DeepSeek V4.1 Flash 1017 API pricing
Updated
Among the 16 providers we checked (prices read 2026-11-14 to 2026-11-15), the lowest blended standard price for DeepSeek V4.1 Flash 1017 is DeepInfra (promotional) at USD 0.098 per 1M input tokens and USD 0.294 per 1M output tokens. The median across 16 standard prices is USD 0.30 / USD 1.20. DeepSeek's own API charges USD 0.30 / USD 1.20 at peak hours.
What does DeepSeek charge for DeepSeek V4.1 Flash 1017?
- Input
- USD 0.30
- Cached input
- USD 0.006
- Output
- USD 1.20
- Blended 3:1
- USD 0.525
USD per 1M tokens on DeepSeek, model deepseek-flash, standard tier, peak hours; off-peak USD 0.15 input, USD 0.003 cached and USD 0.60 output. Source, checked 2026-11-14.
Is a host cheaper than DeepSeek? Yes. DeepInfra charges USD 0.098 input and USD 0.294 output per 1M tokens, 72% below DeepSeek's own USD 0.30 / USD 1.20 at peak hours on the 3:1 blend (a promotional price). Off-peak, DeepSeek charges USD 0.15 input, USD 0.003 cached and USD 0.60 output.
DeepSeek V4.1 Flash 1017 model facts
Facts from DeepSeek's model card for deepseek-ai/DeepSeek-V4.1-Flash-1017 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-V4.1-Flash-1017) with no access gate. | Hugging Face model API, checked 2026-11-16Quote“"private": false, "gated": false, 48 .safetensors files listed” |
| Licence | MIT License | DeepSeek model card, checked 2026-11-16Quote“This repository and the model weights are licensed under the MIT License.” |
| Parameters in the weight files (Hugging Face count, not the maker's figure) | About 763.2 billion (763,205,315,794) | Hugging Face model API, checked 2026-11-16Quote“"safetensors": { "total": 763205315794 }” |
| Context length | 1M tokens (recommended context_window) | DeepSeek model card, checked 2026-11-16Quote“context_window | 1M tokens” |
| Input and output | Image and text in, text out (the card's task tag is image-text-to-text) | DeepSeek model card metadata, checked 2026-11-16Quote“pipeline_tag: image-text-to-text” |
| Tool calling | Yes, per the prompt-encoding reference | DeepSeek model card, checked 2026-11-16Quote“test cases for multi-turn conversations, tool calling, thinking mode” |
| First published on Hugging Face (not necessarily the release date) | 2026-10-17 | Hugging Face model API, checked 2026-11-16Quote“"createdAt": "2026-10-17T02:40:38.000Z"” |
DeepSeek V4.1 Flash 1017 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 3.6× 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 | DeepInfra cheapest promodeepseek-ai/DeepSeek-V4.1-Flash-1017Notes and source quotePromotional price, 51% off list (list 0.2 in / 0.6 out). “$0.098 in $0.294 out $0.003 cached / 1M tokens” | USD 0.098 | USD 0.00294 | USD 0.294 | USD 0.147 | 1,048,576 | FP8 | DeepInfra page checked 2026-11-14 re-checked 2026-11-16 |
| 2 | GMI Cloud promodeepseek-ai/deepseek-v4.1-flash-1017Notes and source quotePromotional price, 40% off list (list 0.3 in / 1.2 out / 0.006 cached). “Price (per 1M tokens) 40% off Input $0.18 $0.30 Output $0.72 $1.20 Cache Read $0.0036 $0.006 Cache Write -” | USD 0.18 | USD 0.0036 | USD 0.72 | USD 0.315 | 1,048,575 | FP8 | GMI Cloud page checked 2026-11-15 re-checked 2026-11-16 |
| 3 | Featherlessdeepseek-ai/DeepSeek-V4.1-Flash-1017Notes and source quoteDeveloper plan (per-token billing, from 50 USD a month in credits). “PRICING: INPUT $0.225 / CACHED $0.006 / OUTPUT $0.9” | USD 0.225 | USD 0.006 | USD 0.90 | USD 0.3938 | 262,144 | FP8 | Featherless page checked 2026-11-15 re-checked 2026-11-16 |
| 4 | Baidudeepseek-v4.1-flash-1017Notes and source quote“DeepSeek-V4.1-Flash DeepSeek-V4.1-Flash-1017 Inference Service Input 0.28 $/M tokens Cache Hit 0.006 $/M tokens Output 1.13 $/M tokens” | USD 0.28 | USD 0.006 | USD 1.13 | USD 0.4925 | 1,048,576 | not stated | Baidu page checked 2026-11-15 re-checked 2026-11-16 |
| 5 | Crusoe Clouddeepseek-ai/DeepSeek-V4.1-FlashNotes and source quoteCrusoe's docs link this model ID to the DeepSeek-V4.1-Flash-1017 weights. “DeepSeek V4.1 Flash text, image $0.29 $1.20 $0.007” | USD 0.29 | USD 0.007 | USD 1.20 | USD 0.5175 | 1,048,576 | not stated | Crusoe Cloud page checked 2026-11-15 re-checked 2026-11-16 |
| 6 | DeepSeek maker peak pricedeepseek-flashNotes and source quotePeak-hour price (first price column of the quoted table). Off-peak is half: 0.15 input, 0.003 cached, 0.6 output. Peak hours are 01:00 - 04:00 and 06:00 - 10:00 UTC, Monday through Friday, excluding Chinese public holidays. All other hours are off-peak. API model name deepseek-flash serves DeepSeek-V4.1-Flash-1017; the legacy names deepseek-v4-flash and deepseek-v4-flash-vision-exp are retired and served by this model at the Flash price. Context 1M, max output 384K. “(CACHE HIT) OFF-PEAK $0.003 $0.022 PEAK $0.006 $0.044 1M INPUT TOKENS (CACHE MISS) OFF-PEAK $0.15 $0.66 PEAK $0.3 $1.32 1M OUTPUT TOKENS OFF-PEAK $0.6 $1.98 PEAK $1.2 $3.96” | USD 0.30 | USD 0.006 | USD 1.20 | USD 0.525 | 1,000,000 | not stated | DeepSeek page checked 2026-11-14 re-checked 2026-11-16 |
| 7 | Alibaba Clouddeepseek-v4.1-flash-1017Notes and source quoteInternational (Singapore) deployment. Peak (busy-hour) price; busy hours are 08:00–22:00 UTC+8 (00:00–14:00 UTC), idle hours bill 0.15 input, 0.6 output. Cached price from the Context Cache page: 0.006 peak, 0.003 off-peak. “deepseek-v4.1-flash-1017 context caching discount International Busy hours: $0.3 Idle hours: $0.15 Busy hours: $1.2 Idle hours: $0.6” | USD 0.30 | USD 0.006 | USD 1.20 | USD 0.525 | not stated | not stated | Alibaba Cloud page checked 2026-11-14 re-checked 2026-11-16 |
| 8 | BasetenNotes and source quoteContext from the model library page (https://www.baseten.co/library/deepseek-v41-flash-1017/), stated as 1M. “DeepSeek V4.1 Flash 1017 $0.30 $0.007 $1.20” | USD 0.30 | USD 0.007 | USD 1.20 | USD 0.525 | 1,000,000 | not stated | Baseten page checked 2026-11-14 re-checked 2026-11-16 |
| 9 | Chutesdeepseek-ai/DeepSeek-V4.1-Flash-1017Notes and source quote“DeepSeek-V4.1-Flash-1017 deepseek-ai/DeepSeek-V4.1-Flash-1017 $0.03 per 1M tokens $0.30 per 1M tokens $1.20 per 1M tokens 1.0M” | USD 0.30 | USD 0.03 | USD 1.20 | USD 0.525 | 1,000,000 | not stated | Chutes page checked 2026-11-15 re-checked 2026-11-16 |
| 10 | Cloudflare Workers AI@cf/deepseek-ai/deepseek-v4.1-flash-1017Notes and source quoteCloudflare publishes this USD per-token price alongside the neuron price. “@cf/deepseek-ai/deepseek-v4.1-flash-1017 $0.300 per M input tokens $0.006 per M cached input tokens $1.200 per M output tokens” | USD 0.30 | USD 0.006 | USD 1.20 | USD 0.525 | not stated | not stated | Cloudflare Workers AI page checked 2026-11-14 re-checked 2026-11-16 |
| 11 | DigitalOceanNotes and source quoteDigitalOcean-hosted. “DeepSeek V4.1 Flash 1017 — Processing modePrompt lengthInputOutputCache read: Standard All prompts$0.30$1.20$0.006” | USD 0.30 | USD 0.006 | USD 1.20 | USD 0.525 | not stated | not stated | DigitalOcean page checked 2026-11-14 re-checked 2026-11-16 |
| 12 | Fireworks AIaccounts/fireworks/models/deepseek-v4p1-flash-1017Notes and source quote“DeepSeek V4.1 Flash 1017 | $0.30 / $0.006 / $1.20 | $0.375 / $0.0075 / $1.50” | USD 0.30 | USD 0.006 | USD 1.20 | USD 0.525 | 1,048,576 | not stated | Fireworks AI page checked 2026-11-14 re-checked 2026-11-16 |
| 13 | Mistral AIdeepseek-v4-1-flash-1017Notes and source quoteThird-party open-weight model hosted by Mistral (Mistral labels it "served without Mistral modifications"). Mistral lists it as Public Preview. Context from the docs model card. “DeepSeek V4.1 Flash 1017 ↗ $0.3 $0.007 $1.2” | USD 0.30 | USD 0.007 | USD 1.20 | USD 0.525 | 1,048,576 | not stated | Mistral AI page checked 2026-11-14 re-checked 2026-11-16 |
| 14 | Novita AIdeepseek/deepseek-v4.1-flash-1017Notes and source quote“DeepSeek V4.1 Flash 1017 1M $0.3 /Mt · Cache Read $0.006 /Mt $1.2 /Mt” | USD 0.30 | USD 0.006 | USD 1.20 | USD 0.525 | 1,048,576 | not stated | Novita AI page checked 2026-11-14 re-checked 2026-11-16 |
| 15 | Together AINotes and source quoteUS geo-pinned option: $0.375 in / $1.50 out. “DeepSeek V4.1 Flash 1017 $0.30 $0.006 (cached) $1.20” | USD 0.30 | USD 0.006 | USD 1.20 | USD 0.525 | not stated | not stated | Together AI page checked 2026-11-14 re-checked 2026-11-16 |
| 16 | Venicedeepseek-v4-1-flash-1017Notes and source quote“| DeepSeek v4.1 Flash (1017) | `deepseek-v4-1-flash-1017` | $0.30 | $1.20 | $0.0075 | — | Private |” | USD 0.30 | USD 0.0075 | USD 1.20 | USD 0.525 | 1,000,000 | FP8 | Venice page checked 2026-11-15 re-checked 2026-11-16 |
| — | Mistral AI batchdeepseek-v4-1-flash-1017Notes and source quoteThird-party open-weight model hosted by Mistral (Mistral labels it "served without Mistral modifications"). Mistral lists it as Public Preview. Context from the docs model card. “DeepSeek V4.1 Flash 1017 ↗ $0.15 $0.0035 $0.6 (Batch tab, "Batch (-50%)")” | USD 0.15 | USD 0.0035 | USD 0.60 | USD 0.2625 | 1,048,576 | not stated | Mistral AI page checked 2026-11-14 re-checked 2026-11-16 |
| — | DeepInfra flex / spot promodeepseek-ai/DeepSeek-V4.1-Flash-1017Notes and source quoteFlex service tier (0.8× standard). Promotional price, 51% off list (list 0.2 in / 0.6 out). “Flex (0.8×) $0.0784 $0.2352 $0.0024” | USD 0.0784 | USD 0.0024 | USD 0.2352 | USD 0.1176 | 1,048,576 | FP8 | DeepInfra page checked 2026-11-14 re-checked 2026-11-16 |
| — | Fireworks AI flex / spotaccounts/fireworks/models/deepseek-v4p1-flash-1017Notes and source quoteFireworks "Spot" mode: 30% off Standard on best-effort capacity; throughput can drop to zero. “DeepSeek V4.1 Flash 1017 Spot $0.0042 $0.21 $0.84” | USD 0.21 | USD 0.0042 | USD 0.84 | USD 0.3675 | 1,048,576 | not stated | Fireworks AI page checked 2026-11-14 re-checked 2026-11-16 |
| — | DeepInfra priority promodeepseek-ai/DeepSeek-V4.1-Flash-1017Notes and source quotePriority service tier (1.5× standard). Promotional price, 51% off list (list 0.2 in / 0.6 out). “Priority (1.5×) $0.147 $0.441 $0.0044” | USD 0.147 | USD 0.0044 | USD 0.441 | USD 0.2205 | 1,048,576 | FP8 | DeepInfra page checked 2026-11-14 re-checked 2026-11-16 |
| — | Fireworks AI priorityaccounts/fireworks/models/deepseek-v4p1-flash-1017Notes and source quotePriority mode. “DeepSeek V4.1 Flash 1017 | Priority $0.375 / $0.0075 / $1.50” | USD 0.375 | USD 0.0075 | USD 1.50 | USD 0.6563 | 1,048,576 | not stated | Fireworks AI page checked 2026-11-14 re-checked 2026-11-16 |
| — | Mistral AI prioritydeepseek-v4-1-flash-1017Notes and source quoteThird-party open-weight model hosted by Mistral (Mistral labels it "served without Mistral modifications"). Mistral lists it as Public Preview. Context from the docs model card. “DeepSeek V4.1 Flash 1017 ↗ $0.525 $0.01225 $2.1 (Priority tab, "Priority (+75%)")” | USD 0.525 | USD 0.01225 | USD 2.10 | USD 0.9188 | 1,048,576 | not stated | Mistral AI page checked 2026-11-15 not auto-checked (page loads prices with JavaScript) |
| — | Baseten fastNotes and source quoteContext from the model library page (https://www.baseten.co/library/deepseek-v41-flash-1017-fast/), stated as 1M. “DeepSeek V4.1 Flash 1017 Fast $0.60 $0.014 $2.40” | USD 0.60 | USD 0.014 | USD 2.40 | USD 1.05 | 1,000,000 | not stated | Baseten page checked 2026-11-14 re-checked 2026-11-16 |
| — | Fireworks AI fastaccounts/fireworks/models/deepseek-v4p1-flash-1017Notes and source quoteUltra-fast (Preview) mode. “DeepSeek V4.1 Flash 1017 Ultra-fast (Preview) | $2.40 / $0.048 / $9.60 | —” | USD 2.40 | USD 0.048 | USD 9.60 | USD 4.20 | 1,048,576 | not stated | Fireworks AI page checked 2026-11-14 re-checked 2026-11-16 |
| — | Venice ultrafastdeepseek-v4-1-flash-1017-ultrafastNotes and source quoteUltrafast variant, model ID deepseek-v4-1-flash-1017-ultrafast. “| DeepSeek V4.1 Flash 1017 Ultrafast | `deepseek-v4-1-flash-1017-ultrafast` | $3.00 | $12.00 | $0.06 | — | Private |” | USD 3 | USD 0.06 | USD 12 | USD 5.25 | 1,000,000 | FP8 | Venice 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.
- Promo: the provider's page describes these prices as promotional or discounted (DeepInfra and GMI Cloud). They rank as published, but can end without notice; the row's notes give the list price or end date where the page states one.
- Other tiers (batch, flex / spot, priority, fast and ultrafast): 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.
- Peak price: DeepSeek bills peak and off-peak rates; the row carries the peak price and the off-peak rate is in its notes.
- 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. "Not auto-checked" rows are on pages that load prices with JavaScript; their checked date is a read with a page renderer. 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 V4.1 Flash 1017 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) |
|---|---|---|---|
| DeepInfra (promo) | USD 8.98 | USD 21.09 | USD 57.42 |
| GMI Cloud (promo) | USD 19.63 | USD 41.30 | USD 118.91 |
| Featherless | USD 24.62 | USD 51.73 | USD 150.93 |
| Baidu | USD 30.74 | USD 64.42 | USD 186.48 |
| Crusoe Cloud | USD 32.42 | USD 67.22 | USD 197.01 |
| DeepSeek (maker) | USD 32.72 | USD 68.83 | USD 198.18 |
| Alibaba Cloud | USD 32.72 | USD 68.83 | USD 198.18 |
| Baseten | USD 32.78 | USD 68.90 | USD 199.71 |
| Chutes | USD 34.02 | USD 70.56 | USD 234.90 |
| Cloudflare Workers AI | USD 32.72 | USD 68.83 | USD 198.18 |
| DigitalOcean | USD 32.72 | USD 68.83 | USD 198.18 |
| Fireworks AI | USD 32.72 | USD 68.83 | USD 198.18 |
| Mistral AI | USD 32.78 | USD 68.90 | USD 199.71 |
| Novita AI | USD 32.72 | USD 68.83 | USD 198.18 |
| Together AI | USD 32.72 | USD 68.83 | USD 198.18 |
| Venice | USD 32.81 | USD 68.94 | USD 200.47 |
For the support chatbot, the cheapest price (DeepInfra, USD 8.98 a month) saves USD 23.75 against the median (USD 32.72). For the coding agent the gap is USD 140.76 a month (71% lower).
Which DeepSeek V4.1 Flash 1017 provider is cheapest for your traffic?
DeepInfra has the lowest input price (USD 0.098) and the lowest output price (USD 0.294), 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 |
|---|---|---|---|
| DeepInfra | USD 0.147 cheapest | USD 0.1114 cheapest | USD 0.08283 cheapest |
| GMI Cloud | USD 0.315 | USD 0.2488 | USD 0.1959 |
| Featherless | USD 0.3938 | USD 0.3116 | USD 0.2459 |
| Baidu | USD 0.4925 | USD 0.3897 | USD 0.3075 |
| Crusoe Cloud | USD 0.5175 | USD 0.4114 | USD 0.3265 |
| DeepSeek (maker) | USD 0.525 | USD 0.4147 | USD 0.3266 |
USD per 1M tokens, 3 input tokens to 1 output token, each provider's cheapest standard row; 10 dearer providers are in the price table above. 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.
All 16 providers publish a cached-input price below the input price: DeepInfra (97% off), GMI Cloud (98% off), Featherless (97% off), Baidu (98% off), Crusoe Cloud (98% off) and 11 more.
Context windows differ: 1,048,576 tokens at DeepInfra, Baidu, Crusoe Cloud and 3 more; 1,048,575 tokens at GMI Cloud; 1,000,000 tokens at DeepSeek, Baseten, Chutes and Venice; 262,144 tokens at Featherless. Alibaba Cloud, Cloudflare Workers AI, DigitalOcean and Together AI do not state one. The cheapest row is not always the one that fits a long prompt.
What does DeepSeek V4.1 Flash 1017 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 V4.1 Flash 1017:
| Content | Input per 1M characters | Cheapest provider |
|---|---|---|
| English | USD 0.048 | Featherless |
| Arabic MSA | USD 0.085 | Featherless |
| Hindi | USD 0.130 | Featherless |
| Chinese | USD 0.132 | Featherless |
| Code | USD 0.059 | 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.
Published benchmark results
BroadNet did not run these benchmarks; results are as published by the DeepSeek model card and Epoch AI and may use different settings. BroadRouter is BroadNet's site.
| Benchmark | Result | Setting or note | Source |
|---|---|---|---|
| HLE w/o tools | 42.6 (44.0†) | The figure in brackets is the text-only subset | DeepSeek model card, checked 2026-11-16 |
| DeepSWE v1.1 | 77.0 | not stated | DeepSeek model card, checked 2026-11-16 |
| Terminal-Bench 4.0 | 42.3 | not stated | DeepSeek model card, checked 2026-11-16 |
| NL2Repo-Bench | 68.2 | not stated | DeepSeek model card, checked 2026-11-16 |
| GPQA Diamond | 0.932 | Max reasoning setting; Epoch run deepseek-v4.1-flash-1017_max, mean score on a 0 to 1 scale | Epoch AI, checked 2026-11-16 |
Epoch AI rows: Epoch AI, Capabilities & benchmarking, licensed CC BY 4.0, shown as the mean score on a 0 to 1 scale, rounded to three decimals (hover a value for the exact figure in Epoch's data file).
Estimate your own bill
- LLM API cost calculator with DeepSeek V4.1 Flash 1017 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 V4.1 Flash 1017 compare with other DeepSeek models?
The DeepSeek models whose cheapest standard price is closest to DeepSeek V4.1 Flash 1017's (USD 0.147 blended):
| Model | Cheapest input | Cheapest output | Max context | Providers |
|---|---|---|---|---|
| DeepSeek R1 Distill Qwen 7B | USD 0.10 | USD 0.20 | 131,072 | 2 |
| DeepSeek V4 Flash | USD 0.09 | USD 0.18 | 1,048,576 | 8 |
| DeepSeek R1 Distill Qwen 14B | USD 0.20 | USD 0.20 | 131,072 | 2 |
| DeepSeek R1 Distill Llama 8B | USD 0.14 | USD 0.39 | 131,072 | 2 |
| DeepSeek V4.1 Flash | USD 0.14 | USD 0.42 | 1,048,576 | 16 |
| DeepSeek V3.2 | USD 0.2088 | USD 0.3096 | 163,840 | 11 |
Priced closest from other makers: GLM 4.7 Flash (Z.ai, USD 0.145) · Ministral 3 8B (Mistral AI, USD 0.15) · Llama 4 Scout 17B 16E Instruct (Meta, USD 0.15).
Compare DeepSeek V4.1 Flash 1017 with
- DeepSeek V4.1 Flash 1017 vs DeepSeek V4.1 Flash: API price side by side
- DeepSeek V4.1 Flash 1017 vs Gemma 4 26B A4B: API price side by side
Also compared: vs DeepSeek V4.1 Flash · vs Gemma 4 26B A4B.
Every DeepSeek V4.1 Flash 1017 price comparison · All model-vs-model price comparisons
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 V4.1 Flash 1017 API cost per token?
From USD 0.098 per 1M input tokens (USD 0.000000098 per token) and USD 0.294 per 1M output tokens (USD 0.000000294 per token) at the lowest standard prices we found. The median of 16 standard prices is USD 0.30 input and USD 1.20 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 V4.1 Flash 1017?
Among the 16 providers we checked (prices read 2026-11-14 to 2026-11-15), the lowest is DeepInfra (promotional price), ranked on a blend of 3 input tokens to 1 output token (USD 0.147 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.
Is DeepSeek V4.1 Flash 1017 cheaper from a host than from DeepSeek?
Yes. DeepInfra charges USD 0.098 input and USD 0.294 output per 1M tokens, 72% below DeepSeek's own USD 0.30 / USD 1.20 at peak hours on the 3:1 blend (a promotional price). Off-peak, DeepSeek charges USD 0.15 input, USD 0.003 cached and USD 0.60 output.
Does DeepSeek V4.1 Flash 1017 have cached input pricing?
All 16 standard prices include one. The lowest is USD 0.00294 per 1M at DeepInfra; the median is USD 0.006. Providers without one bill cached input at the input price. What cached input means.
What is the DeepSeek V4.1 Flash 1017 context window?
Up to 1,048,576 tokens. 6 standard prices come with less, down to 262,144 tokens (Featherless, Baseten, Chutes, DeepSeek and 2 more). 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 V4.1 Flash 1017?
For 1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning, over 30 days: USD 57.42 a month at DeepInfra, USD 198.18 at the median price and USD 234.90 at Chutes. Try your own numbers.
Is there a batch, flex or priority price for DeepSeek V4.1 Flash 1017?
Yes: batch from Mistral AI at USD 0.15 / USD 0.60; flex / spot from DeepInfra at USD 0.0784 / USD 0.2352; priority from DeepInfra at USD 0.147 / USD 0.441; fast from Baseten at USD 0.60 / USD 2.40; ultrafast from Venice at USD 3 / USD 12 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 V4.1 Flash 1017 free to use through an API?
No provider in our data lists a free price for DeepSeek V4.1 Flash 1017 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 V4.1 Flash 1017 open source, with open weights, and what is its licence?
DeepSeek publishes the weights on Hugging Face as deepseek-ai/DeepSeek-V4.1-Flash-1017, in a public repository with no access gate. The licence, as the DeepSeek model card states it: MIT License. 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 V4.1 Flash 1017 have?
DeepSeek's model card does not state a total that we found. Hugging Face counts about 763.2 billion (763,205,315,794) parameters in the published weight files of deepseek-ai/DeepSeek-V4.1-Flash-1017. That is a file-level count, not the maker's figure, and it can include extra modules (checked 2026-11-16).
Does DeepSeek V4.1 Flash 1017 support tool calling?
Yes, per the prompt-encoding reference, according to the DeepSeek model card: “test cases for multi-turn conversations, tool calling, thinking mode” (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 V4.1 Flash 1017 with the OpenAI SDK?
BroadNet does not serve DeepSeek V4.1 Flash 1017. 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: Alibaba Cloud Model Studio (https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1, model deepseek-v4.1-flash-1017), DeepInfra (https://api.deepinfra.com/v1/openai, model deepseek-ai/DeepSeek-V4.1-Flash-1017), DeepSeek (https://api.deepseek.com, model deepseek-flash) and Fireworks AI (https://api.fireworks.ai/inference/v1, model accounts/fireworks/models/deepseek-v4p1-flash-1017), and 1 more on their provider pages. Each provider page quotes the provider's docs with a check date.
How does DeepSeek V4.1 Flash 1017 score on benchmarks?
As published, the DeepSeek model card reports 77.0 on DeepSWE v1.1 and 42.3 on Terminal-Bench 4.0; Epoch AI measured 0.932 on GPQA Diamond in its own run, as a mean score on a 0 to 1 scale (checked 2026-11-16). BroadNet did not run these benchmarks, and sources may use different settings, so the figures are not directly comparable. Every published result we found, with its setting and source.
Read as MarkdownAsk ChatGPTAsk ClaudeAsk Perplexity
Sources
- Alibaba Cloud: pricing (checked 2026-11-14)
- Baidu: pricing (checked 2026-11-15)
- Baseten: pricing (checked 2026-11-14)
- Chutes: pricing (checked 2026-11-15)
- Cloudflare Workers AI: pricing (checked 2026-11-14)
- Crusoe Cloud: pricing (checked 2026-11-15)
- DeepInfra: pricing (checked 2026-11-14)
- DeepSeek: own API pricing (checked 2026-11-14)
- DigitalOcean: pricing (checked 2026-11-14)
- Featherless: pricing (checked 2026-11-15)
- Fireworks AI: pricing (checked 2026-11-14)
- Fireworks AI: pricing (checked 2026-11-14)
- GMI Cloud: pricing (checked 2026-11-15)
- Mistral AI: pricing (checked 2026-11-15)
- Novita AI: pricing (checked 2026-11-14)
- Together AI: pricing (checked 2026-11-14)
- Venice: pricing (checked 2026-11-15)