Home › Compare › GPT-6.1 Terra vs GPT-4.1
GPT-6.1 Terra vs GPT-4.1
A straight cost comparison of GPT-6.1 Terra (OpenAI) and GPT-4.1 (OpenAI), per 1,000,000 tokens, verified November 2026.
Rate-by-rate comparison
| Metric | GPT-6.1 Terra | GPT-4.1 | Winner |
|---|---|---|---|
| Input / 1M | $1 | $2 | GPT-6.1 Terra |
| Cached input / 1M | $0.05 | $0.50 | GPT-6.1 Terra |
| Cache write / 1M | $1.25 | — | GPT-4.1 |
| Output / 1M | $5 | $8 | GPT-6.1 Terra |
| Context window | 1,050,000 | 1,047,576 | 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 | Cheaper |
| GPT-4.1 | $4 | +$1.75 |
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-4.1 | Winner |
|---|---|---|---|
| Classification 100K reqs · 500 in / 10 out | $55 | $108 | GPT-6.1 Terra |
| Data extraction 10K reqs · 2K in / 200 out | $30 | $56 | GPT-6.1 Terra |
| Support chat 1K reqs · 4K in / 600 out | $7 | $12.80 | GPT-6.1 Terra |
| Code review 2K reqs · 8K in / 1.5K out | $31 | $56 | GPT-6.1 Terra |
| Summarisation 1K reqs · 20K in / 1K out | $25 | $48 | GPT-6.1 Terra |
| Agent loop 5K reqs · 12K in / 2K out | $110 | $200 | GPT-6.1 Terra |
| Translation 500 reqs · 15K in / 15K out | $45 | $75 | GPT-6.1 Terra |
| Long-document QA 200 reqs · 120K in / 800 out | $24.80 | $49.28 | GPT-6.1 Terra |
| Cached RAG 1K reqs · 50K in (45K cached) / 1K out | $12.30 | $40.57 | GPT-6.1 Terra |
| Nightly batch 10K reqs · 10K in / 2K out | $100 | $180 | GPT-6.1 Terra |
GPT-6.1 Terra wins 10 of 10, GPT-4.1 wins 0 of 10. The winner is set by the token mix, not by the headline rate.
Where the two bills cross over
GPT-6.1 Terra is cheaper on both sides of the mix: $1 vs $2 per million input tokens, and $5 vs $8 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-4.1 | Difference |
|---|---|---|---|
| 100 | $0.70 | $1.28 | GPT-6.1 Terra cheaper by $0.58 |
| 1,000 | $7 | $12.80 | GPT-6.1 Terra cheaper by $5.80 |
| 10,000 | $70 | $128 | GPT-6.1 Terra cheaper by $58 |
| 100,000 | $700 | $1,280 | GPT-6.1 Terra cheaper by $580 |
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-4.1 | Winner |
|---|---|---|---|
| 0% | $7 | $12.80 | GPT-6.1 Terra |
| 50% | $5.10 | $9.80 | GPT-6.1 Terra |
| 80% | $3.96 | $8 | GPT-6.1 Terra |
| 95% | $3.39 | $7.11 | GPT-6.1 Terra |
Both models publish a cached-read rate, so the discount is comparable: GPT-6.1 Terra reads cache at $0.05 per million, GPT-4.1 at $0.50.
Which one should you pick?
GPT-6.1 Terra wins on classification, data extraction, support chat, code review, summarisation, agent loop, translation, long-document qa, cached rag, nightly batch, while GPT-4.1 wins on none of the ten workloads above.
Beyond price, the two differ on input rate ($1 vs $2); output rate ($5 vs $8); cached-input rate ($0.05 vs $0.50); cache-write rate ($1.25 vs —); context window (1,050,000 vs 1,047,576); long-context tier (yes, above 272,000 vs none).
Batch mode is available on GPT-6.1 Terra and GPT-4.1, 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-4.1?
On a blended 1M-input-plus-250K-output workload, GPT-6.1 Terra is cheaper by 44% ($2.25 vs $4). 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-4.1?
GPT-6.1 Terra has the larger context window (1,050,000 vs 1,047,576 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-4.1 at $0.50.
Related comparisons
- GPT-6.1 Terra vs GPT-5.4 mini
- GPT-6.1 Sol vs GPT-4.1
- GPT-4.1 vs Claude Sonnet 4.6
- All OpenAI pricing
- All OpenAI pricing