DeepSeek-V3.1-Terminus API pricing
Updated
Among the 3 providers we checked (prices read 2026-11-14 to 2026-11-15), 2 tie for the lowest blended standard price for DeepSeek-V3.1-Terminus; GMI Cloud charges USD 0.27 per 1M input tokens and USD 1 per 1M output tokens. The median across 3 standard prices is USD 0.27 / USD 1. Each price is read from the provider's own pricing page.
Does DeepSeek sell DeepSeek-V3.1-Terminus directly?
DeepSeek publishes no price for DeepSeek-V3.1-Terminus on its own API that we could find, so this page compares hosts only.
DeepSeek-V3.1-Terminus model facts
Facts from DeepSeek's model card for deepseek-ai/DeepSeek-V3.1-Terminus 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-V3.1-Terminus) 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 | Not found on DeepSeek's model card when we read it | checked 2026-11-16 |
| First published on Hugging Face (not necessarily the release date) | 2025-09-22 | Hugging Face model API, checked 2026-11-16Quote“"createdAt": "2025-09-22T04:56:04.000Z"” |
DeepSeek-V3.1-Terminus 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 2% above the cheapest.
| # | Provider | Input | Cached input | Output | Blended 3:1 | Context | Precision | Source |
|---|---|---|---|---|---|---|---|---|
| 1 | GMI Cloud tied cheapestdeepseek-ai/DeepSeek-V3.1-TerminusNotes and source quoteNo cache-read price published. “Price (per 1M tokens) Input $0.27 Output $1.00” | USD 0.27 | not published | USD 1 | USD 0.4525 | 131,072 | FP8 | GMI Cloud page checked 2026-11-15 re-checked 2026-11-16 |
| 2 | SiliconFlow tied cheapestNotes and source quoteContext shown as 164K. “DeepSeek-V3.1-Terminus 164K $0.27 $1.0” | USD 0.27 | not published | USD 1 | USD 0.4525 | 163,840 | not stated | SiliconFlow page checked 2026-11-14 re-checked 2026-11-16 |
| 3 | Featherlessdeepseek-ai/DeepSeek-V3.1-TerminusNotes and source quoteDeveloper plan (per-token billing, from 50 USD a month in credits). No cached price published. “PRICING: INPUT $0.285 / OUTPUT $1” | USD 0.285 | not published | USD 1 | USD 0.4637 | 131,072 | FP8 | Featherless page checked 2026-11-15 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.
- 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-V3.1-Terminus 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) |
|---|---|---|---|
| GMI Cloud | USD 42.30 | USD 79.80 | USD 576.00 |
| SiliconFlow | USD 42.30 | USD 79.80 | USD 576.00 |
| Featherless | USD 43.65 | USD 83.40 | USD 603.00 |
For the support chatbot, the cheapest price (GMI Cloud and 1 other, tied, USD 42.30 a month) saves USD 0 against the median (USD 42.30). For the coding agent the gap is USD 0 a month.
Which DeepSeek-V3.1-Terminus provider is cheapest for your traffic?
GMI Cloud and SiliconFlow share the lowest input price (USD 0.27) and the lowest output price (USD 1), so they are the cheapest standard price at every mix of input and output tokens, before cache discounts.
| Provider | No cache hits | 50% cached | 90% cached |
|---|---|---|---|
| GMI Cloud (no cache price) | USD 0.4525 cheapest | USD 0.4525 cheapest | USD 0.4525 cheapest |
| SiliconFlow (no cache price) | USD 0.4525 cheapest | USD 0.4525 cheapest | USD 0.4525 cheapest |
| Featherless (no cache price) | USD 0.4637 | USD 0.4637 | USD 0.4637 |
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.
None of the 3 providers publishes a cached-input discount for DeepSeek-V3.1-Terminus, so cache hits do not change the ranking.
Context windows differ: 163,840 tokens at SiliconFlow; 131,072 tokens at GMI Cloud and Featherless. The cheapest row is not always the one that fits a long prompt.
What does DeepSeek-V3.1-Terminus 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-V3.1-Terminus:
| Content | Input per 1M characters | Cheapest provider |
|---|---|---|
| English | USD 0.058 | GMI Cloud |
| Arabic MSA | USD 0.102 | GMI Cloud |
| Hindi | USD 0.156 | GMI Cloud |
| Chinese | USD 0.158 | GMI Cloud |
| Code | USD 0.071 | GMI Cloud |
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-V3.1-Terminus preloaded: your traffic and cache rate, against any of 428 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-V3.1-Terminus compare with other DeepSeek models?
The DeepSeek models whose cheapest standard price is closest to DeepSeek-V3.1-Terminus's (USD 0.4525 blended):
| Model | Cheapest input | Cheapest output | Max context | Providers |
|---|---|---|---|---|
| DeepSeek V3 | USD 0.25 | USD 1 | 163,840 | 3 |
| DeepSeek V3.1 | USD 0.25 | USD 0.95 | 163,840 | 7 |
| DeepSeek V3 0324 | USD 0.29 | USD 1.14 | 131,072 | 3 |
| DeepSeek R1 Distill Llama 70B | USD 0.25 | USD 0.75 | 131,072 | 2 |
| DeepSeek R1 Distill Qwen 32B | USD 0.50 | USD 0.90 | 131,072 | 3 |
| DeepSeek-V4-Flash-Vision-Exp | USD 0.2156 | USD 0.6468 | 1,048,576 | 3 |
Priced closest from other makers: Inkling 2 Small (Thinking Machines, USD 0.4512) · GPT-5.6 Luna (OpenAI, USD 0.45) · GLM 4.6V (Z.ai, USD 0.45).
All 428 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-V3.1-Terminus API cost per token?
From USD 0.27 per 1M input tokens (USD 0.00000027 per token) and USD 1 per 1M output tokens (USD 0.000001 per token) at the lowest standard prices we found. The median of 3 standard prices is USD 0.27 input and USD 1 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-V3.1-Terminus?
Among the 3 providers we checked (prices read 2026-11-14 to 2026-11-15), 2 are tied for the lowest price: GMI Cloud and SiliconFlow, each USD 0.4525 per 1M on a blend of 3 input tokens to 1 output token. For input alone the lowest price is USD 0.27 (GMI Cloud and 1 other, tied); for output alone, USD 1 (GMI Cloud and 2 others, tied). Batch, flex, priority and fast tiers are shown in the table but not ranked.
Does DeepSeek sell DeepSeek-V3.1-Terminus on its own API?
DeepSeek publishes no price for DeepSeek-V3.1-Terminus on its own API that we could find, so there is no maker price to compare. The lowest-priced host we checked is GMI Cloud at USD 0.27 / USD 1 per 1M tokens.
Does DeepSeek-V3.1-Terminus have cached input pricing?
None of the 3 standard prices includes a cached-input price, so budget repeated prompts at the full input price.
What is the DeepSeek-V3.1-Terminus 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-V3.1-Terminus?
For 1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning, over 30 days: USD 576.00 a month at GMI Cloud, USD 576.00 at the median price and USD 603.00 at Featherless. Try your own numbers.
Is DeepSeek-V3.1-Terminus free to use through an API?
No provider in our data lists a free price for DeepSeek-V3.1-Terminus 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-V3.1-Terminus open source, with open weights, and what is its licence?
DeepSeek publishes the weights on Hugging Face as deepseek-ai/DeepSeek-V3.1-Terminus, 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-V3.1-Terminus 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-V3.1-Terminus. That is a file-level count, not the maker's figure, and it can include extra modules (checked 2026-11-16).