraction, support chat, code review, summarisation, agent loop, translation, long-document qa, cached rag, nightly batch.
Beyond price, the two differ on input rate ($1 vs $0.75); output rate ($5 vs $4.50); cached-input rate ($0.05 vs $0.075); cache-write rate ($1.25 vs —); context window (1,050,000 vs 400,000); long-context tier (yes, above 272,000 vs none).
Batch mode is available on GPT-6.1 Terra and GPT-5.4 mini, which halves the nightly job. Both publish cached-input discounts, so a stable system prompt is worth caching on either.
FAQ
Is GPT-6.1 Terra cheaper than GPT-5.4 mini?
On a blended 1M-input-plus-250K-output workload, GPT-5.4 mini is cheaper by 17% ($1.88 vs $2.25). The gap changes for cache-heavy prompts and for batch jobs, as the workload table shows.
Which handles longer prompts, GPT-6.1 Terra or GPT-5.4 mini?
GPT-5.4 mini has the larger context window (1,050,000 vs 400,000 tokens). Watch the long-context threshold on GPT-6.1 Terra: rates rise once input passes it.
Do both models support prompt caching?
GPT-6.1 Terra bills cached reads at $0.05 per 1M; GPT-5.4 mini at $0.075.
Related comparisons
- GPT-5.4 mini vs GPT-5.4 nano
- GPT-6.1 Terra vs GPT-4.1
- GPT-5.4 mini vs Gemini 4 Hydrogen
- All OpenAI pricing
- All OpenAI pricing