Up to date
deepseek-ai MIT out 6 months ago
1.60T parameters (6 of 384 experts per token), text in, text out, 1M tokens of context. 16 providers serve it from $0.21 per million input tokens.
Verified 2026-10-25 Rank #17 in LLMs · score 119.8 method v1 Sources 5 Downloads 30d 361.1k · #195 of 619 tracked
Changed this week: Cheapest input price fell 52.3%: $0.436 → $0.208 per 1M (OpenRouter).2026-10-24 · Cheapest input price rose 82.1%: $0.436 → $0.794 per 1M (OpenRouter).2026-10-24 · 3 new quantized builds on the Hub (30 in all).2026-10-24
No drawable SVG in the reply.
Why did the open-weights model cross the road?
Because it had no guardrails.
.-.
/ \
/ \
'-------'
| |
| |
\ /
\O/
~~~~~~~
~~~~~~~~~
~~~~~~~~~~~
~~~~~~~~~~~~~The ringer: the same four playful tests for every model, replies shown as received and checked by code. A joke, not a benchmark; never ranked.2 of 3 pass · parasail-deepseek-v4-pro on parasail · run 2026-10-09 · temperature 0 · cost $0.070 · 2026-10 thing: supermarket · all models →
Picked by rule from 52 tracked pieces: the lab's own post, the most shared, a field report, the latest.
DeepSeek V4 Pro 0813 is a large-scale mixture-of-experts model released on Aug 12, 2026 with a context window of 1.0M.
The 5 picks above, plus these 20. Top is the radar's score: discussion, source authority and the lab's own posts, fading with age.
Live hosted endpoints, cheapest first, USD per million tokens. Ties break on output price, then provider name.
13 providers with a live price, from $0.21 to $1.91 per million input tokens; the median is $1.15. One dot per provider, cheapest in teal.
Hugging Face does not say who downloads a model or with what. These are the proxies: API providers listing it, quantized builds, fine-tunes/adapters/merges, and Spaces that load it.
Widely served (16 API providers); 30 quantized builds for local use.
Top Spaces running it: smolagents/ml-intern ♥ 423 · akhaliq/DeepSeek-V4-Pro ♥ 20 · wangsheng/DeepSeekV4Chat ♥ 19 · quickgrid/Tokenizer-Visualizer ♥ 6
Weights only, an estimate: leave room for the KV cache. Method
About 959 GB at INT4, 1.92 TB at FP8, 3.84 TB at BF16: weights only, so leave room for the KV cache. Every expert must be resident, so total parameters count.
Estimate params × bytes per param × 1.2 · how we estimate
Claim-matched tests, graded by code. Receipts, not a score.
{
"providers": [
{
"provider": "parasail",
"endpoint_model": "parasail-deepseek-v4-pro",
"source_url": "https://api.parasail.io/v1/chat/completions",
"ttft_ms_median": 4626,
"ttft_any_ms_median": 1192,
"tokens_per_s_median": 33.5,
"runs": [
{
"ttft_s": 6.063,
"ttft_any_s": 1.192,
"tokens_per_s": 33.5,
"latency_s": 10.91,
"tokens_out": 366,
"reasoning_chars": 877,
"finish": "stop"
},
{
"ttft_s": 2.327,
"ttft_any_s": 0.999,
"tokens_per_s": 37.7,
"latency_s": 7.75,
"tokens_out": 292,
"reasoning_chars": 493,
"finish": "stop"
},
{
"ttft_s": 4.626,
"ttft_any_s": 1.598,
"tokens_per_s": 24.7,
"latency_s": 11.48,
"tokens_out": 284,
"reasoning_chars": 345,
"finish": "stop"
}
]
}
],
"note": "Single client, wall clock; tok/s counts every output token including hidden reasoning."
} {
"calls": [
{
"name": "get_weather",
"args": {
"city": "Lisbon",
"date": "2026-10-14"
}
},
{
"name": "check_calendar",
"args": {
"date": "2026-10-14"
}
},
{
"name": "book_table",
"args": {
"restaurant": "Cervejaria Ramiro",
"date": "2026-10-14",
"time": "19:30",
"party_size": 2
}
}
],
"checks": {
"get_weather": true,
"check_calendar": true,
"book_table": true
},
"final": "Here's a summary of everything:\n\n- **Weather in Lisbon on Wednesday, October 14, 2026**: Clear skies, 22°C, only a 5% chance of rain — no rain expected.\n- **Free evening slot**: 19:30–21:30\n- **Booking at Cervejaria Ramiro**: Table for 2 at 19:30 on October 14, 2026 — **Confirmed!**\n\nYour confirmation code is: **TBL-4471**. Enjoy the seafood! 🦐",
"fixture": "receipts.errand.v1"
} {
"fields_matched": 80,
"fields_total": 80,
"cost_per_1000_usd": 0.8097,
"parsed": true,
"per_item": [
{
"street": true,
"city": true,
"postcode": true,
"country": true
},
{
"street": true,
"city": true,
"postcode": true,
"country": true
},
{
"street": true,
"city": true,
"postcode": true,
"country": true
},
{
"street": true,
"city": true,
"postcode": true,
"country": true
},
{
"street": true,
"city": true,
"postcode": true,
"country": true
},
{
"street": true,
"city": true,
"postcode": true,
"country": true
},
{
"street": true,
"city": true,
"postcode": true,
"country": true
},
{
"street": true,
"city": true,
"postcode": true,
"country": true
},
{
"street": true,
"city": true,
"postcode": true,
"country": true
},
{
"street": true,
"city": true,
"postcode": true,
"country": true
},
{
"street": true,
"city": true,
"postcode": true,
"country": true
},
{
"street": true,
"city": true,
"postcode": true,
"country": true
},
{
"street": true,
"city": true,
"postcode": true,
"country": true
},
{
"street": true,
"city": true,
"postcode": true,
"country": true
},
{
"street": true,
"city": true,
"postcode": true,
"country": true
},
{
"street": true,
"city": true,
"postcode": true,
"country": true
},
{
"street": true,
"city": true,
"postcode": true,
"country": true
},
{
"street": true,
"city": true,
"postcode": true,
"country": true
},
{
"street": true,
"city": true,
"postcode": true,
"country": true
},
{
"street": true,
"city": true,
"postcode": true,
"country": true
}
],
"sample": [
{
"street": "1600 Amphitheatre Parkway",
"unit": null,
"city": "Mountain View",
"region": "CA",
"postcode": "94043",
"country": "US"
},
{
"street": "10 Downing Street",
"unit": null,
"city": "London",
"region": null,
"postcode": "SW1A 2AA",
"country": "GB"
},
{
"street": "Rua Augusta 274",
"unit": null,
"city": "Lisboa",
"region": null,
"postcode": "1100-053",
"country": "PT"
}
],
"fixture": "receipts.addresses.v1"
} {
"lengths_k": [
8,
32,
64
],
"depths": [
0.1,
0.5,
0.9
],
"cells": [
[
1,
1,
1
],
[
1,
1,
1
],
[
1,
1,
1
]
],
"detail": [
{
"k": 8,
"depth": 0.1,
"recalled": true,
"reply": "amber-falcon-7731",
"latency_s": 103,
"finish": "stop"
},
{
"k": 8,
"depth": 0.5,
"recalled": true,
"reply": "cobalt-marten-7828",
"latency_s": 2.44,
"finish": "stop"
},
{
"k": 8,
"depth": 0.9,
"recalled": true,
"reply": "saffron-newt-7925",
"latency_s": 3.4,
"finish": "stop"
},
{
"k": 32,
"depth": 0.1,
"recalled": true,
"reply": "jade-lynx-8022",
"latency_s": 4.7,
"finish": "stop"
},
{
"k": 32,
"depth": 0.5,
"recalled": true,
"reply": "umber-kestrel-8119",
"latency_s": 8.98,
"finish": "stop"
},
{
"k": 32,
"depth": 0.9,
"recalled": true,
"reply": "coral-heron-8216",
"latency_s": 63.86,
"finish": "stop"
},
{
"k": 64,
"depth": 0.1,
"recalled": true,
"reply": "slate-badger-8313",
"latency_s": 9.82,
"finish": "stop"
},
{
"k": 64,
"depth": 0.5,
"recalled": true,
"reply": "ochre-otter-8410",
"latency_s": 5.69,
"finish": "stop"
},
{
"k": 64,
"depth": 0.9,
"recalled": true,
"reply": "teal-ibis-8507",
"latency_s": 6.77,
"finish": "stop"
}
]
} Weights, every dated article, and repo commits on one rail.
Teal is the weights (2026-04-22), amber triangles are 10 dated articles (each links to it), grey ticks are repo commits.
46 derivatives on the Hub. Which build to run, by runtime: the most downloaded in each class.
From the Hugging Face model tree; quantized builds in teal, fine-tunes, merges and adapters in greys.
Everything else, folded: the full tables, every source.
| Benchmark | Value | Setting / notes | Reported by | Date |
|---|---|---|---|---|
| author-reported AGIEval (EM) | 83.1 | DeepSeek-V4-Pro-Base | model author | 2026-10-07 |
| author-reported BBH (EM) | 87.5 | DeepSeek-V4-Pro-Base | model author | 2026-10-07 |
| author-reported BigCodeBench · Write code with agents | 59.2 pass@1 | DeepSeek-V4-Pro-Base | model author | 2026-10-07 |
| author-reported C-Eval · Work across languages | 93.1 | DeepSeek-V4-Pro-Base | model author | 2026-10-07 |
| author-reported CLUEWSC (EM) | 85.2 | DeepSeek-V4-Pro-Base | model author | 2026-10-07 |
| author-reported CMMLU · Work across languages | 90.8 | DeepSeek-V4-Pro-Base | model author | 2026-10-07 |
| author-reported Commonsense QA sets · Chat and follow instructions | 85.6 | DeepSeek-V4-Pro-Base | model author | 2026-10-07 |
| author-reported DROP (F1) | 88.7 | DeepSeek-V4-Pro-Base | model author | 2026-10-07 |
| author-reported FACTS Parametric (EM) | 62.6 | DeepSeek-V4-Pro-Base | model author | 2026-10-07 |
| author-reported GSM8K · Reason through hard problems | 92.6 | DeepSeek-V4-Pro-Base | model author | 2026-10-07 |
| author-reported HellaSwag · Chat and follow instructions | 88 | DeepSeek-V4-Pro-Base | model author | 2026-10-07 |
| author-reported HumanEval · Write code with agents | 76.8 pass@1 | DeepSeek-V4-Pro-Base | model author | 2026-10-07 |
| author-reported LongBench v2 · Read long documents | 51.5 | DeepSeek-V4-Pro-Base | model author | 2026-10-07 |
| author-reported MATH-500 · Reason through hard problems | 64.5 | DeepSeek-V4-Pro-Base | model author | 2026-10-07 |
| author-reported MATH-500 · Reason through hard problems | 90.9 | DeepSeek-V4-Pro-Base | model author | 2026-10-07 |
| author-reported MGSM · Work across languages | 84.4 | DeepSeek-V4-Pro-Base | model author | 2026-10-07 |
| author-reported MMLU · Reason through hard problems | 90.1 | DeepSeek-V4-Pro-Base | model author | 2026-10-07 |
| author-reported MMLU · Reason through hard problems | 90.8 | DeepSeek-V4-Pro-Base | model author | 2026-10-07 |
| author-reported MMLU-Pro · Reason through hard problems | 73.5 | DeepSeek-V4-Pro-Base | model author | 2026-10-07 |
| author-reported MMLU-Pro · Reason through hard problems | 87.5 | DeepSeek-V4-Pro-Max | model author | 2026-10-07 |
| author-reported MMMLU · Work across languages | 90.3 | DeepSeek-V4-Pro-Base | model author | 2026-10-07 |
| author-reported MultiLoKo (EM) | 51.1 | DeepSeek-V4-Pro-Base | model author | 2026-10-07 |
| author-reported SimpleQA · Reason through hard problems | 55.2 | DeepSeek-V4-Pro-Base | model author | 2026-10-07 |
| author-reported SimpleQA · Reason through hard problems | 57.9 pass@1 | DeepSeek-V4-Pro-Max | model author | 2026-10-07 |
| author-reported SuperGPQA · Reason through hard problems | 53.9 | DeepSeek-V4-Pro-Base | model author | 2026-10-07 |
| Benchmark | Value | Setting / notes | Reported by | Date |
|---|---|---|---|---|
| author-reported Winogrande · Chat and follow instructions | 81.5 | DeepSeek-V4-Pro-Base | model author | 2026-10-07 |
Labels are evidence, not verdicts: measured a third-party leaderboard row for this model; author-reported a number the model author published in the card or eval files; structural a deterministic signal from the name, config or chat template, or a decision-model estimate. Each chip links to its source. All use cases.
| Pipeline tag | text-generation |
|---|---|
| Library | transformers |
| Architectures | DeepseekV4ForCausalLM |
| Model type | deepseek_v4 |
| Dtype | bfloat16 |
| Params by dtype | BF16: 2,816,899,328 · F32: 87,776,414 · F8_E4M3: 23,169,335,296 · I8: 1,572,763,336,704 · I64: 2,327,040 |
| Size band | XXL |
| MoE | yes |
| Experts | 384 |
| Experts per token | 6 |
| Context length | 1,048,576 (config.json max_position_embeddings) |
| Papers | arXiv:2606.19348 |
| License | MIT (mit) |
| Hub snapshot | 2026-10-25 |
vLLM: supported · DeepseekV4ForCausalLM · 7050ef881ff0835f6890a47db1859a24c65481d6SGLang: supported · DeepseekV4ForCausalLM · 773cb938fe9484a8f7e7e46fb1b1fe96412c59ed
vLLM registry (7050ef881ff0835f6890a47db1859a24c65481d6) · SGLang registry (773cb938fe9484a8f7e7e46fb1b1fe96412c59ed) · Matched by architecture class name against each project's registry on main; 'supported' means the architecture is registered, not that this checkpoint was tested.
Weights-only memory for DeepSeek-V4-Pro: params × bytes/param × 1.2 overhead. KV cache and activations are extra. How this is computed.
| BF16 (2 bytes/param) | 3.84 TB · Cluster (≥640 GB) |
|---|---|
| FP8 (1 byte/param) | 1.92 TB · Cluster (≥640 GB) |
| INT4 (0.5 bytes/param) | 959 GB · Cluster (≥640 GB) |
Weights only (params × bytes/param × 1.2 overhead); KV cache and activations extra. MoE: all experts must be resident, so total parameters count.
quantized: 30finetune: 16
| Variant | Relation | Quant | Params | Band | License | Author | Likes | Downloads |
|---|---|---|---|---|---|---|---|---|
| nvidia/DeepSeek-V4-Pro-NVFP4 | quantized | NVFP4 | 1.60T | XXL | mit | nvidia | 81 | 453.6k |
| sgl-project/DeepSeek-V4-Pro-FP8 | quantized | -FP8 | 1.60T | XXL | mit | sgl-project | 13 | 78.5k |
| teamblobfish/DeepSeek-V4-Pro-GGUF | quantized | GGUF | — | — | mit | teamblobfish | 15 | 64.1k |
| mlx-community/DeepSeek-V4-Pro | quantized | — | 267B | XXL | mit | mlx-community | 5 | 22.2k |
| inferencerlabs/DeepSeek-V4-Pro-MTP-MLX | quantized | MLX | 25.8B | L | — | inferencerlabs | 3 | 12k |
| unsloth/DeepSeek-V4-Pro | quantized | — | 812B | XXL | mit | unsloth | 61 | 4k |
| batiai/DeepSeek-V4-Pro-GGUF | quantized | GGUF | — | — | mit | batiai | 2 | 4.8k |
| amd/DeepSeek-V4-Pro-MXFP4 | quantized | MXFP4 | 810B | XXL | mit | amd | 0 | 4.9k |
| Intel/DeepSeek-V4-Pro-W4A16-AutoRound | quantized | -W4A16 | 220B | XXL | mit | Intel | 0 | 2.9k |
| nvidia/DeepSeek-V4-Pro-nvfp4-DSpark | quantized | nvfp4 | 1.65T | XXL | mit | nvidia | 7 | 2.4k |
| yujiepan/deepseek-v4-tiny-random | quantized | — | 189M | S | — | yujiepan | 3 | 2.4k |
| NagusameCS/ultratensor-models | quantized | GGUF | — | — | mit | NagusameCS | 0 | 2.3k |
| inference-optimization/DeepSeek-V4-Pro-0.5B-A0.37B | finetune | — | 490M | S | mit | inference-optimization | 0 | 1.8k |
| canada-quant/DeepSeek-V4-Pro-NVFP4-FP8-MTP | quantized | NVFP4 | 1.70T | XXL | mit | canada-quant | 5 | 1.1k |
| RedHatAI/DeepSeek-V4-Pro-NVFP4-FP8 | quantized | NVFP4 | 894B | XXL | mit | RedHatAI | 1 | 1.2k |
| silence09/DeepSeek-V4-Pro-Tiny | finetune | — | 1.31B | S | mit | silence09 | 4 | 1k |
| amd/DeepSeek-V4-Pro-NVFP4 | quantized | NVFP4 | 812B | XXL | mit | amd | 2 | 1.1k |
| yujiepan/deepseek-v4-fp4-fp8-tiny-random | quantized | -fp8 | 189M | S | — | yujiepan | 0 | 1.1k |
| m8than/DeepSeek-V4-Pro-E2M1-Furnace | quantized | — | 223B | XXL | mit | m8than | 0 | 1k |
| zenlm/zen5-max-gguf | quantized | gguf | — | — | mit | zenlm | 2 | 868 |
| DevQuasar/deepseek-ai.DeepSeek-V4-Pro-GGUF | quantized | GGUF | — | — | — | DevQuasar | 0 | 855 |
| intel-ai/DeepSeek-V4-Pro-MXFP4-Mixed-CT-AutoRound | quantized | MXFP4 | 862B | XXL | mit | intel-ai | 0 | 605 |
| tiny-random/deepseek-v4-bf16 | finetune | -bf16 | 7.98M | S | — | tiny-random | 0 | 562 |
| yujiepan/deepseek-v4-bf16-tiny-random | finetune | -bf16 | 7.98M | S | — | yujiepan | 0 | 517 |
| livadies/DeepSeek-V4-Pro-Ghetto-Edition-MoE-Rank-64 | finetune | — | 169M | S | apache-2.0 | livadies | 2 | 332 |
| tiny-random/deepseek-v4 | quantized | — | 189M | S | — | tiny-random | 0 | 429 |
| wdfgyuagguf/DeepSeek-V4-Pro-NVFP4-FREE | quantized | NVFP4 | 910B | XXL | mit | wdfgyuagguf | 2 | 314 |
| AxionML/DeepSeek-V4-Pro-NVFP4 | quantized | NVFP4 | 1.60T | XXL | mit | AxionML | 0 | 293 |
| tiny-random/deepseek-v4-fp4-fp8 | quantized | -fp8 | 189M | S | — | tiny-random | 1 | 227 |
| brodatech/DeepSeek-V4-Pro-NVFP4 | quantized | NVFP4 | 910B | XXL | mit | brodatech | 0 | 210 |
| nathanielthomas/DeepSeek-V4-Pro-FP8 | quantized | -FP8 | 1.60T | XXL | mit | nathanielthomas | 1 | 126 |
| SLAI-AITP/SLAI-T-Rex-Pro | finetune | — | 1.60T | XXL | apache-2.0 | SLAI-AITP | 2 | 56 |
| INCModel/DeepSeek-V4-Pro-MXFP4-LLMC | quantized | MXFP4 | 851B | XXL | mit | INCModel | 0 | 152 |
| Divinci-AI/deepseek-v4-pro-vindex | finetune | — | — | — | mit | Divinci-AI | 2 | 0 |
| florentin-one/LSTR | finetune | — | — | — | mit | florentin-one | 2 | 0 |
| erenyeager-1/deepseek-v4_2 | quantized | — | 189M | S | — | erenyeager-1 | 0 | 87 |
| ANetResearch/DeepSeek-V4-Pro-kllm | quantized | — | 1.60T | XXL | mit | ANetResearch | 1 | 0 |
| benjzzz/DeepSeek-V4-Pro-671B-GALE-1bit-v4 | finetune | — | — | — | other | benjzzz | 1 | 0 |
| inference-optimization/DeepSeek-V4-Pro-3.7B-A3.4B-small | finetune | — | 3.68B | M | mit | inference-optimization | 0 | 48 |
| renard777/DeepSeek-V4-Pro-NVFP4 | quantized | NVFP4 | 1.60T | XXL | mit | renard777 | 0 | 17 |
| Date | Commit | SHA |
|---|---|---|
| 2026-06-22 | Update technical report | b5968e9 |
| 2026-06-08 | Update inference/kernel.py | 5607980 |
| 2026-05-06 | Update technical report | 89d501a |
| 2026-04-27 | Update config.json | 4504094 |
| 2026-04-27 | Update inference/model.py | a1fd202 |
| 2026-04-24 | Update technical report | 5e74e69 |
| 2026-04-24 | Update README | 0366e4e |
| 2026-04-24 | Update README | 165b591 |
| 2026-04-24 | Update config.json | 9b13d9e |
| 2026-04-24 | Update inference/config.json | 3cd0b49 |
| 2026-04-24 | Update benchmark figure | 833c42d |
| 2026-04-24 | Update technical report | 5c449c2 |
| 2026-04-24 | Update technical report | 254fa90 |
| 2026-04-24 | Update technical report link | 699727f |
| 2026-04-24 | Update inference/generate.py | 0f9442d |
| 2026-04-24 | Upload config.json | 508f90a |
| 2026-04-24 | Release DeepSeek-V4 | 0e1a0e5 |
| 2026-04-23 | use sys.path for encoding | 30451c8 |
| 2026-04-23 | delete pycache | a75964d |
| 2026-04-23 | add inference code | 44572c0 |
| 2026-04-23 | Add files using upload-large-folder tool | 3e9dc38 |
| 2026-04-23 | Add files using upload-large-folder tool | 8ef7029 |
| 2026-04-22 | initial commit | 244d014 |
Hosted endpoints observed for DeepSeek-V4-Pro, sorted by input price (USD per million tokens). Each row names its observer and date; prices change daily, so check the source before quoting. Cheapest observed input price: $0.21/M.
| Provider | Model ref | Context | Quant | $/M in | $/M out | tok/s | TTFT | Tools | Status | Observed |
|---|---|---|---|---|---|---|---|---|---|---|
| Baidu openrouter | deepseek/deepseek-v4-pro | 1M | fp8 | $0.21 | $0.42 | — | — | yes | live | 2026-10-24 |
| StreamLake openrouter | deepseek/deepseek-v4-pro | 1000K | fp8 | $0.21 | $0.42 | — | — | yes | live | 2026-10-24 |
| Relace openrouter | deepseek/deepseek-v4-pro | 1M | fp4 | $0.90 | $1.50 | — | — | yes | live | 2026-10-24 |
| GMICloud openrouter | deepseek/deepseek-v4-pro | 1M | fp8 | $0.96 | $1.91 | — | — | yes | live | 2026-10-24 |
| DigitalOcean openrouter | deepseek/deepseek-v4-pro | 1M | unknown | $1.04 | $2.09 | — | — | yes | live | 2026-10-24 |
| Reka openrouter | deepseek/deepseek-v4-pro | 1M | unknown | $1.05 | $2.10 | — | — | yes | live | 2026-10-24 |
| Cloudflare openrouter | deepseek/deepseek-v4-pro | 1M | unknown | $1.15 | $2.55 | — | — | yes | live | 2026-10-24 |
| DeepInfra hf, deepinfra, openrouter | deepseek-ai/DeepSeek-V4-Pro | 1M | fp8 | $1.30 | $2.60 | 56.8 | 477 ms | yes | live | 2026-10-25 |
| Alibaba openrouter | deepseek/deepseek-v4-pro | 977K | fp8 | $1.42 | $2.83 | — | — | yes | status -2 | 2026-10-24 |
| SiliconFlow openrouter | deepseek/deepseek-v4-pro | 1M | fp8 | $1.50 | $3.13 | — | — | yes | live | 2026-10-24 |
| Novita hf, openrouter | deepseek/deepseek-v4-pro | 1M | fp8 | $1.60 | $3.20 | 54.3 | 1311 ms | yes | live | 2026-10-25 |
| Venice openrouter | deepseek/deepseek-v4-pro | 977K | unknown | $1.65 | $3.30 | — | — | yes | live | 2026-10-24 |
| AtlasCloud openrouter | deepseek/deepseek-v4-pro | 1M | fp4 | $1.68 | $3.38 | — | — | yes | live | 2026-10-24 |
| Azure openrouter | deepseek/deepseek-v4-pro | 1M | unknown | $1.91 | $3.83 | — | — | yes | live | 2026-10-24 |
| Featherless hf | deepseek-ai/DeepSeek-V4-Pro | — | — | — | — | — | — | — | live | 2026-10-25 |
| Parasail parasail | deepseek-ai/DeepSeek-V4-Pro | — | — | — | — | — | — | — | serverless | 2026-10-24 |
Ranked by source signals (HN, Lobsters, authority domains, official posts) and recency. Summaries are generated from a stored copy of the article text; every sentence cites a span of that text, and nothing is shown that failed the citation check.
arXiv links found in the model card and its tags. "Peer-reviewed" is shown only with evidence: a published venue in OpenAlex (measured) or the authors' own journal reference on arXiv (reported).
Hub snapshot: 2026-10-25 · HF API: 2026-10-24 21:31 UTC · Providers: 2026-10-24 21:44 UTC · Articles: 2026-10-24 21:45 UTC · Summary: 2026-10-07 14:59 UTC · Last verified 2026-10-25
Email alerts are not open yet; the feeds above are the same data. See feeds for the item schema.