BroadRouter

DeepSeek V4.1 Flash 1017 vs DeepSeek V4.1 Flash API pricing

Updated

DeepSeek V4.1 Flash 1017: USD 0.09 input, USD 0.30 output per 1M tokens (Sail Research). DeepSeek V4.1 Flash: USD 0.07 input, USD 0.50 output per 1M tokens (Relace). At 3 input tokens per output token, DeepSeek V4.1 Flash costs 25% more than DeepSeek V4.1 Flash 1017 (USD 0.1775 vs USD 0.1425 per 1M).

DeepSeek V4.1 Flash 1017 is a dated snapshot of DeepSeek V4.1 Flash (the same name plus a release date), so this page shows whether the snapshot is priced differently. Price only: every number is computed from prices read from each provider's own pricing page (linked per cell, newest check 2026-11-16), with no claim about quality, speed or accuracy. Third-party benchmark results both models share are quoted as published.

How do DeepSeek V4.1 Flash 1017 and DeepSeek V4.1 Flash differ on price?

DeepSeek V4.1 Flash 1017 and DeepSeek V4.1 Flash 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.

DeepSeek V4.1 Flash 1017 and DeepSeek V4.1 Flash API prices compared
PriceDeepSeek V4.1 Flash 1017DeepSeek V4.1 Flash
Model pageDeepSeek V4.1 Flash 1017
DeepSeek · 23 providers
DeepSeek V4.1 Flash
DeepSeek · 23 providers
Cheapest standard price, blended 3:1USD 0.1425 lower
USD 0.09 in / USD 0.30 out at Sail Research
Sail Research page checked 2026-11-16
USD 0.1775
USD 0.07 in / USD 0.50 out at Relace
Relace page checked 2026-11-16
Cheapest inputUSD 0.09
Sail Research source
USD 0.07 lower
Relace source
Cheapest cached inputUSD 0.0024
River source
USD 0.002 lower
CoreWeave Forge source
Cheapest outputUSD 0.294 lower promo
DeepInfra source
USD 0.42 promo
DeepInfra source
Maker's own APIUSD 0.30 / USD 1.20
DeepSeek source
USD 0.30 / USD 1.20
DeepSeek, serving version source
Median standard priceUSD 0.30 / USD 1.20
input / output, 23 prices
USD 0.30 / USD 1.20
input / output, 23 prices
Context window1,048,576 tokens, largest stated; from 262,144 at some providers1,048,576 tokens, largest stated; from 262,144 at some providers
Providers with a standard price2323

Report a wrong price or number (email to info@broadnet.ai, with this page's link filled in).

What do DeepSeek V4.1 Flash 1017 and DeepSeek V4.1 Flash 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).

Monthly cost of three workloads on DeepSeek V4.1 Flash 1017 and DeepSeek V4.1 Flash
WorkloadDeepSeek V4.1 Flash 1017DeepSeek V4.1 FlashDifference
Support chatbot
2,000 requests a day, 1,500 input tokens (60% cached), 300 output
USD 8.96
Sail Research
USD 11.95
Relace
USD 2.99
DeepSeek V4.1 Flash 1017 lower
RAG over documents
1,000 requests a day, 8,000 input tokens (30% cached), 500 output
USD 20.05
Sail Research
USD 19.84
Relace
USD 0.22
DeepSeek V4.1 Flash lower
Coding agent (one developer)
1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning
USD 57.42
DeepInfra
USD 76.14
Relace
USD 18.72
DeepSeek V4.1 Flash 1017 lower

The cheaper model depends on the workload: DeepSeek V4.1 Flash 1017 for Support chatbot, DeepSeek V4.1 Flash for RAG over documents, DeepSeek V4.1 Flash 1017 for Coding agent (one developer). Cache-heavy work rewards a low cached-input price. The widest gap is on Support chatbot: the dearer model costs 33% more than the cheaper one.

Does the cheaper model change with your input:output ratio?

The cheaper model changes with the mix: below 10 input tokens per output token, DeepSeek V4.1 Flash 1017 is cheaper; above 10, DeepSeek V4.1 Flash is cheaper. At the site's 3:1 blend, DeepSeek V4.1 Flash 1017 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.

Price per 1M tokens of DeepSeek V4.1 Flash 1017 and DeepSeek V4.1 Flash at different input:output mixes
Input : output tokensDeepSeek V4.1 Flash 1017DeepSeek V4.1 Flash
1 : 3 (long answers)USD 0.245 lower
DeepInfra
USD 0.35
DeepInfra
1 : 1USD 0.195 lower
Sail Research
USD 0.28
DeepInfra
3 : 1 (the site’s blend)USD 0.1425 lower
Sail Research
USD 0.1775
Relace
10 : 1 (retrieval, long prompts)USD 0.1091 tie
Sail Research
USD 0.1091 tie
Relace
30 : 1 (agents, big contexts)USD 0.09677
Sail Research
USD 0.08387 lower
Relace

USD per 1M tokens at the cheapest standard provider for each mix, before cache discounts. Thinking tokens bill as output.

What do DeepSeek V4.1 Flash 1017 and DeepSeek V4.1 Flash 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 V4.1 Flash 1017 (the same one for both, so the gap equals the price gap):

Input cost per 1M characters by language, DeepSeek V4.1 Flash 1017 and DeepSeek V4.1 Flash
ContentDeepSeek V4.1 Flash 1017DeepSeek V4.1 Flash
EnglishUSD 0.019
Sail Research
USD 0.015 lower
Relace
Arabic MSAUSD 0.034
Sail Research
USD 0.026 lower
Relace
Egyptian ArabicUSD 0.035
Sail Research
USD 0.027 lower
Relace
HindiUSD 0.052
Sail Research
USD 0.040 lower
Relace
ChineseUSD 0.053
Sail Research
USD 0.041 lower
Relace
SpanishUSD 0.023
Sail Research
USD 0.018 lower
Relace
CodeUSD 0.024
Sail Research
USD 0.018 lower
Relace

From the real cost by language dataset (measured tokens per character on FLORES-200 and other texts). Your own text will differ.

Published results on the same benchmark

BroadNet did not run these benchmarks. BroadRouter is BroadNet's site. Each row pairs results from one source with the same setting for both models, as published; results from different sources or settings are never put side by side. One benchmark says little about your own workload.

Published results for DeepSeek V4.1 Flash 1017 and DeepSeek V4.1 Flash on the same benchmark, with sources
BenchmarkDeepSeek V4.1 Flash 1017DeepSeek V4.1 FlashSource and setting
GPQA Diamond0.9320.898Epoch AI, checked 2026-11-16
Max reasoning setting, mean score on a 0 to 1 scale

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).

All published results for each model, with every setting: DeepSeek V4.1 Flash 1017 · DeepSeek V4.1 Flash.

DeepSeek V4.1 Flash on BroadNet Inference

BroadRouter is BroadNet's own site, so BroadNet's price is shown here for reference and is not part of the comparison above. BroadNet Inference serves DeepSeek V4.1 Flash as broadnet/deepseek-v4.1-flash at USD 0.175 input, USD 0.0055 cached and USD 0.52 output per 1M tokens (USD 0.2612 blended 3:1; the cheapest third-party standard price above is USD 0.1775). On BroadNet it reads up to 1,048,576 tokens per request and accepts text and image input (BroadNet rate card).

DeepSeek V4.1 Flash on BroadNet · BroadNet pricing.json

Check it on your own traffic

More comparisons: DeepSeek V4.1 Flash 1017 vs Gemma 4 26B A4B · DeepSeek V4.1 Flash vs DeepSeek V4 Flash · Qwen3.8 Flash vs DeepSeek V4.1 Flash · Claude Haiku 5.5 vs DeepSeek V4.1 Flash · GPT-6 Luna vs DeepSeek V4.1 Flash · DeepSeek V4.1 Flash vs MiniMax M3.1 Flash · GLM 5.3 Flash vs DeepSeek V4.1 Flash · DeepSeek V4.1 Flash vs Qwen3.8 27B · Llama 4 Maverick vs DeepSeek V4.1 Flash · gpt-oss-120b vs DeepSeek V4.1 Flash · DeepSeek V4.1 Flash vs GLM 5.3 · Gemini 3.8 Flash vs DeepSeek V4.1 Flash · DeepSeek V4.1 Flash vs Qwen3.6 35B A3B · DeepSeek V4.1 Flash vs Qwen3.5 35B A3B · DeepSeek V4.1 Flash vs MiniMax M3 · every DeepSeek V4.1 Flash 1017 comparison · every DeepSeek V4.1 Flash comparison · all 662 price comparisons

Questions

Is DeepSeek V4.1 Flash 1017 cheaper than DeepSeek V4.1 Flash?

Yes. On a blend of 3 input tokens to 1 output token, DeepSeek V4.1 Flash 1017 costs USD 0.1425 per 1M tokens and DeepSeek V4.1 Flash USD 0.1775, at each model's cheapest standard price. For input alone, DeepSeek V4.1 Flash is cheaper (USD 0.07 against USD 0.09 per 1M); for output alone, DeepSeek V4.1 Flash 1017 is (USD 0.294 against USD 0.42). This compares price only, not quality.

What do DeepSeek V4.1 Flash 1017 and DeepSeek V4.1 Flash cost per 1M tokens?

DeepSeek V4.1 Flash 1017: from USD 0.09 input and USD 0.30 output at Sail Research; DeepSeek's own API charges USD 0.30 / USD 1.20; median of 23 standard prices USD 0.30 / USD 1.20. DeepSeek V4.1 Flash: from USD 0.07 input and USD 0.50 output at Relace; DeepSeek's own API charges USD 0.30 / USD 1.20; median of 23 standard prices USD 0.30 / USD 1.20. Each price is read from the provider's own pricing page; the source is linked in the table.

Which providers sell both DeepSeek V4.1 Flash 1017 and DeepSeek V4.1 Flash?

15 providers have a standard price for both: DeepInfra (USD 0.147 and USD 0.21 at 3:1), River (USD 0.21 and USD 0.21 at 3:1), Doubleword (USD 0.2625 and USD 0.2625 at 3:1), Morph (USD 0.29 and USD 0.29 at 3:1), GMI Cloud (USD 0.315 and USD 0.315 at 3:1), Featherless (USD 0.3938 and USD 0.525 at 3:1), Inference.net (USD 0.475 and USD 0.475 at 3:1), Modal (USD 0.4375 and USD 0.525 at 3:1), Alibaba Cloud (USD 0.525 and USD 0.525 at 3:1), Baseten (USD 0.525 and USD 0.525 at 3:1), DigitalOcean (USD 0.525 and USD 0.525 at 3:1), Fireworks AI (USD 0.525 and USD 0.525 at 3:1), Novita AI (USD 0.525 and USD 0.525 at 3:1), Together AI (USD 0.525 and USD 0.525 at 3:1), Venice (USD 0.525 and USD 0.525 at 3:1). The first is the lowest combined price. Buying each model from its own cheapest provider costs USD 0.1425 and USD 0.1775.

Which is cheaper for a coding agent or a chatbot, DeepSeek V4.1 Flash 1017 or DeepSeek V4.1 Flash?

For a coding agent (1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning): USD 57.42 a month on DeepSeek V4.1 Flash 1017 (DeepInfra) against USD 76.14 on DeepSeek V4.1 Flash (Relace), a difference of USD 18.72. For a support chatbot (2,000 requests a day, 1,500 input tokens (60% cached), 300 output): USD 8.96 a month on DeepSeek V4.1 Flash 1017 (Sail Research) against USD 11.95 on DeepSeek V4.1 Flash (Relace), a difference of USD 2.99. 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 V4.1 Flash 1017 and DeepSeek V4.1 Flash change?

The cheaper model changes with the mix: below 10 input tokens per output token, DeepSeek V4.1 Flash 1017 is cheaper; above 10, DeepSeek V4.1 Flash is cheaper. At the site's 3:1 blend, DeepSeek V4.1 Flash 1017 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 V4.1 Flash 1017 and DeepSeek V4.1 Flash have cached input pricing?

DeepSeek V4.1 Flash 1017 from USD 0.0024 per 1M cached input tokens (River; 23 of 23 standard prices list a discount). DeepSeek V4.1 Flash from USD 0.002 per 1M cached input tokens (CoreWeave Forge; 23 of 23 standard prices list a discount). Cached tokens are billed at the input price where no cache price is published.

Which has the larger context window, DeepSeek V4.1 Flash 1017 or DeepSeek V4.1 Flash?

Both go up to 1,048,576 tokens on the providers that state it.

Can I use DeepSeek V4.1 Flash on BroadNet Inference?

BroadNet Inference serves DeepSeek V4.1 Flash as broadnet/deepseek-v4.1-flash at USD 0.175 input and USD 0.52 output per 1M tokens (rate card synced 2026-11-14). BroadRouter is BroadNet's own site, so BroadNet's price is shown for reference and not ranked against the providers above.

Which scores higher on GPQA Diamond, DeepSeek V4.1 Flash 1017 or DeepSeek V4.1 Flash?

Per Epoch AI (checked 2026-11-16), DeepSeek V4.1 Flash 1017 scores 0.932 and DeepSeek V4.1 Flash scores 0.898 on GPQA Diamond (Max reasoning setting, mean score on a 0 to 1 scale). BroadNet did not run these benchmarks, and one benchmark says little about your own workload. Every result both models share, with sources.

Read as MarkdownAsk ChatGPTAsk ClaudeAsk Perplexity