DeepSeek R1 0528 vs GPT-4.1 Mini API pricing
Updated
DeepSeek R1 0528: USD 0.385 input, USD 1.625 output per 1M tokens (Featherless). GPT-4.1 Mini: USD 0.40 input, USD 1.60 output per 1M tokens (OpenAI and 1 other). At 3 input tokens per output token, GPT-4.1 Mini costs 0.7% more than DeepSeek R1 0528 (USD 0.70 vs USD 0.695 per 1M).
How do DeepSeek R1 0528 and GPT-4.1 Mini differ on price?
- Cheapest input price: DeepSeek R1 0528 USD 0.385 against USD 0.40 per 1M tokens, so GPT-4.1 Mini costs 1.04× as much (4% more).
- Cheapest output price: GPT-4.1 Mini USD 1.60 against USD 1.625 per 1M tokens, so DeepSeek R1 0528 costs 1.02× as much (2% more).
- Among the 201 indexed models, DeepSeek R1 0528 ranks 110th cheapest and GPT-4.1 Mini 111th on the 3:1 blend.
- The cheaper model changes at 1.7 input tokens per output token.
- Both list cached-input discounts: DeepSeek R1 0528 at 3 standard prices of 5, from USD 0.23 (GMI Cloud, 60% below that provider's input price); GPT-4.1 Mini at 2 standard prices of 2, from USD 0.10 (OpenAI, 75% below that provider's input price).
- Only DeepSeek R1 0528 has a stated context window (163,840 tokens); no provider of GPT-4.1 Mini states one on its pricing page.
- DeepSeek R1 0528 has 5 providers with a standard price, 3 more than GPT-4.1 Mini; no provider sells both, so using both means two accounts.
- Shopping around matters more for DeepSeek R1 0528: its dearest standard price is 3.4× its cheapest, against 1× for GPT-4.1 Mini.
- OpenAI's own API is one of 2 providers tied for the lowest standard price we found for GPT-4.1 Mini, USD 0.70 at 3:1.
- DeepSeek R1 0528 has a batch price at 1 provider, from USD 1.181 at 3:1 (Google Vertex AI); GPT-4.1 Mini has a batch price at 2 providers, from USD 0.35 at 3:1 (OpenAI).
- For the one-developer coding agent preset, the gap is USD 3,683 a year in GPT-4.1 Mini's favour (DeepSeek R1 0528 USD 711.90 a month, GPT-4.1 Mini USD 405.00).
- Per character of input, the gap depends on the language: DeepSeek R1 0528 costs 1.73× as much as GPT-4.1 Mini on Hindi text but 27% less than GPT-4.1 Mini on Chinese, because the two tokenizers split those languages differently.
DeepSeek R1 0528 and GPT-4.1 Mini 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 | DeepSeek R1 0528 | GPT-4.1 Mini |
|---|---|---|
| Model page | DeepSeek R1 0528 DeepSeek · 5 providers | GPT-4.1 Mini OpenAI · 2 providers |
| Cheapest standard price, blended 3:1 | USD 0.695 lower USD 0.385 in / USD 1.625 out at Featherless Featherless page checked 2026-11-15 | USD 0.70 USD 0.40 in / USD 1.60 out at OpenAI and 1 other OpenAI page checked 2026-11-14 |
| Cheapest input | USD 0.385 lower Featherless source | USD 0.40 OpenAI source |
| Cheapest cached input | USD 0.23 GMI Cloud source | USD 0.10 lower OpenAI source |
| Cheapest output | USD 1.625 Featherless source | USD 1.60 lower OpenAI source |
| Maker's own API | DeepSeek publishes no paid standard price on its own API that we found. | USD 0.40 / USD 1.60 OpenAI source |
| Median standard price | USD 0.57 / USD 2.29 input / output, 5 prices | USD 0.40 / USD 1.60 input / output, 2 prices |
| Context window | 163,840 tokens, largest stated; from 131,072 at some providers | No provider states one on its pricing page. |
| Providers with a standard price | 5 | 2 |
- 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 DeepSeek R1 0528 and GPT-4.1 Mini 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 | DeepSeek R1 0528 | GPT-4.1 Mini | Difference |
|---|---|---|---|
| Support chatbot 2,000 requests a day, 1,500 input tokens (60% cached), 300 output | USD 63.90 Featherless | USD 48.60 OpenAI | USD 15.30 GPT-4.1 Mini lower |
| RAG over documents 1,000 requests a day, 8,000 input tokens (30% cached), 500 output | USD 116.78 Featherless | USD 98.40 OpenAI | USD 18.38 GPT-4.1 Mini lower |
| Coding agent (one developer) 1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning | USD 711.90 GMI Cloud | USD 405.00 OpenAI | USD 306.90 GPT-4.1 Mini lower |
GPT-4.1 Mini is cheaper on all three workloads. The widest gap is on Coding agent (one developer): the dearer model costs 76% more than the cheaper one.
Does the cheaper model change with your input:output ratio?
The cheaper model changes with the mix: below 1.7 input tokens per output token, GPT-4.1 Mini is cheaper; above 1.7, DeepSeek R1 0528 is cheaper. At the site's 3:1 blend, DeepSeek R1 0528 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 | DeepSeek R1 0528 | GPT-4.1 Mini |
|---|---|---|
| 1 : 3 (long answers) | USD 1.315 Featherless | USD 1.30 lower OpenAI |
| 1 : 1 | USD 1.005 Featherless | USD 1 lower OpenAI |
| 3 : 1 (the site’s blend) | USD 0.695 lower Featherless | USD 0.70 OpenAI |
| 10 : 1 (retrieval, long prompts) | USD 0.4977 lower Featherless | USD 0.5091 OpenAI |
| 30 : 1 (agents, big contexts) | USD 0.425 lower Featherless | USD 0.4387 OpenAI |
USD per 1M tokens at the cheapest standard provider for each mix, before cache discounts. Thinking tokens bill as output.
What do DeepSeek R1 0528 and GPT-4.1 Mini cost per character in other languages?
Cost to send 1M characters at each model's cheapest non-promotional standard input price, with the DeepSeek V4.1 Flash tokenizer for DeepSeek R1 0528 and the GPT (o200k) tokenizer for GPT-4.1 Mini:
| Content | DeepSeek R1 0528 | GPT-4.1 Mini |
|---|---|---|
| English | USD 0.082 lower Featherless | USD 0.085 Microsoft Azure |
| Arabic MSA | USD 0.145 Featherless | USD 0.128 lower Microsoft Azure |
| Egyptian Arabic | USD 0.149 Featherless | USD 0.133 lower Microsoft Azure |
| Hindi | USD 0.222 Featherless | USD 0.129 lower Microsoft Azure |
| Chinese | USD 0.226 lower Featherless | USD 0.309 Microsoft Azure |
| Spanish | USD 0.099 Featherless | USD 0.090 lower Microsoft Azure |
| Code | USD 0.102 lower Featherless | USD 0.102 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
- DeepSeek R1 0528 API pricing: all 5 providers and other tiers.
- GPT-4.1 Mini API pricing: all 2 providers and other tiers.
- Cost calculator with DeepSeek R1 0528 and GPT-4.1 Mini preloaded
- DeepSeek token counter
- GPT token counter
- Prompt caching calculator
More comparisons: DeepSeek R1 0528 vs DeepSeek R1 · GPT-5 Mini vs GPT-4.1 Mini · GPT-4.1 Mini vs GPT-4.1 · every DeepSeek R1 0528 comparison · every GPT-4.1 Mini comparison · all 662 price comparisons
Questions
Is DeepSeek R1 0528 cheaper than GPT-4.1 Mini?
Yes. On a blend of 3 input tokens to 1 output token, DeepSeek R1 0528 costs USD 0.695 per 1M tokens and GPT-4.1 Mini USD 0.70, at each model's cheapest standard price. For input alone, DeepSeek R1 0528 is cheaper (USD 0.385 against USD 0.40 per 1M); for output alone, GPT-4.1 Mini is (USD 1.60 against USD 1.625). This compares price only, not quality.
What do DeepSeek R1 0528 and GPT-4.1 Mini cost per 1M tokens?
DeepSeek R1 0528: from USD 0.385 input and USD 1.625 output at Featherless; median of 5 standard prices USD 0.57 / USD 2.29. GPT-4.1 Mini: from USD 0.40 input and USD 1.60 output at OpenAI and 1 other; OpenAI's own API charges USD 0.40 / USD 1.60; median of 2 standard prices USD 0.40 / USD 1.60. Each price is read from the provider's own pricing page; the source is linked in the table.
Which providers sell both DeepSeek R1 0528 and GPT-4.1 Mini?
None of the providers we track sells both at a standard price. DeepSeek R1 0528 is cheapest at Featherless and GPT-4.1 Mini at OpenAI and 1 other, so running both means two accounts.
Which is cheaper for a coding agent or a chatbot, DeepSeek R1 0528 or GPT-4.1 Mini?
For a coding agent (1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning): USD 711.90 a month on DeepSeek R1 0528 (GMI Cloud) against USD 405.00 on GPT-4.1 Mini (OpenAI), a difference of USD 306.90. For a support chatbot (2,000 requests a day, 1,500 input tokens (60% cached), 300 output): USD 63.90 a month on DeepSeek R1 0528 (Featherless) against USD 48.60 on GPT-4.1 Mini (OpenAI), a difference of USD 15.30. 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 DeepSeek R1 0528 and GPT-4.1 Mini change?
The cheaper model changes with the mix: below 1.7 input tokens per output token, GPT-4.1 Mini is cheaper; above 1.7, DeepSeek R1 0528 is cheaper. At the site's 3:1 blend, DeepSeek R1 0528 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 DeepSeek R1 0528 and GPT-4.1 Mini have cached input pricing?
DeepSeek R1 0528 from USD 0.23 per 1M cached input tokens (GMI Cloud; 3 of 5 standard prices list a discount). GPT-4.1 Mini from USD 0.10 per 1M cached input tokens (OpenAI; 2 of 2 standard prices list a discount). Cached tokens are billed at the input price where no cache price is published.