Up to date
meta-llama Llama Community License (llama4) out 19 months ago
402B parameters, images and text in, text out, 512K tokens of context. 3 providers serve it from $0.19 per million input tokens.
Verified 2026-10-25 Rank #299 in LLMs · score 83.9 method v1 Sources 5 Downloads 30d 9.5k · #510 of 619 tracked
Changed this week: Context length changed: 1,048,576 → 524,288 tokens.2026-10-24
Picked by rule from 28 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.
3 providers with a live price, from $0.19 to $0.35 per million input tokens; the median is $0.35. 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 3 API providers; 17 quantized builds for local use.
Top Spaces running it: pliny-the-prompter/obliteratus ♥ 621 · openfree/Llama-4-Maverick-17B-Research ♥ 88 · hadadrjt/ai ♥ 86 · whitecircle/circle-guard-bench ♥ 32
Weights only, an estimate: leave room for the KV cache. Method
About 241 GB at INT4, 482 GB at FP8, 964 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.
15.6. Each tick is a model on this site with a measured Aider Polyglot row; author-reported numbers stay in Reference. Percent (pass_rate_2). edit_format=whole
Source · leaderboard · 2025-04-06
Weights, every dated article, and repo commits on one rail.
Teal is the weights (2025-04-01), amber triangles are 9 dated articles (each links to it).
25 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 Aider Polyglot · Write code with agents | 15.6 percent (pass_rate_2) | edit_format=whole | leaderboard | 2025-04-06 |
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: 401,583,781,376 |
| Size band | XXL |
| MoE | no |
| Context length | 524,288 (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-Maverick-17B-128E-Instruct: params × bytes/param × 1.2 overhead. KV cache and activations are extra. How this is computed.
| BF16 (2 bytes/param) | 964 GB · Cluster (≥640 GB) |
|---|---|
| FP8 (1 byte/param) | 482 GB · Multi-GPU node (<640 GB) |
| INT4 (0.5 bytes/param) | 241 GB · Multi-GPU node (<640 GB) |
Weights only (params × bytes/param × 1.2 overhead); KV cache and activations extra.
Base model: meta-llama/Llama-4-Maverick-17B-128E
quantized: 17finetune: 8
Hosted endpoints observed for Llama-4-Maverick-17B-128E-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: $0.19/M.
| Provider | Model ref | Context | Quant | $/M in | $/M out | tok/s | TTFT | Tools | Status | Observed |
|---|---|---|---|---|---|---|---|---|---|---|
| DigitalOcean openrouter | meta-llama/llama-4-maverick | 125K | unknown | $0.19 | $0.65 | — | — | yes | live | 2026-10-24 |
| Parasail parasail, openrouter | parasail-llama-4-maverick-instruct-fp8 | 512K | fp8 | $0.35 | $1.00 | — | — | yes | serverless | 2026-10-24 |
| Google openrouter | meta-llama/llama-4-maverick | 512K | unknown | $0.35 | $1.15 | — | — | 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 21:37 UTC · Providers: 2026-10-24 21:44 UTC · Articles: 2026-10-24 21:45 UTC · Summary: 2026-10-07 15:07 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.
