Llama 4 Scout
MetaReleased Apr 5, 2025Open weights · Llama Community Licensellama-4-scout
- Intelligence (Epoch)
- 130 · 97th of 111
- Reasoning
- no
- Knowledge cutoff
- December 2024
- Context
- 1.31M tokens
- Max output
- 16k tokens
- Input
- text, image
- API features
- tools, structured outputs, JSON mode, seed
Read Oct 23, 06:00 UTC from the hosts' published offers and OpenRouter, spec sheet from Meta · cutoff: llama.com
Intelligence for the price
13 models score higher for the same price or less; it ranks 14 of the 21 models at its price or below.
Epoch Capabilities Index against the lowest input + output price per M, log scale · prices Oct 23. Score: Epoch AI, CC BY 4.0, 130 with an interval of 125 to 131.
Against its rivals
The best of its price range and the top score
- Llama 4 Scoutthis model$0.40130
- Claude Opus 5.5top score$24.00169
- Claude Haiku 5.5same price range$0.60159
- GPT-6 Lunasame price range$0.60157
Same level for 2.7× less: Gemma 3 12B at Novita AI, $0.15 per M input + output · their Epoch intervals overlap (124 against 130).
Bars: Epoch Capabilities Index (Epoch AI, CC BY 4.0), drawn from 100, below the lowest score in the catalogue · price: lowest input + output per M.
Run it yourself
open weights, Llama Community License · fits 4 of the 6 workstations in our guideSelf-host guide ›- Parameters
- 109B
- 17B active per token (MoE)
- Memory needed
- 65 GB
- in INT4 · 131 GB in INT8
- Smallest cloud setup
- A100
- 80 GB · $1.19/h, about $869 a month
- Worth it above
- 2B tokens
- a month, against the cheapest API at $0.40 per M
| Quantization | Memory | Smallest cloud GPU | Quality |
|---|---|---|---|
| INT4 (Q4) | 65 GB | A100 · $1.19/h | smallest footprint, minor quality loss |
| INT8 (Q8) | 131 GB | 2× H100 · $4.30/h | near-lossless |
| FP16 (full) | 262 GB | 4× H100 · $8.60/h | reference quality |
At home: in INT4 it fits a Mac Studio M5 Ultra (96 GB unified), about $5,499 once, or $0.2092/h over 3 years, electricity aside; it pays for itself after about 14B tokens against the cheapest API.
Memory ≈ parameters × bytes per parameter × 1.2 · cloud price: on-demand rate, running 24/7 · builds: GGUF, AWQ, MLX, GPTQ, Ollama · break-even calculator
| Provider | Input | Output | Cache ↑ | tok/s | First token | Uptime 24h | Checked |
|---|---|---|---|---|---|---|---|
| DeepInfrafp8 · 320K ctx · 16K out | $0.10 | $0.30 | — | 35 | 0.61 s | 100% | Oct 23 |
| Novita AIprecision not stated · 128K ctx (320K) | $0.18 | $0.59 | — | — | — | — | Oct 23 |
| Googleprecision not stated · 8K out | $0.25 | $0.70 | — | — | — | — | Oct 23 |
3 of 3 providers · prices per million tokens, read Oct 23, 06:00 UTC · speed: OpenRouter, median of the last 30 min, read Oct 23, 06:00 UTC · uptime: OpenRouter, last 24 h · under each host: weights precision, context and max output as served, the maker's value in brackets when the host's differs
| Provider | Weights | Context | Max output | Tools | Structured outputs | Reasoning |
|---|---|---|---|---|---|---|
| DeepInfra | fp8 | 320K | 16K | no | yes | no |
| Novita AI | not stated by the host | 128K | not stated by the host | — | — | — |
| not stated by the host | under review | 8K | yes | yes | no |
Weights, context and max output: read at each host's own catalogue or docs where its terms allow, otherwise as the host declares to OpenRouter; hover a cell for its source and date · tools, structured outputs, reasoning: as declared to OpenRouter · not verified by us
Llama 4 Scout spec sheet, field by field, with sources
Llama 4 Scout spec sheetmaker-declared
What Meta declares about the model itself — read from its own weights repository and documentation, not from any host. What each endpoint actually serves is in the pricing above: the two can differ, and both are true.
- Context window
- weights repository under access conditions
- Parameters
- weights repository under access conditions
- Active experts
- weights repository under access conditions
- Weight precision
- weights repository under access conditions
- License
- Llama Community License — open weights, conditionalcuratedScope: the licence on the published weights, and nothing else. It is not the maker's acceptable-use policy, which is a separate document, and it is not the contract you sign with whichever host you call — hosts set their own terms, which this index does not read.
- Knowledge cutoff
- December 2024maker's docs
- Modalities
- weights repository under access conditions
- Max output (official)
- to verify
- Release date
- to verify≈ April 5, 2025 third-party catalogue — not the maker's figure
- Maker lifecycle status
- to verify
meta-llama/Llama-4-Scout-17B-16E-Instruct · weights repository @ 92f3b15 · file not readable · read 2026-10-08 · 2 of 10 fields published by the maker
| Date | Provider | Input | Output | Change |
|---|---|---|---|---|
| Oct 22 | DeepInfra | $0.08 → $0.10 | $0.24 → $0.30 | +25% |
| Oct 16 | DeepInfra | $0.10 → $0.08 | $0.30 → $0.24 | −20% |
Every published change of input or output price, newest first · change on input + output · full series: pricing-history.csv.
| Provider | Chatbot 1,000 in / 500 out | RAG / long context 8,000 in / 500 out | Batch summarize 4,000 in / 1,000 out |
|---|---|---|---|
| DeepInfra | $0.25 | $0.95 | $0.70 |
| Novita AI | $0.47 | $1.74 | $1.31 |
| $0.60 | $2.35 | $1.70 |
What each host bills for 1,000 requests of a representative job
Your own workload
Other Meta models · all its models, hosts and history ›
- Llama 3.3 70B12 providers · from $0.42
- Llama 3.1 8B5 providers · from $0.06
- Llama 4 Maverick5 providers · from $1.00
- Muse Spark Open5 providers · from $5.50
- Llama 3.1 70B Instruct3 providers · from $0.80
- Llama 3.2 3B Instruct2 providers · from $0.38