Up to date
321B parameters (8 of 288 experts per token), images and text in, text out, 1M tokens of context. 35 providers serve it from $0.018 per million input tokens.
Verified 2026-10-25 Rank #3 in LLMs · score 138.7 method v1 Sources 5 Downloads 30d 6.4M · #21 of 619 tracked
Changed this week: Cheapest input price fell 51.4%: $0.036 → $0.018 per 1M (OpenRouter).2026-10-24 · 20 new quantized builds on the Hub (201 in all).2026-10-24 · Cheapest input price fell 85.6%: $0.036 → $0.005 per 1M (OpenRouter).2026-10-24 · 1 more
Why did the open-weights model cross the road?
To get to the other side — the weights are open, so you can verify it yourself!
_____
// \\
//_______\\
\ | /
\ | /
\|/
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.3 of 4 pass · parasail-glm-53-flash on parasail · run 2026-10-09 · temperature 0 · cost $0.031 · 2026-10 thing: supermarket · all models →
Picked by rule from 43 tracked pieces: the lab's own post, the most shared, a field report, the latest.
GLM-5.3-Flash-Base outperforms GLM-4.5-Base overall and remains competitive with GLM-5-Base across most benchmarks.
Z.ai introduces GLM-5.3-Flash, the first natively multimodal model in the GLM-5 series, scoring 57 at $0.045 per task.
Anthropic analyzes GLM-5.3, a new open-weight model from Zhipu AI that lacks robust safeguards against misuse.
A team ran GLM 5.3 Flash exclusively for September but failed after 2B tokens due to infrastructure limits and a prototype error.
GLM-5.3-Flash is an open weights model released by Z AI on August 26, 2026, that scores 42 on the Artificial Analysis Intelligence Index.
An engineer spent $266 to root an Amazon Fire HD 10 tablet that kept shutting down its kiosk.
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.
32 providers with a live price, from $0.018 to $0.25 per million input tokens; the median is $0.15. 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 (35 API providers); heavily run locally (201 quantized builds).
Top Spaces running it: embedl/hfviewer ♥ 181 · akhaliq/GLM-5.3-Flash ♥ 13 · FineEnvs/simulation-rl-environments ♥ 12 · emanforhelp/model-pulse ♥ 5
Weights only, an estimate: leave room for the KV cache. Method
About 193 GB at INT4, 386 GB at FP8, 771 GB 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
The probe replies as received on 2026-10-07 from parasail, graded by code. Receipts, not a score.
def is_balanced(s: str) -> bool:
pairs = {')': '(', ']': '[', '}': '{'}
opening = set(pairs.values())
stack = []
for ch in s:
if ch in opening:
stack.append(ch)
elif ch in pairs:
if not stack or stack.pop() != pairs[ch]:
return amber-falcon-7731
{"city": "Lisbon", "unit": "c"} {"name": "Foo-9B-Instruct", "license": "Apache-2.0", "parameters_b": 9.2, "context_tokens": 131072, "languages": ["English", "French", "German", "Japanese"]} {
"providers": [
{
"provider": "parasail",
"endpoint_model": "parasail-glm-53-flash",
"source_url": "https://api.parasail.io/v1/chat/completions",
"ttft_ms_median": 4310,
"ttft_any_ms_median": 574,
"tokens_per_s_median": 190.6,
"runs": [
{
"ttft_s": 3.712,
"ttft_any_s": 0.466,
"tokens_per_s": 190.6,
"latency_s": 4.52,
"tokens_out": 862,
"reasoning_chars": 3288,
"finish": "stop"
},
{
"ttft_s": null,
"ttft_any_s": 0.574,
"tokens_per_s": 191.8,
"latency_s": 7.82,
"tokens_out": 1500,
"reasoning_chars": 5721,
"finish": "length"
},
{
"ttft_s": 4.907,
"ttft_any_s": 0.723,
"tokens_per_s": 184.5,
"latency_s": 5.43,
"tokens_out": 1002,
"reasoning_chars": 3923,
"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": {
"date": "2026-10-14",
"party_size": 2,
"restaurant": "Cervejaria Ramiro",
"time": "19:30"
}
}
],
"checks": {
"get_weather": true,
"check_calendar": true,
"book_table": true
},
"final": "All done! Here's a summary:\n\n- **Weather in Lisbon on 2026-10-14:** Clear, 5% chance of rain, high of 22°C — no rain expected, so I proceeded with the booking.\n- **Calendar:** Your free evening slot was 19:30–21:30.\n- **Booking:** Table for 2 at Cervejaria Ramiro on 2026-10-14 at 19:30.\n\n**Confirmation code: TBL-4471**",
"fixture": "receipts.errand.v1"
} Weights, every dated article, and repo commits on one rail.
Teal is the weights (2026-08-25), amber triangles are 10 dated articles (each links to it), grey ticks are repo commits.
245 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 |
|---|---|---|---|---|
| measured Terminal-Bench · Write code with agents | 35.76 percent (accuracy, mean of trials) | agent: Claude Code, reasoning_effort=none | leaderboard | 2026-08-26 |
| author-reported terminalbench_2_1 (harborframework/terminal-bench-2.1) | 84.3 | — | GLM-5.3-Flash model card | 2026-08-26 |
| author-reported deep_swe (datacurve/deep-swe) | 63.4 | Reported as DeepSWE v1.1 on the model card, run via the mini-swe-agent harness with 400K context. | GLM-5.3-Flash model card | 2026-08-26 |
| author-reported hle (cais/hle) | 55.3 | HLE with tools (full set) and a 300K-context management strategy, not the no-tools default; judged by GPT-5.6-luna (medium). | GLM-5.3-Flash model card | 2026-08-26 |
| author-reported ale-cli-pass-rate (agents-last-exam/agents-last-exam) | 26.3 | Claude Code harness; read from the card's benchmark chart. | GLM-5.3-Flash model card | 2026-08-26 |
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.
Listed in LLMs
| Pipeline tag | image-text-to-text |
|---|---|
| Library | transformers |
| Architectures | Glm5NextForConditionalGeneration |
| Model type | glm5_next |
| Dtype | bfloat16 |
| Params by dtype | BF16: 6,926,096,640 · F32: 295,518 · F8_E4M3: 314,396,639,232 |
| Size band | XXL |
| MoE | yes |
| Experts | 288 |
| Experts per token | 8 |
| Context length | 1,048,576 (config.json max_position_embeddings) |
| Languages | en, zh |
| Papers | arXiv:2602.15763 |
| License | MIT (mit) |
| Hub snapshot | 2026-10-25 |
vLLM: supported · Glm5NextForConditionalGeneration · 7050ef881ff0835f6890a47db1859a24c65481d6SGLang: supported · Glm5NextForConditionalGeneration · 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 GLM-5.3-Flash: params × bytes/param × 1.2 overhead. KV cache and activations are extra. How this is computed.
| BF16 (2 bytes/param) | 771 GB · Cluster (≥640 GB) |
|---|---|
| FP8 (1 byte/param) | 386 GB · Multi-GPU node (<640 GB) |
| INT4 (0.5 bytes/param) | 193 GB · Multi-GPU node (<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.
A fixed probe set run against a live API endpoint: the same questions for every model, answers graded by code, nothing judged by a model. Latencies are single-request wall clock from one client location, not a benchmark.
| Probe | Result | Latency | Reply (truncated) |
|---|---|---|---|
| Self-description | info | 1.5 s | I'm GLM, a large language model made by Z.ai. I don't know my exact training data cutoff date with certainty. |
| Tool call | pass | 0.7 s | {"city": "Lisbon", "unit": "c"} |
| Strict JSON | pass | 1.4 s | {"name": "Foo-9B-Instruct", "license": "Apache-2.0", "parameters_b": 9.2, "context_tokens": 131072, "languages": ["English", "French", "German", "Japanese"]} |
| Code (hidden tests) | pass | 7.4 s | def is_balanced(s: str) -> bool: pairs = {')': '(', ']': '[', '}': '{'} opening = set(pairs.values()) stack = [] for ch in s: if ch in opening: stack.append(ch) elif ch in pairs: if not stack or stack.pop() != pairs[ch]: return |
| Multi-step arithmetic | pass | 1.5 s | 16 |
| Needle recall at 128k tokens | pass | 4.3 s | amber-falcon-7731 |
Probe set firstlook.v1 · observed 2026-10-07 20:04 UTC · endpoint · provider docs · cost of this run $0.02
quantized: 201finetune: 32merge: 4adapter: 8
| Variant | Relation | Quant | Params | Band | License | Author | Likes | Downloads |
|---|---|---|---|---|---|---|---|---|
| unsloth/GLM-5.3-Flash-GGUF | quantized | GGUF | — | — | mit | unsloth | 500 | 1.7M |
| peasantsmith/GLM-5.3-Flash-Maya-GGUF | quantized | GGUF | — | — | mit | peasantsmith | 80 | 294.3k |
| orcarouter/GLM-5.3-Flash-Uncensored-FP8 | finetune | -FP8 | 321B | XXL | mit | orcarouter | 303 | 249.4k |
| nvidia/GLM-5.3-Flash-NVFP4 | quantized | NVFP4 | 169B | XXL | mit | nvidia | 174 | 181k |
| RedHatAI/GLM-5.3-Flash-NVFP4 | quantized | NVFP4 | 169B | XXL | mit | RedHatAI | 46 | 88.9k |
| incoai/GLM-5.3-Flash-DFlash2 | finetune | — | 1.17B | S | cc-by-nc-nd-4.0 | incoai | 127 | 76.2k |
| LibertAIDAI/GLM-5.3-Flash-NVFP4 | quantized | NVFP4 | 165B | XXL | mit | LibertAIDAI | 68 | 69.9k |
| dealignai/GLM-5.3-Flash-UNCENSORED-FP8 | quantized | -FP8 | 321B | XXL | mit | dealignai | 169 | 60.1k |
| huihui-ai/Huihui-GLM-5.3-Flash-abliterated-GGUF | quantized | GGUF | — | — | mit | huihui-ai | 294 | 44.1k |
| orcarouter/GLM-5.3-Flash-Uncensored-GGUF | quantized | GGUF | — | — | mit | orcarouter | 140 | 48.1k |
| GCSA-AiLab/GLM-5.3-Flash-Uncensored-RCO-GSQ-GGUF | quantized | GGUF | — | — | mit | GCSA-AiLab | 8 | 41.6k |
| autotrust/GLM-5.3-Flash-GGUF-DGX-Spark | quantized | GGUF | — | — | mit | autotrust | 28 | 40.2k |
| pfeifferj/GLM-5.3-Flash-GSQ-RCO-GGUF | quantized | GGUF | — | — | mit | pfeifferj | 34 | 36.6k |
| orcarouter/GLM-5.3-Flash-MLX | quantized | MLX | 348B | XXL | mit | orcarouter | 39 | 32.6k |
| amd/GLM-5.3-Flash-Quark-MXFP4 | quantized | MXFP4 | 169B | XXL | mit | amd | 1 | 32.5k |
| patrickbdevaney/GLM-5.3-Flash-REAP50-GGUF | quantized | GGUF | — | — | mit | patrickbdevaney | 20 | 31.2k |
| aj9o9/GLM-5.3-Flash-GGUF | quantized | GGUF | — | — | mit | aj9o9 | 26 | 28.9k |
| autotrust/GLM5.3-Flash-E224-DGX-Spark | quantized | — | 128B | XXL | mit | autotrust | 72 | 23.9k |
| lapadatbogdan/GLM-5.3-Flash-Coder-RCO-152E-GGUF | quantized | GGUF | — | — | mit | lapadatbogdan | 23 | 23.4k |
| OneNexus/GLM-5.3-Flash-MXFP4 | quantized | MXFP4 | 169B | XXL | mit | OneNexus | 3 | 23.6k |
| dealignai/GLM-5.3-Flash-UNCENSORED-NVFP4 | quantized | NVFP4 | 165B | XXL | mit | dealignai | 52 | 16.5k |
| wtdcode/GLM-5.3-Flash-AWQ-W4A16 | quantized | AWQ | 321B | XXL | — | wtdcode | 22 | 17.3k |
| canada-quant/GLM-5.3-Flash-W4A16-MTP | quantized | -W4A16 | 49.9B | XL | mit | canada-quant | 21 | 15.5k |
| autotrust/GLM5.3-Flash-E192-DGX-Spark | quantized | — | 111B | XXL | mit | autotrust | 26 | 15.1k |
| DevQuasar/zai-org.GLM-5.3-Flash-GGUF | quantized | GGUF | — | — | — | DevQuasar | 10 | 15k |
| dealignai/GLM-5.3-Flash-CYBERSECURITY-W4A16 | quantized | -W4A16 | 321B | XXL | mit | dealignai | 42 | 12.6k |
| avar6/GLM-5.3-Flash-BF16-gguf | quantized | -BF16 | — | — | — | avar6 | 14 | 12.7k |
| orcarouter/GLM-5.3-Flash-Uncensored-NVFP4 | quantized | NVFP4 | 321B | XXL | mit | orcarouter | 94 | 8.3k |
| TensorFold/GLM-5.3-Flash-MLX-4bit-MTP | quantized | MLX | 321B | XXL | mit | TensorFold | 13 | 12.3k |
| Justvugg/GLM-5.3-Flash-colibri-int4-g64 | quantized | int4 | — | — | mit | Justvugg | 16 | 12.1k |
| BoldingBuilds/GLM-5.3-Flash-Uncensored-GGUF | quantized | GGUF | — | — | mit | BoldingBuilds | 4 | 12.6k |
| turboderp/GLM-5.3-Flash-exl3 | quantized | exl3 | — | — | mit | turboderp | 62 | 7.9k |
| nvidia/GLM-5.3-Flash-FP4-Local | quantized | — | 175B | XXL | other | nvidia | 119 | 5k |
| pipenetwork/GLM-5.3-Flash-MLX-mixed-4_8bit | quantized | MLX | 314B | XXL | mit | pipenetwork | 15 | 9.7k |
| Mia-AiLab/GLM-5.3-Flash-EXL3-4bpw-TensorFold | quantized | EXL3 | 87.8B | XL | apache-2.0 | Mia-AiLab | 65 | 6.4k |
| cyankiwi/GLM-5.3-Flash-AWQ-INT4 | quantized | AWQ | 56.7B | XL | mit | cyankiwi | 12 | 9k |
| unsloth/GLM-5.3-Flash-FP8 | quantized | -FP8 | 321B | XXL | mit | unsloth | 26 | 7.8k |
| pipenetwork/GLM-5.3-Flash-MLX-6bit | quantized | MLX | 314B | XXL | mit | pipenetwork | 4 | 8.3k |
| Intel/GLM-5.3-Flash-W4A16-AutoRound | quantized | -W4A16 | 50.3B | XL | mit | Intel | 18 | 7k |
| pipenetwork/GLM-5.3-Flash-MLX-4bit | quantized | MLX | 314B | XXL | mit | pipenetwork | 4 | 7.4k |
| Date | Commit | SHA |
|---|---|---|
| 2026-10-15 | chat template: speed up tool-result validation and reordering (GLM-5.3-Flash) (#63) | 46a050b |
| 2026-10-12 | Add Agents' Last Exam result (26.3, overall-pass-rate, read from card benchmark chart) (#62) | 91b6921 |
| 2026-09-07 | Add evaluation results (#12) | eb9eb20 |
| 2026-09-04 | chat template: early break in tool result reordering check | 690b705 |
| 2026-08-31 | update pipeline_tag | 03eb536 |
| 2026-08-27 | update | 04c4e9e |
| 2026-08-26 | update | 3f1971b |
| 2026-08-26 | update | 84c6a6a |
| 2026-08-26 | update | 9a7ae5f |
| 2026-08-26 | update template | c5b82b6 |
| 2026-08-26 | Add files using upload-large-folder tool | dbc994b |
| 2026-08-26 | Add files using upload-large-folder tool | 9855d73 |
| 2026-08-26 | update | c54b8d1 |
| 2026-08-26 | Add files using upload-large-folder tool | edfc283 |
| 2026-08-26 | Add files using upload-large-folder tool | 545670d |
| 2026-08-26 | Update README.md | 5d626e9 |
| 2026-08-26 | Update README.md | 69032ad |
| 2026-08-25 | initial commit | 3c7f1b4 |
Hosted endpoints observed for GLM-5.3-Flash, 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: $0.02/M.
| Provider | Model ref | Context | Quant | $/M in | $/M out | tok/s | TTFT | Tools | Status | Observed |
|---|---|---|---|---|---|---|---|---|---|---|
| Relace openrouter | z-ai/glm-5.3-flash | 1M | unknown | $0.02 | $0.14 | — | — | yes | live | 2026-10-24 |
| OpenInference openrouter | z-ai/glm-5.3-flash | 1M | fp4 | $0.02 | $0.11 | — | — | yes | live | 2026-10-24 |
| Sail Research openrouter | z-ai/glm-5.3-flash | 1M | fp4 | $0.05 | $0.18 | — | — | yes | live | 2026-10-24 |
| Wafer openrouter | z-ai/glm-5.3-flash | 1M | nvfp4 | $0.06 | $0.20 | — | — | yes | live | 2026-10-24 |
| Darkbloom openrouter | z-ai/glm-5.3-flash | 256K | fp4 | $0.07 | $0.18 | — | — | yes | status -2 | 2026-10-24 |
| StreamLake openrouter | z-ai/glm-5.3-flash | 1000K | fp8 | $0.07 | $0.25 | — | — | yes | live | 2026-10-24 |
| GMICloud openrouter | z-ai/glm-5.3-flash | 1M | fp8 | $0.07 | $0.25 | — | — | yes | live | 2026-10-24 |
| Near AI openrouter | z-ai/glm-5.3-flash | 1M | fp8 | $0.08 | $0.50 | — | — | yes | live | 2026-10-24 |
| Reka openrouter | z-ai/glm-5.3-flash | 1M | unknown | $0.08 | $2.40 | — | — | yes | live | 2026-10-24 |
| Novita hf, openrouter | zai-org/glm-5.3-flash | 1M | fp8 | $0.08 | $0.28 | 54.5 | 2335 ms | yes | live | 2026-10-25 |
| DeepInfra hf, deepinfra, openrouter | zai-org/GLM-5.3-Flash | 1M | fp4 | $0.12 | $0.40 | 45.9 | 568 ms | yes | live | 2026-10-25 |
| InferenceNet openrouter | z-ai/glm-5.3-flash | 1M | fp4 | $0.12 | $0.39 | — | — | yes | live | 2026-10-24 |
| NextBit openrouter | z-ai/glm-5.3-flash | 1M | fp4 | $0.13 | $0.50 | — | — | yes | live | 2026-10-24 |
| Phala openrouter | z-ai/glm-5.3-flash | 1M | nvfp4 | $0.13 | $0.42 | — | — | yes | live | 2026-10-24 |
| DigitalOcean openrouter | z-ai/glm-5.3-flash | 1M | unknown | $0.13 | $0.44 | — | — | yes | live | 2026-10-24 |
| Makora openrouter | z-ai/glm-5.3-flash | 1M | unknown | $0.14 | $0.47 | — | — | yes | live | 2026-10-24 |
| Together AI hf, openrouter | zai-org/GLM-5.3-Flash | 1024K | unknown | $0.15 | $0.50 | 129.6 | 322 ms | yes | live | 2026-10-25 |
| Fireworks AI hf, openrouter | accounts/fireworks/models/glm-5p3-flash | 1M | unknown | $0.15 | $0.50 | 96.9 | 861 ms | yes | live | 2026-10-25 |
| Z.ai hf, openrouter | glm-5.3-flash | 1M | fp8 | $0.15 | $0.50 | 48.2 | 2075 ms | yes | live | 2026-10-25 |
| Baseten hf, openrouter | zai-org/GLM-5.3-Flash | 1M | fp8 | $0.15 | $0.50 | 43 | 4859 ms | yes | live | 2026-10-25 |
| Parasail parasail, openrouter | parasail-glm-53-flash | 1M | fp4 | $0.15 | $0.50 | — | — | yes | serverless | 2026-10-24 |
| Mistral openrouter | z-ai/glm-5.3-flash | 1M | unknown | $0.15 | $0.50 | — | — | yes | live | 2026-10-24 |
| Cohere openrouter | z-ai/glm-5.3-flash | 1M | unknown | $0.15 | $0.50 | — | — | yes | live | 2026-10-24 |
| PrimeIntellect openrouter | z-ai/glm-5.3-flash | 1M | unknown | $0.15 | $0.50 | — | — | yes | live | 2026-10-24 |
| Nebius openrouter | z-ai/glm-5.3-flash | 1000K | fp4 | $0.15 | $0.50 | — | — | yes | status -2 | 2026-10-24 |
| Modal openrouter | z-ai/glm-5.3-flash | 1M | nvfp4 | $0.15 | $0.50 | — | — | yes | live | 2026-10-24 |
| Crusoe openrouter | z-ai/glm-5.3-flash | 1M | fp4 | $0.15 | $0.50 | — | — | yes | live | 2026-10-24 |
| CoreWeave openrouter | z-ai/glm-5.3-flash | 1M | nvfp4 | $0.15 | $0.50 | — | — | yes | live | 2026-10-24 |
| AtlasCloud openrouter | z-ai/glm-5.3-flash | 1M | fp8 | $0.15 | $0.50 | — | — | yes | live | 2026-10-24 |
| Friendli openrouter | z-ai/glm-5.3-flash | 1M | unknown | $0.15 | $0.50 | — | — | yes | live | 2026-10-24 |
| SiliconFlow openrouter | z-ai/glm-5.3-flash | 1M | fp8 | $0.15 | $0.50 | — | — | yes | live | 2026-10-24 |
| Venice openrouter | z-ai/glm-5.3-flash | 1M | unknown | $0.15 | $0.50 | — | — | yes | live | 2026-10-24 |
| Inceptron openrouter | z-ai/glm-5.3-flash | 1M | fp8 | $0.20 | $0.75 | — | — | yes | live | 2026-10-24 |
| Morph openrouter | z-ai/glm-5.3-flash | 1M | fp8 | $0.25 | $0.65 | — | — | yes | live | 2026-10-24 |
| Featherless hf | zai-org/GLM-5.3-Flash | — | — | — | — | — | — | — | live | 2026-10-25 |
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.