BroadRouter

DeepSeek V4.1 Flash 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 is DeepInfra (promotional) at USD 0.14 input and USD 0.42 output per 1M 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 for the version it serves.

DeepSeek · slug deepseek-v4.1-flash · up to 1,048,576 tokens of context · 16 providers with a standard price. Every price is read from the provider's own pricing page and linked in its row, checked 2026-11-15. No aggregator feed. Download all prices (every provider and model, with sources, CSV or JSON). How it compares with the market: the LLM API price index. Archived list prices since 2026-10-03 (2 archived price points, 0 list-price changes): LLM API price history.

What does DeepSeek charge for DeepSeek V4.1 Flash?

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. Serving version: DeepSeek's API serves DeepSeek V4.1 Flash 1017 under this name, so its price is shown here for reference and is not ranked against hosts of DeepSeek V4.1 Flash. Source, checked 2026-11-14.

Is a host cheaper than DeepSeek? Yes. DeepInfra charges USD 0.14 input and USD 0.42 output per 1M tokens, 60% below DeepSeek's own USD 0.30 / USD 1.20 at peak hours on the 3:1 blend (a promotional price). DeepSeek's row is for the version its API serves under this name (DeepSeek V4.1 Flash's 1017 snapshot), so it can differ slightly from what the hosts serve. Off-peak, DeepSeek charges USD 0.15 input, USD 0.003 cached and USD 0.60 output.

DeepSeek V4.1 Flash 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 2.5× the cheapest. Free rows, the maker's serving version and other service tiers follow, tagged and unranked.

DeepSeek V4.1 Flash API prices by provider
#ProviderInputCached inputOutputBlended 3:1ContextPrecisionSource
1DeepInfra cheapest promo
deepseek-ai/DeepSeek-V4.1-Flash
Notes and source quote

Promotional price, 30% off list (list 0.2 in / 0.6 out).

“$0.14 in $0.42 out $0.004 cached / 1M tokens”
USD 0.14USD 0.0042USD 0.42USD 0.211,048,576FP8DeepInfra page
checked 2026-11-14
re-checked 2026-11-16
2CoreWeave Forge
deepseek-ai/DeepSeek-V4.1-Flash
Notes and source quote
“DeepSeek V4.1-Flash $0.13 $0.65 $0.002”
USD 0.13USD 0.002USD 0.65USD 0.261,048,576not statedCoreWeave Forge page
checked 2026-11-15
re-checked 2026-11-16
3SiliconFlow
Notes and source quote

Context shown as 1049K.

“DeepSeek-V4.1-Flash 1049K $0.15 $0.003 $0.6”
USD 0.15USD 0.003USD 0.60USD 0.26251,048,576not statedSiliconFlow page
checked 2026-11-14
re-checked 2026-11-16
4GMI Cloud promo
deepseek-ai/DeepSeek-V4.1-Flash
Notes and source quote

Promotional 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 0.18USD 0.0036USD 0.72USD 0.3151,048,575FP8GMI Cloud page
checked 2026-11-15
re-checked 2026-11-16
5Alibaba Cloud
deepseek-v4.1-flash
Notes and source quote

International (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: "a fixed $0.003 per 1M tokens during off-peak hours and $0.006 per 1M tokens during peak hours".

“deepseek-v4.1-flash context caching discount International Busy hours: $0.3 Idle hours: $0.15 Busy hours: $1.2 Idle hours: $0.6”
USD 0.30USD 0.006USD 1.20USD 0.525not statednot statedAlibaba Cloud page
checked 2026-11-14
re-checked 2026-11-16
6Baseten
deepseek-ai/DeepSeek-V4.1-Flash
Notes and source quote

Context from the model library page (https://www.baseten.co/library/deepseek-v41-flash/), stated as 1M.

“DeepSeek V4.1 Flash $0.30 $0.007 $1.20”
USD 0.30USD 0.007USD 1.20USD 0.5251,000,000not statedBaseten page
checked 2026-11-14
re-checked 2026-11-16
7DigitalOcean
Notes and source quote

DigitalOcean-hosted.

“DeepSeek V4.1 Flash — Processing modePrompt lengthInputOutputCache read: Standard All prompts$0.30$1.20$0.006”
USD 0.30USD 0.006USD 1.20USD 0.525not statednot statedDigitalOcean page
checked 2026-11-14
re-checked 2026-11-16
8Featherless
deepseek-ai/DeepSeek-V4.1-Flash
Notes and source quote

Developer plan (per-token billing, from 50 USD a month in credits).

“PRICING: INPUT $0.3 / CACHED $0.03 / OUTPUT $1.2”
USD 0.30USD 0.03USD 1.20USD 0.525262,144FP8Featherless page
checked 2026-11-15
re-checked 2026-11-16
9Fireworks AI
accounts/fireworks/models/deepseek-v4p1-flash
Notes and source quote
“DeepSeek V4.1 Flash | $0.30 / $0.006 / $1.20 | $0.375 / $0.0075 / $1.50”
USD 0.30USD 0.006USD 1.20USD 0.5251,048,576not statedFireworks AI page
checked 2026-11-14
re-checked 2026-11-16
10Google Vertex AI
deepseek-v4.1-flash
Notes and source quote

Google says it was free until October 16, 2026; this is the price after that date.

“DeepSeek-V4.1-Flash * Input $0.30 … Output $1.20 … Cache Hit $0.03”
USD 0.30USD 0.03USD 1.20USD 0.525not statednot statedGoogle Vertex AI page
checked 2026-11-14
re-checked 2026-11-16
11Hyperbolic
deepseek-v4.1-flash
Notes and source quote

Context shown on page as "1M" (rounded); stored as the decimal value.

“DeepSeek V4.1 Flash deepseek-v4.1-flash DeepSeek · 1M context · Text $0.30 $1.20 $0.006”
USD 0.30USD 0.006USD 1.20USD 0.5251,000,000not statedHyperbolic page
checked 2026-11-14
re-checked 2026-11-16
12Microsoft Azure
Notes and source quote

Foundry Models serverless (pay-as-you-go), Global deployment. Also sold as "FW DeepSeek V4.1 Flash" (Fireworks on Azure, Global): input $0.375, cached $0.008, output $1.50.

“DeepSeek V4.1 Flash Global $0.30 $0.006 $1.20”
USD 0.30USD 0.006USD 1.20USD 0.525not statednot statedMicrosoft Azure page
checked 2026-11-14
re-checked 2026-11-16
13Novita AI
deepseek/deepseek-v4.1-flash
Notes and source quote
“DeepSeek V4.1 Flash 1M $0.3 /Mt · Cache Read $0.006 /Mt $1.2 /Mt”
USD 0.30USD 0.006USD 1.20USD 0.5251,048,576not statedNovita AI page
checked 2026-11-14
re-checked 2026-11-16
14Parasail
Notes and source quote
“DeepSeek V4.1 Flash $0.30 $1.20 $0.006”
USD 0.30USD 0.006USD 1.20USD 0.525not statednot statedParasail page
checked 2026-11-14
re-checked 2026-11-16
15Together AI
Notes and source quote

US geo-pinned option: $0.375 in / $1.50 out.

“DeepSeek V4.1 Flash $0.30 $0.006 (cached) $1.20”
USD 0.30USD 0.006USD 1.20USD 0.525not statednot statedTogether AI page
checked 2026-11-14
re-checked 2026-11-16
16Venice
deepseek-v4-1-flash
Notes and source quote
“| DeepSeek V4.1 Flash | `deepseek-v4-1-flash` | $0.30 | $1.20 | $0.0075 | — | Private |”
USD 0.30USD 0.0075USD 1.20USD 0.5251,000,000FP8Venice page
checked 2026-11-15
re-checked 2026-11-16
—DeepSeek maker, serving version peak price
deepseek-flash
Notes and source quote

Peak-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 0.30USD 0.006USD 1.20USD 0.5251,000,000not statedDeepSeek page
checked 2026-11-14
re-checked 2026-11-16
—DeepInfra flex / spot promo
deepseek-ai/DeepSeek-V4.1-Flash
Notes and source quote

Flex service tier (0.8× standard). Promotional price, 30% off list (list 0.2 in / 0.6 out).

“Flex (0.8×) $0.112 $0.336 $0.0034”
USD 0.112USD 0.0034USD 0.336USD 0.1681,048,576FP8DeepInfra page
checked 2026-11-14
re-checked 2026-11-16
—Fireworks AI flex / spot
accounts/fireworks/models/deepseek-v4p1-flash
Notes and source quote

Fireworks "Spot" mode: 30% off Standard on best-effort capacity; throughput can drop to zero.

“DeepSeek V4.1 Flash Spot $0.0042 $0.21 $0.84”
USD 0.21USD 0.0042USD 0.84USD 0.36751,048,576not statedFireworks AI page
checked 2026-11-14
re-checked 2026-11-16
—DeepInfra priority promo
deepseek-ai/DeepSeek-V4.1-Flash
Notes and source quote

Priority service tier (1.5× standard). Promotional price, 30% off list (list 0.2 in / 0.6 out).

“Priority (1.5×) $0.21 $0.63 $0.0063”
USD 0.21USD 0.0063USD 0.63USD 0.3151,048,576FP8DeepInfra page
checked 2026-11-14
re-checked 2026-11-16
—Fireworks AI priority
accounts/fireworks/models/deepseek-v4p1-flash
Notes and source quote

Priority mode.

“DeepSeek V4.1 Flash | Priority $0.375 / $0.0075 / $1.50”
USD 0.375USD 0.0075USD 1.50USD 0.65631,048,576not statedFireworks AI page
checked 2026-11-14
re-checked 2026-11-16
—Baseten fast
Notes and source quote

Context from the model library page (https://www.baseten.co/library/deepseek-v41-flash-fast/), stated as 1M.

“DeepSeek V4.1 Flash Fast $0.60 $0.014 $2.40”
USD 0.60USD 0.014USD 2.40USD 1.051,000,000not statedBaseten page
checked 2026-11-14
re-checked 2026-11-16
—BroadNet Inference this site's owner
broadnet/deepseek-v4.1-flash
Same model. Not ranked: BroadRouter is BroadNet's own site. Model page
USD 0.175USD 0.0055USD 0.52USD 0.26121,048,576not statedpricing.json
synced 2026-11-14

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

What does DeepSeek V4.1 Flash 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.
Monthly cost of three workloads on DeepSeek V4.1 Flash, by provider
ProviderSupport chatbotRAG over documentsCoding agent (one developer)
DeepInfra (promo)USD 12.83USD 30.12USD 82.03
CoreWeave ForgeUSD 16.49USD 31.73USD 96.66
SiliconFlowUSD 16.36USD 34.42USD 99.09
GMI Cloud (promo)USD 19.63USD 41.30USD 118.91
Alibaba CloudUSD 32.72USD 68.83USD 198.18
BasetenUSD 32.78USD 68.90USD 199.71
DigitalOceanUSD 32.72USD 68.83USD 198.18
FeatherlessUSD 34.02USD 70.56USD 234.90
Fireworks AIUSD 32.72USD 68.83USD 198.18
Google Vertex AIUSD 34.02USD 70.56USD 234.90
HyperbolicUSD 32.72USD 68.83USD 198.18
Microsoft AzureUSD 32.72USD 68.83USD 198.18
Novita AIUSD 32.72USD 68.83USD 198.18
ParasailUSD 32.72USD 68.83USD 198.18
Together AIUSD 32.72USD 68.83USD 198.18
VeniceUSD 32.81USD 68.94USD 200.47
DeepSeek (maker, serving version, peak)USD 32.72USD 68.83USD 198.18
BroadNet Inference (this site's owner)USD 15.96USD 37.60USD 102.46

For the support chatbot, the cheapest price (DeepInfra, USD 12.83 a month) saves USD 19.90 against the median (USD 32.72). For the coding agent the gap is USD 116.15 a month (59% lower).

Which DeepSeek V4.1 Flash provider is cheapest for your traffic?

CoreWeave Forge has the lowest input price (USD 0.13) and DeepInfra the lowest output price (USD 0.42). They cost the same at 23 input tokens per output token. With more input than that, as with long prompts or retrieval, CoreWeave Forge is cheaper; with less, as with long answers, DeepInfra is.

DeepSeek V4.1 Flash: price per 1M tokens at 3 input to 1 output, by share of input served from cache
ProviderNo cache hits50% cached90% cached
DeepInfraUSD 0.21 cheapestUSD 0.1591 cheapestUSD 0.1183 cheapest
CoreWeave ForgeUSD 0.26USD 0.212USD 0.1736
SiliconFlowUSD 0.2625USD 0.2074USD 0.1633
GMI CloudUSD 0.315USD 0.2488USD 0.1959
Alibaba CloudUSD 0.525USD 0.4147USD 0.3266
BasetenUSD 0.525USD 0.4151USD 0.3272

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), CoreWeave Forge (98% off), SiliconFlow (98% off), GMI Cloud (98% off), Alibaba Cloud (98% off) and 11 more.

Context windows differ: 1,048,576 tokens at DeepInfra, CoreWeave Forge, SiliconFlow and 2 more; 1,048,575 tokens at GMI Cloud; 1,000,000 tokens at Baseten, Hyperbolic and Venice; 262,144 tokens at Featherless. Alibaba Cloud, DigitalOcean, Google Vertex AI, Microsoft Azure, Parasail and Together AI do not state one. The cheapest row is not always the one that fits a long prompt.

DeepSeek V4.1 Flash on BroadNet Inference

BroadRouter is BroadNet's own site. BroadNet Inference serves this model as broadnet/deepseek-v4.1-flash at USD 0.175 input, USD 0.0055 cached input and USD 0.52 output per 1M tokens, with a 1,048,576-token context. On the 3:1 blend, 2 standard prices above are lower, so pick BroadNet for other reasons: zero data retention, one OpenAI-compatible key for every BroadNet model and an unlimited flat plan with no token meter.

DeepSeek V4.1 Flash on BroadNet: setup, limits and code · When a flat plan beats per-token pricing

What does DeepSeek V4.1 Flash 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:

ContentInput per 1M charactersCheapest provider
EnglishUSD 0.028CoreWeave Forge
Arabic MSAUSD 0.049CoreWeave Forge
HindiUSD 0.075CoreWeave Forge
ChineseUSD 0.076CoreWeave Forge
CodeUSD 0.034CoreWeave Forge

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.

Published benchmark results for DeepSeek V4.1 Flash, with sources
BenchmarkResultSetting or noteSource
GPQA Diamond (Pass@1)90.9Instruct model, maximum reasoning effort (reasoning_effort=100)DeepSeek model card, checked 2026-11-16
HLE (Pass@1)36.8 (39.1†)Instruct model, maximum reasoning effort (reasoning_effort=100); the figure in brackets is the text-only subsetDeepSeek model card, checked 2026-11-16
Terminal-Bench 2.1 (Pass@1)90.6Instruct model, maximum reasoning effort (reasoning_effort=100); DeepSeek Harness, Minimal modeDeepSeek model card, checked 2026-11-16
DeepSWE v1.1 (Resolved)74.2Instruct model, maximum reasoning effort (reasoning_effort=100); mini-SWE harnessDeepSeek model card, checked 2026-11-16
Codeforces (Rating)3471Instruct model, maximum reasoning effort (reasoning_effort=100)DeepSeek model card, checked 2026-11-16
GPQA Diamond0.898Max reasoning setting; Epoch run deepseek-v4.1-flash_max, mean score on a 0 to 1 scaleEpoch AI, checked 2026-11-16
SimpleQA Verified0.429Max reasoning setting; Epoch run deepseek-v4.1-flash_max, mean score on a 0 to 1 scaleEpoch AI, checked 2026-11-16
OTIS Mock AIME 2024-20250.983Max reasoning setting; Epoch run deepseek-v4.1-flash_max, mean score on a 0 to 1 scaleEpoch 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

The DeepSeek models whose cheapest standard price is closest to DeepSeek V4.1 Flash's (USD 0.21 blended):

DeepSeek models priced closest to DeepSeek V4.1 Flash
ModelCheapest inputCheapest outputMax contextProviders
DeepSeek R1 Distill Llama 8BUSD 0.14USD 0.39131,0722
DeepSeek R1 Distill Qwen 14BUSD 0.20USD 0.20131,0722
DeepSeek V3.2USD 0.2088USD 0.3096163,84011
DeepSeek V4.1 Flash 1017USD 0.098USD 0.2941,048,57616
DeepSeek-V3.2-ExpUSD 0.27USD 0.41163,8402
DeepSeek-V4-Flash-Vision-ExpUSD 0.2156USD 0.64681,048,5763

Priced closest from other makers: Claude Haiku 5.5 (Anthropic, USD 0.20) · GPT-6 Luna (OpenAI, USD 0.20) · Ministral 3 14B (Mistral AI, USD 0.20).

Compare DeepSeek V4.1 Flash with

Also compared: vs DeepSeek V4 Flash · vs Claude Haiku 5.5 · vs GPT-6 Luna · vs Qwen3.8 Flash · vs MiniMax M3.1 Flash · vs Qwen3.8 27B · vs GLM 5.3 Flash · vs Llama 4 Maverick 17B 128E Instruct FP8 · vs OpenAI GPT OSS 120B · vs GLM 5.3 · vs Gemini 3.8 Flash · vs Gemma 4 31B · vs Qwen3.6 35B A3B · vs Qwen3.5 35B A3B · vs MiniMax M3 · vs DeepSeek V4.1 Flash 1017 · vs Ministral 3 14B · vs Qwen3 VL 30B A3B Instruct.

Every DeepSeek V4.1 Flash 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 API cost per token?

From USD 0.13 per 1M input tokens (USD 0.00000013 per token) and USD 0.42 per 1M output tokens (USD 0.00000042 per token) at the lowest standard prices we found, which can come from different providers. 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?

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 0.21 per 1M). For input alone the lowest price is USD 0.13 (CoreWeave Forge); for output alone, USD 0.42 (DeepInfra). Batch, flex, priority and fast tiers are shown in the table but not ranked.

Is DeepSeek V4.1 Flash cheaper from a host than from DeepSeek?

Yes. DeepInfra charges USD 0.14 input and USD 0.42 output per 1M tokens, 60% below DeepSeek's own USD 0.30 / USD 1.20 at peak hours on the 3:1 blend (a promotional price). DeepSeek's row is for the version its API serves under this name (DeepSeek V4.1 Flash's 1017 snapshot), so it can differ slightly from what the hosts serve. Off-peak, DeepSeek charges USD 0.15 input, USD 0.003 cached and USD 0.60 output.

Does DeepSeek V4.1 Flash have cached input pricing?

All 16 standard prices include one. The lowest is USD 0.002 per 1M at CoreWeave Forge; 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 context window?

Up to 1,048,576 tokens. 5 standard prices come with less, down to 262,144 tokens (Featherless, Baseten, Hyperbolic, Venice 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 V4.1 Flash?

For 1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning, over 30 days: USD 82.03 a month at DeepInfra, USD 198.18 at the median price and USD 234.90 at Google Vertex AI. Try your own numbers.

Is there a batch, flex or priority price for DeepSeek V4.1 Flash?

Yes: flex / spot from DeepInfra at USD 0.112 / USD 0.336; priority from DeepInfra at USD 0.21 / USD 0.63; fast from Baseten at USD 0.60 / USD 2.40 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 free to use through an API?

No provider in our data lists a free price for DeepSeek V4.1 Flash as of 2026-11-15. BroadNet Inference serves it as broadnet/deepseek-v4.1-flash to paid accounts only: the USD 5 starting credit does not cover it (rate card synced 2026-11-14). 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.

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

Yes. 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 (rate card synced 2026-11-14), with zero data retention. On the 3:1 blend, 2 standard prices on this page are lower. BroadRouter is BroadNet's own site. DeepSeek V4.1 Flash on BroadNet.

How does DeepSeek V4.1 Flash score on benchmarks?

As published, the DeepSeek model card reports 90.9 on GPQA Diamond (Pass@1) and 90.6 on Terminal-Bench 2.1 (Pass@1); Epoch AI measured 0.898 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