DeepSeek R1 0528 API pricing
Updated
Among the 5 providers we checked (prices read 2026-11-14 to 2026-11-15), the lowest blended standard price for DeepSeek R1 0528 is Featherless at USD 0.385 per 1M input tokens and USD 1.625 per 1M output tokens. The median across 5 standard prices is USD 0.57 / USD 2.29. Each price is read from the provider's own pricing page.
Does DeepSeek sell DeepSeek R1 0528 directly?
DeepSeek publishes no price for DeepSeek R1 0528 on its own API that we could find, so this page compares hosts only.
DeepSeek R1 0528 model facts
Facts from DeepSeek's model card for deepseek-ai/DeepSeek-R1-0528 and the Hugging Face model API, read 2026-11-16. BroadNet did not verify them, and hosts may serve the model at a different precision. BroadRouter is BroadNet's site.
| Fact | As stated | Source |
|---|---|---|
| Open weights | Yes. The weights are in a public Hugging Face repository (deepseek-ai/DeepSeek-R1-0528) with no access gate. | Hugging Face model API, checked 2026-11-16Quote“"private": false, "gated": false, 163 .safetensors files listed” |
| Licence | MIT (mit) | DeepSeek model card metadata, checked 2026-11-16Quote“license: mit” |
| Parameters in the weight files (Hugging Face count, not the maker's figure) | About 684.5 billion (684,531,386,000) | Hugging Face model API, checked 2026-11-16Quote“"safetensors": { "total": 684531386000 }” |
| Context length | Not found on DeepSeek's model card when we read it; see the context column in the price table | checked 2026-11-16 |
| Tool calling | Yes | DeepSeek model card, checked 2026-11-16Quote“enhanced support for function calling” |
| First published on Hugging Face (not necessarily the release date) | 2025-05-28 | Hugging Face model API, checked 2026-11-16Quote“"createdAt": "2025-05-28T09:46:42.000Z"” |
DeepSeek R1 0528 price per provider
USD per 1M tokens. Standard prices are ranked on a blend of 3 input tokens to 1 output token, cheapest first; the dearest standard price is 3.4× the cheapest. Free rows, the maker's serving version and other service tiers follow, tagged and unranked.
| # | Provider | Input | Cached input | Output | Blended 3:1 | Context | Precision | Source |
|---|---|---|---|---|---|---|---|---|
| 1 | Featherless cheapestdeepseek-ai/DeepSeek-R1-0528Notes and source quoteDeveloper plan (per-token billing, from 50 USD a month in credits). No cached price published. “PRICING: INPUT $0.385 / OUTPUT $1.625” | USD 0.385 | not published | USD 1.625 | USD 0.695 | 131,072 | FP8 | Featherless page checked 2026-11-15 re-checked 2026-11-16 |
| 2 | DeepInfradeepseek-ai/DeepSeek-R1-0528Notes and source quote“$0.50 in $2.15 out $0.35 cached / 1M tokens” | USD 0.50 | USD 0.35 | USD 2.15 | USD 0.9125 | 163,840 | FP4 | DeepInfra page checked 2026-11-14 re-checked 2026-11-16 |
| 3 | GMI Clouddeepseek-ai/DeepSeek-R1-0528Notes and source quote“Price (per 1M tokens) Input $0.57 Output $2.29 Cache Read $0.23 Cache Write -” | USD 0.57 | USD 0.23 | USD 2.29 | USD 1 | 131,072 | FP8 | GMI Cloud page checked 2026-11-15 re-checked 2026-11-16 |
| 4 | Novita AIdeepseek/deepseek-r1-0528Notes and source quote“DeepSeek R1 0528 160K $0.7 /Mt · Cache Read $0.35 /Mt $2.5 /Mt” | USD 0.70 | USD 0.35 | USD 2.50 | USD 1.15 | 163,840 | not stated | Novita AI page checked 2026-11-14 re-checked 2026-11-16 |
| 5 | Google Vertex AIdeepseek-r1-0528Notes and source quote“DeepSeek-R1 (0528) Input $1.35 … Output $5.40” | USD 1.35 | not published | USD 5.40 | USD 2.363 | not stated | not stated | Google Vertex AI page checked 2026-11-14 re-checked 2026-11-16 |
| — | Google Vertex AI batchdeepseek-r1-0528Notes and source quote“DeepSeek-R1 (0528) Batch Input $0.675 … Batch Output $2.70” | USD 0.675 | not published | USD 2.70 | USD 1.181 | not stated | not stated | Google Vertex AI page checked 2026-11-14 re-checked 2026-11-16 |
| — | DeepInfra flex / spotdeepseek-ai/DeepSeek-R1-0528Notes and source quoteFlex service tier (0.8× standard). “Flex (0.8×) $0.40 $1.72 $0.28” | USD 0.40 | USD 0.28 | USD 1.72 | USD 0.73 | 163,840 | FP4 | DeepInfra page checked 2026-11-14 re-checked 2026-11-16 |
- Ranked: standard-tier prices only, on (3 × input + output) ÷ 4. "Cached input: not published" means the provider's page shows no cache price; budget cached tokens at the input price.
- Other tiers (batch and flex / spot): batch runs asynchronously within hours; flex and spot are best-effort and can be slow or refused at capacity; priority and fast cost more for reliability or speed. Shown, not ranked.
- Automated re-check 2026-11-16: a weekly job re-fetches each source page and looks for the recorded quote or prices. It is not a human review. "Re-checked" means it still found them. Rows with no re-check note show only the date the price was read.
- Precision is shown only where the provider states it; "not stated" is unknown, not full precision.
Report a wrong price or number (email to info@broadnet.ai, with this page's link filled in).
What does DeepSeek R1 0528 cost for a real workload?
Monthly cost over 30 days at each standard price, using the presets of the LLM API cost calculator. Providers without a cached price bill cached input at the input price.
- Support chatbot: 2,000 requests a day, 1,500 input tokens (60% cached), 300 output.
- RAG over documents: 1,000 requests a day, 8,000 input tokens (30% cached), 500 output.
- Coding agent (one developer): 1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning.
| Provider | Support chatbot | RAG over documents | Coding agent (one developer) |
|---|---|---|---|
| Featherless | USD 63.90 | USD 116.78 | USD 839.25 |
| DeepInfra | USD 75.60 | USD 141.45 | USD 864.00 |
| GMI Cloud | USD 74.16 | USD 146.67 | USD 711.90 |
| Novita AI | USD 89.10 | USD 180.30 | USD 949.50 |
| Google Vertex AI | USD 218.70 | USD 405.00 | USD 2,916 |
For the support chatbot, the cheapest price (Featherless, USD 63.90 a month) saves USD 11.70 against the median (USD 75.60). For the coding agent the gap is USD 152.10 a month (18% lower). The winner changes with the workload: GMI Cloud wins the cache-heavy agent, Featherless the chatbot.
Which DeepSeek R1 0528 provider is cheapest for your traffic?
Featherless has the lowest input price (USD 0.385) and the lowest output price (USD 1.625), so it is the cheapest standard price at every mix of input and output tokens, before cache discounts.
| Provider | No cache hits | 50% cached | 90% cached |
|---|---|---|---|
| Featherless (no cache price) | USD 0.695 cheapest | USD 0.695 cheapest | USD 0.695 cheapest |
| DeepInfra | USD 0.9125 | USD 0.8562 | USD 0.8113 |
| GMI Cloud | USD 1 | USD 0.8725 | USD 0.7705 |
| Novita AI | USD 1.15 | USD 1.019 | USD 0.9138 |
| Google Vertex AI (no cache price) | USD 2.363 | USD 2.363 | USD 2.363 |
USD per 1M tokens, 3 input tokens to 1 output token, each provider's cheapest standard row. A provider without a cached price bills cached input at the input price. Any charge for writing to the cache, which some providers add, is not included.
3 of 5 providers publish a cached-input price below the input price: DeepInfra (30% off), GMI Cloud (60% off), Novita AI (50% off). Featherless and Google Vertex AI publish none, so cached tokens there bill at the input price.
Context windows differ: 163,840 tokens at DeepInfra and Novita AI; 131,072 tokens at Featherless and GMI Cloud. Google Vertex AI does not state one. The cheapest row is not always the one that fits a long prompt.
What does DeepSeek R1 0528 cost in other languages?
The same text needs a different number of tokens in each language. With the DeepSeek V4.1 Flash tokenizer, sending 1M characters costs this much at the cheapest standard input price we found for DeepSeek R1 0528:
| Content | Input per 1M characters | Cheapest provider |
|---|---|---|
| English | USD 0.082 | Featherless |
| Arabic MSA | USD 0.145 | Featherless |
| Hindi | USD 0.222 | Featherless |
| Chinese | USD 0.226 | Featherless |
| Code | USD 0.102 | Featherless |
From BroadRouter's real cost by language dataset, which covers 15 languages and content types for every model we could match to a measured tokenizer.
Estimate your own bill
- LLM API cost calculator with DeepSeek R1 0528 preloaded: your traffic and cache rate, against any of 429 models.
- DeepSeek token counter: count the tokens in your real prompts. Tokenizers differ, so the same text costs a different number of tokens on different models.
- Prompt caching calculator: what a higher cache-hit rate saves.
How does DeepSeek R1 0528 compare with other DeepSeek models?
The DeepSeek models whose cheapest standard price is closest to DeepSeek R1 0528's (USD 0.695 blended):
| Model | Cheapest input | Cheapest output | Max context | Providers |
|---|---|---|---|---|
| DeepSeek R1 Distill Qwen 32B | USD 0.50 | USD 0.90 | 131,072 | 3 |
| DeepSeek R1 | USD 0.50 | USD 2.18 | 163,840 | 4 |
| DeepSeek V3 0324 | USD 0.29 | USD 1.14 | 131,072 | 3 |
| DeepSeek-V3.1-Terminus | USD 0.27 | USD 1 | 163,840 | 3 |
| DeepSeek V3 | USD 0.25 | USD 1 | 163,840 | 3 |
| DeepSeek V3.1 | USD 0.25 | USD 0.95 | 163,840 | 7 |
Priced closest from other makers: GPT-4.1 Mini (OpenAI, USD 0.70) · GPT-5 Mini (OpenAI, USD 0.6875) · Qwen3.6 27B (Qwen, USD 0.6875).
Compare DeepSeek R1 0528 with
- DeepSeek R1 0528 vs DeepSeek R1: API price side by side
Also compared: vs DeepSeek R1.
Every DeepSeek R1 0528 price comparison · All model-vs-model price comparisons
All 429 models: API prices compared · Cheapest LLM APIs right now · LLM API price index (open data) · Download all prices (CSV, JSON) · Price change log
Questions
How much does the DeepSeek R1 0528 API cost per token?
From USD 0.385 per 1M input tokens (USD 0.000000385 per token) and USD 1.625 per 1M output tokens (USD 0.000001625 per token) at the lowest standard prices we found. The median of 5 standard prices is USD 0.57 input and USD 2.29 output. Each price was read from the provider's own pricing page; the source is linked in its row.
Which provider is cheapest for DeepSeek R1 0528?
Among the 5 providers we checked (prices read 2026-11-14 to 2026-11-15), the lowest is Featherless, ranked on a blend of 3 input tokens to 1 output token (USD 0.695 per 1M). It also has the lowest input and the lowest output price. Batch, flex, priority and fast tiers are shown in the table but not ranked.
Does DeepSeek sell DeepSeek R1 0528 on its own API?
DeepSeek publishes no price for DeepSeek R1 0528 on its own API that we could find, so there is no maker price to compare. The lowest-priced host we checked is Featherless at USD 0.385 / USD 1.625 per 1M tokens.
Does DeepSeek R1 0528 have cached input pricing?
3 of 5 standard prices include one. The lowest is USD 0.23 per 1M at GMI Cloud; the median is USD 0.35. Providers without one bill cached input at the input price. What cached input means.
What is the DeepSeek R1 0528 context window?
Up to 163,840 tokens. 2 standard prices come with less, down to 131,072 tokens (Featherless and GMI Cloud). Check the context column before you pick the cheapest row for long prompts. Context window calculator.
How much does a coding agent cost per month on DeepSeek R1 0528?
For 1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning, over 30 days: USD 711.90 a month at GMI Cloud, USD 864.00 at the median price and USD 2,916 at Google Vertex AI. Try your own numbers.
Is there a batch, flex or priority price for DeepSeek R1 0528?
Yes: batch from Google Vertex AI at USD 0.675 / USD 2.70; flex / spot from DeepInfra at USD 0.40 / USD 1.72 per 1M input / output tokens. These tiers trade speed or availability for price (batch runs within hours, flex and spot can be slow or refused at capacity, priority and fast cost more for speed or reliability), so they are shown but not ranked.
Is DeepSeek R1 0528 free to use through an API?
No provider in our data lists a free price for DeepSeek R1 0528 as of 2026-11-15. Free tiers and credits by provider (checked 2026-11-14) lists general offers that do not name a model; all free LLM API models are on one page.
Is DeepSeek R1 0528 open source, with open weights, and what is its licence?
DeepSeek publishes the weights on Hugging Face as deepseek-ai/DeepSeek-R1-0528, in a public repository with no access gate. The licence, as the DeepSeek model card metadata states it: MIT (mit). Open weights means you can download and run the model yourself; what you may do with it, including commercial use, is set by that licence, so read it in full (checked 2026-11-16). These facts come from DeepSeek's card and the Hugging Face model API; BroadNet did not verify them, and hosts may serve the model at a different precision.
How many parameters does DeepSeek R1 0528 have?
DeepSeek's model card does not state a total that we found. Hugging Face counts about 684.5 billion (684,531,386,000) parameters in the published weight files of deepseek-ai/DeepSeek-R1-0528. That is a file-level count, not the maker's figure, and it can include extra modules (checked 2026-11-16).
Does DeepSeek R1 0528 support tool calling?
Yes, according to the DeepSeek model card: “enhanced support for function calling” (checked 2026-11-16). Whether the tools parameter works through an API also depends on the provider serving it, so check that provider's docs. BroadNet did not test it.
How do I call DeepSeek R1 0528 with the OpenAI SDK?
BroadNet does not serve DeepSeek R1 0528. Use the OpenAI-compatible base URL of a provider that lists it: create the client with OpenAI(base_url=..., api_key=...) and pass that provider's model ID. Documented base URLs for providers on this page, in alphabetical order: DeepInfra (https://api.deepinfra.com/v1/openai, model deepseek-ai/DeepSeek-R1-0528). Each provider page quotes the provider's docs with a check date.