Up to date
meta-llama Llama Community License (llama4) out 19 months ago
109B parameters, images and text in, text out, 1.3M tokens of context. 4 providers serve it from $0.080 per million input tokens.
Verified 2026-10-25 Rank #58 in LLMs · score 105.6 method v1 Sources 4 Downloads 30d 142.7k · #279 of 619 tracked
Changed this week: Cheapest input price fell 20%: $0.100 → $0.080 per 1M (OpenRouter).2026-10-24 · 1 new provider: Nscale.2026-10-23
Picked by rule from 26 tracked pieces: the lab's own post, the most shared, a field report, the latest.
Meta's AI API has remained waitlist-only for 10 months since the Llama-4 release, prompting discussions on internal dysfunction.
The 2 picks above, plus these 23. 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.
4 providers with a live price, from $0.080 to $0.25 per million input tokens; the median is $0.14. 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.
Served by 4 API providers; 39 quantized builds for local use; a big base for builders (90 fine-tunes, adapters and merges).
Top Spaces running it: pliny-the-prompter/obliteratus ♥ 621 · hadadrjt/ai ♥ 86 · openfree/Llama-4-Scout-17B-Research ♥ 63 · ginigen-ai/smol-worldcup ♥ 59
Weights only, an estimate: leave room for the KV cache. Method
About 65 GB at INT4, 130 GB at FP8, 261 GB at BF16: weights only, so leave room for the KV cache.
Estimate params × bytes per param × 1.2 · how we estimate
Third-party measurements only; author-reported numbers stay in Reference, marked as such.
28.13. Each tick is a model on this site with a measured BFCL row; author-reported numbers stay in Reference. Percent (overall accuracy). FC
Source · leaderboard · 2026-10-25
Weights, every dated article, and repo commits on one rail.
Teal is the weights (2025-04-02), amber triangles are 10 dated articles (each links to it).
129 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 BFCL · Call tools and APIs | 28.13 percent (overall accuracy) | FC5 sub-scores
| leaderboard | 2026-10-25 |
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 | Llama4ForConditionalGeneration |
| Model type | llama4 |
| Params by dtype | BF16: 108,641,793,536 |
| Size band | XXL |
| MoE | no |
| Context length | 1,310,720 (provider listing) |
| Gated | manual |
| Papers | arXiv:2204.05149 |
| License | Llama Community License (llama4) (other) |
| Hub snapshot | 2026-10-25 |
vLLM: supported · Llama4ForConditionalGeneration · 7050ef881ff0835f6890a47db1859a24c65481d6SGLang: supported · Llama4ForConditionalGeneration · 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 Llama-4-Scout-17B-16E-Instruct: params × bytes/param × 1.2 overhead. KV cache and activations are extra. How this is computed.
| BF16 (2 bytes/param) | 261 GB · Multi-GPU node (<640 GB) |
|---|---|
| FP8 (1 byte/param) | 130 GB · Multi-GPU node (<640 GB) |
| INT4 (0.5 bytes/param) | 65 GB · Single high-end GPU (<80 GB) |
Weights only (params × bytes/param × 1.2 overhead); KV cache and activations extra.
Base model: meta-llama/Llama-4-Scout-17B-16E
quantized: 39finetune: 39adapter: 51
Hosted endpoints observed for Llama-4-Scout-17B-16E-Instruct, 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: $0.08/M.
| Provider | Model ref | Context | Quant | $/M in | $/M out | tok/s | TTFT | Tools | Status | Observed |
|---|---|---|---|---|---|---|---|---|---|---|
| DeepInfra hf, deepinfra, openrouter | meta-llama/Llama-4-Scout-17B-16E-Instruct | 320K | fp8 | $0.08 | $0.24 | 59 | 402 ms | yes | live | 2026-10-25 |
| Nscale hf | meta-llama/Llama-4-Scout-17B-16E-Instruct | 869K | — | $0.09 | $0.29 | 69.5 | 369 ms | yes | live | 2026-10-25 |
| Novita hf | meta-llama/llama-4-scout-17b-16e-instruct | 128K | — | $0.18 | $0.59 | 51 | 534 ms | no | live | 2026-10-25 |
| Google openrouter | meta-llama/llama-4-scout | 1.3M | unknown | $0.25 | $0.70 | — | — | yes | live | 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 21:32 UTC · Providers: 2026-10-24 21:44 UTC · Articles: 2026-10-24 21:45 UTC · Summary: 2026-10-07 15:00 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.
