GPT-5 vs GPT-4.1 API pricing
Updated
GPT-5: USD 1.25 input, USD 10 output per 1M tokens (OpenAI and 2 others). GPT-4.1: USD 2 input, USD 8 output per 1M tokens (OpenAI and 2 others). At 3 input tokens per output token, GPT-4.1 costs 1.8% more than GPT-5 (USD 3.50 vs USD 3.438 per 1M).
How do GPT-5 and GPT-4.1 differ on price?
- Cheapest input price: GPT-5 USD 1.25 against USD 2 per 1M tokens, so GPT-4.1 costs 1.6× as much (60% more).
- Cheapest output price: GPT-4.1 USD 8 against USD 10 per 1M tokens, so GPT-5 costs 1.25× as much (25% more).
- Among the 201 indexed models, GPT-5 ranks 165th cheapest and GPT-4.1 168th on the 3:1 blend.
- The cheaper model changes at 2.7 input tokens per output token.
- Both list cached-input discounts: GPT-5 at 3 standard prices of 3, from USD 0.125 (OpenAI, 90% below that provider's input price); GPT-4.1 at 3 standard prices of 3, from USD 0.50 (OpenAI, 75% below that provider's input price).
- Both have 3 providers with a standard price; 3 providers sell both (DigitalOcean, Microsoft Azure and OpenAI).
- On one account, DigitalOcean charges USD 3.438 for GPT-5 (its cheapest price) and USD 3.50 for GPT-4.1 (its cheapest price) at 3:1, tied with 2 other providers for the lowest combined price among the providers that sell both.
- Shopping around matters equally: on both, the dearest standard price is 1× the cheapest.
- OpenAI's own API is one of 3 providers tied for the lowest standard price we found for GPT-5, USD 3.438 at 3:1.
- OpenAI's own API is one of 3 providers tied for the lowest standard price we found for GPT-4.1, USD 3.50 at 3:1.
- GPT-5 has a batch price at 2 providers, from USD 1.719 at 3:1 (OpenAI); GPT-4.1 has a batch price at 2 providers, from USD 1.75 at 3:1 (OpenAI).
- For the one-developer coding agent preset, the gap is USD 7,155 a year in GPT-5's favour (GPT-5 USD 1,429 a month, GPT-4.1 USD 2,025).
- Per character of input, GPT-5 costs 38% less than GPT-4.1 in every measured language, because both use the GPT (o200k) tokenizer.
GPT-5 and GPT-4.1 prices side by side
USD per 1M tokens, standard tier. "Cheapest" is the lowest price at 3 input tokens to 1 output token; each line can come from a different provider.
| Price | GPT-5 | GPT-4.1 |
|---|---|---|
| Model page | GPT-5 (2025-08-07) OpenAI · 3 providers | GPT-4.1 (2025-04-14) OpenAI · 3 providers |
| Cheapest standard price, blended 3:1 | USD 3.438 lower USD 1.25 in / USD 10 out at OpenAI and 2 others OpenAI page checked 2026-11-14 | USD 3.50 USD 2 in / USD 8 out at OpenAI and 2 others OpenAI page checked 2026-11-14 |
| Cheapest input | USD 1.25 lower OpenAI source | USD 2 OpenAI source |
| Cheapest cached input | USD 0.125 lower OpenAI source | USD 0.50 OpenAI source |
| Cheapest output | USD 10 OpenAI source | USD 8 lower OpenAI source |
| Maker's own API | USD 1.25 / USD 10 OpenAI source | USD 2 / USD 8 OpenAI source |
| Median standard price | USD 1.25 / USD 10 input / output, 3 prices | USD 2 / USD 8 input / output, 3 prices |
| Context window | No provider states one on its pricing page. | No provider states one on its pricing page. |
| Providers with a standard price | 3 | 3 |
- Lower marks the lower price on a line; tie, equal prices. Other tiers and free rows are on the model pages.
Report a wrong price or number (email to info@broadnet.ai, with this page's link filled in).
What do GPT-5 and GPT-4.1 cost for a real workload?
30 days at each model's cheapest standard price for the workload (presets of the cost calculator; cached input at the cached price where listed).
| Workload | GPT-5 | GPT-4.1 | Difference |
|---|---|---|---|
| Support chatbot 2,000 requests a day, 1,500 input tokens (60% cached), 300 output | USD 231.75 OpenAI | USD 243.00 OpenAI | USD 11.25 GPT-5 lower |
| RAG over documents 1,000 requests a day, 8,000 input tokens (30% cached), 500 output | USD 369.00 OpenAI | USD 492.00 OpenAI | USD 123.00 GPT-5 lower |
| Coding agent (one developer) 1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning | USD 1,429 OpenAI | USD 2,025 OpenAI | USD 596.25 GPT-5 lower |
GPT-5 is cheaper on all three workloads. The widest gap is on Coding agent (one developer): the dearer model costs 42% more than the cheaper one.
Does the cheaper model change with your input:output ratio?
The cheaper model changes with the mix: below 2.7 input tokens per output token, GPT-4.1 is cheaper; above 2.7, GPT-5 is cheaper. At the site's 3:1 blend, GPT-5 is cheaper. More input per output token, as with retrieval or agents that resend long contexts, favours the lower input price; long answers favour the lower output price.
| Input : output tokens | GPT-5 | GPT-4.1 |
|---|---|---|
| 1 : 3 (long answers) | USD 7.813 OpenAI | USD 6.50 lower OpenAI |
| 1 : 1 | USD 5.625 OpenAI | USD 5 lower OpenAI |
| 3 : 1 (the site’s blend) | USD 3.438 lower OpenAI | USD 3.50 OpenAI |
| 10 : 1 (retrieval, long prompts) | USD 2.045 lower OpenAI | USD 2.545 OpenAI |
| 30 : 1 (agents, big contexts) | USD 1.532 lower OpenAI | USD 2.194 OpenAI |
USD per 1M tokens at the cheapest standard provider for each mix, before cache discounts. Thinking tokens bill as output.
What do GPT-5 and GPT-4.1 cost per character in other languages?
Cost to send 1M characters at each model's cheapest non-promotional standard input price, with the GPT (o200k) tokenizer for GPT-5 (the same one for both, so the gap equals the price gap):
| Content | GPT-5 | GPT-4.1 |
|---|---|---|
| English | USD 0.267 lower Microsoft Azure | USD 0.427 Microsoft Azure |
| Arabic MSA | USD 0.399 lower Microsoft Azure | USD 0.639 Microsoft Azure |
| Egyptian Arabic | USD 0.416 lower Microsoft Azure | USD 0.666 Microsoft Azure |
| Hindi | USD 0.403 lower Microsoft Azure | USD 0.644 Microsoft Azure |
| Chinese | USD 0.964 lower Microsoft Azure | USD 1.54 Microsoft Azure |
| Spanish | USD 0.282 lower Microsoft Azure | USD 0.451 Microsoft Azure |
| Code | USD 0.318 lower Microsoft Azure | USD 0.508 Microsoft Azure |
From the real cost by language dataset (measured tokens per character on FLORES-200 and other texts). Your own text will differ.
Check it on your own traffic
- GPT-5 (2025-08-07) API pricing: all 3 providers and other tiers.
- GPT-4.1 (2025-04-14) API pricing: all 3 providers and other tiers.
- Cost calculator with GPT-5 and GPT-4.1 preloaded
- GPT token counter
- Prompt caching calculator
More comparisons: GPT-5.2 vs GPT-5 · GPT-5 Pro vs GPT-5 · GPT-5 Nano vs GPT-5 · GPT-4.1 Mini vs GPT-4.1 · every GPT-5 comparison · every GPT-4.1 comparison · all 662 price comparisons
Questions
Is GPT-5 cheaper than GPT-4.1?
Yes. On a blend of 3 input tokens to 1 output token, GPT-5 costs USD 3.438 per 1M tokens and GPT-4.1 USD 3.50, at each model's cheapest standard price. For input alone, GPT-5 is cheaper (USD 1.25 against USD 2 per 1M); for output alone, GPT-4.1 is (USD 8 against USD 10). This compares price only, not quality.
What do GPT-5 and GPT-4.1 cost per 1M tokens?
GPT-5: from USD 1.25 input and USD 10 output at OpenAI and 2 others; OpenAI's own API charges USD 1.25 / USD 10; median of 3 standard prices USD 1.25 / USD 10. GPT-4.1: from USD 2 input and USD 8 output at OpenAI and 2 others; OpenAI's own API charges USD 2 / USD 8; median of 3 standard prices USD 2 / USD 8. Each price is read from the provider's own pricing page; the source is linked in the table.
Which providers sell both GPT-5 and GPT-4.1?
3 providers have a standard price for both: DigitalOcean (USD 3.438 and USD 3.50 at 3:1), Microsoft Azure (USD 3.438 and USD 3.50 at 3:1), OpenAI (USD 3.438 and USD 3.50 at 3:1). The first 3 tie for the lowest combined price. Buying each model from its own cheapest provider costs USD 3.438 and USD 3.50.
Which is cheaper for a coding agent or a chatbot, GPT-5 or GPT-4.1?
For a coding agent (1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning): USD 1,429 a month on GPT-5 (OpenAI) against USD 2,025 on GPT-4.1 (OpenAI), a difference of USD 596.25. For a support chatbot (2,000 requests a day, 1,500 input tokens (60% cached), 300 output): USD 231.75 a month on GPT-5 (OpenAI) against USD 243.00 on GPT-4.1 (OpenAI), a difference of USD 11.25. Each uses the cheapest standard price for that workload, cached input included. Try your own numbers.
At what input:output ratio does the cheaper of GPT-5 and GPT-4.1 change?
The cheaper model changes with the mix: below 2.7 input tokens per output token, GPT-4.1 is cheaper; above 2.7, GPT-5 is cheaper. At the site's 3:1 blend, GPT-5 is cheaper. More input per output token, as with retrieval or agents that resend long contexts, favours the lower input price; long answers favour the lower output price.
Do GPT-5 and GPT-4.1 have cached input pricing?
GPT-5 from USD 0.125 per 1M cached input tokens (OpenAI; 3 of 3 standard prices list a discount). GPT-4.1 from USD 0.50 per 1M cached input tokens (OpenAI; 3 of 3 standard prices list a discount). Cached tokens are billed at the input price where no cache price is published.