Llama 4 Maverick
MetaReleased Apr 5, 2025Open weights · Llama Community Licensellama-4-maverick
- Intelligence (Epoch)
- 132 · 94th of 111
- Reasoning
- no
- Knowledge cutoff
- December 2024
- Context
- 1M tokens
- Max output
- 32k tokens
- Input
- text, image
- API features
- tools, structured outputs, JSON mode, seed, logprobs
Read Oct 23, 06:00 UTC from the hosts' published offers and OpenRouter, spec sheet from Meta · cutoff: llama.com
Intelligence for the price
21 models score higher for the same price or less; it ranks 22 of the 35 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, 132 with an interval of 128 to 134.
Against its rivals
The best of its price range and the top score
- Llama 4 Maverickthis model$1.00132
- 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 8.3× less: gpt-oss-20b at AkashML, $0.12 per M input + output · their Epoch intervals overlap (138 against 132).
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 1 of the 6 workstations in our guideSelf-host guide ›- Parameters
- 400B
- 17B active per token (MoE)
- Memory needed
- 240 GB
- in INT4 · 480 GB in INT8
- Smallest cloud setup
- 4× H100
- 320 GB · $8.60/h, about $6,278 a month
- Worth it above
- 6B tokens
- a month, against the cheapest API at $1.00 per M
| Quantization | Memory | Smallest cloud GPU | Quality |
|---|---|---|---|
| INT4 (Q4) | 240 GB | 4× H100 · $8.60/h | smallest footprint, minor quality loss |
| INT8 (Q8) | 480 GB | 8× H100 · $17.20/h | near-lossless |
| FP16 (full) | 960 GB | multi-node, over 640 GB | reference quality |
At home: in INT4 it fits a Mac Studio M5 Ultra (256 GB unified), about $9,499 once, or $0.3615/h over 3 years, electricity aside; it pays for itself after about 9B 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 |
|---|---|---|---|---|---|---|---|
| DigitalOcean125K ctx (1M) · 16K out | $0.25 | $0.87 | $0.05 | 15 | 0.72 s | 100% | Oct 23 |
| Parasailfp8 · 512K ctx (1M) · 32K out | $0.35 | $1.00 | $0.17 | 68 | 0.53 s | 99.9% | Oct 23 |
| DeepInfra1M ctx | $0.20 | $0.80 | — | — | — | 99.8% | Oct 1 |
| Novita AIprecision not stated · 1M ctx · 8K out | $0.27 | $0.85 | — | — | — | — | Oct 23 |
| Googleprecision not stated · 512K ctx (1M) · 8K out | $0.35 | $1.15 | — | — | — | — | Oct 23 |
5 of 5 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 | not checked yet | 1M | not stated by the host | — | — | — |
| Novita AI | not stated by the host | 1M | 8K | — | — | — |
| DigitalOcean | not checked yet | 125K | 16K | yes | yes | no |
| Parasail | fp8 | 512K | 32K | yes | yes | no |
| not stated by the host | 512K | 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 Maverick spec sheet, field by field, with sources
Llama 4 Maverick 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-Maverick-17B-128E-Instruct · weights repository @ 73d1471 · file not readable · read 2026-10-08 · 2 of 10 fields published by the maker
| Provider | Chatbot 1,000 in / 500 out | RAG / long context 8,000 in / 500 out | Batch summarize 4,000 in / 1,000 out |
|---|---|---|---|
| DeepInfra | $0.60 | $2.00 | $1.60 |
| Novita AI | $0.69 | $2.58 | $1.93 |
| DigitalOcean | $0.68 | $2.44 | $1.87 |
| Parasail | $0.85 | $3.30 | $2.40 |
| $0.93 | $3.38 | $2.55 |
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
- Muse Spark Open5 providers · from $5.50
- Llama 3.1 70B Instruct3 providers · from $0.80
- Llama 4 Scout3 providers · from $0.40
- Llama 3.2 3B Instruct2 providers · from $0.38