meta-llama
Meta: Llama 4 Maverick
meta-llama/llama-4-maverick
Our take
AI-assisted analysis based on the sources below. Suitability is an editorial assessment; test it on your own workload.
OpenRouter’s catalog describes meta-llama/llama-4-maverick as Meta’s Llama 4 Maverick 17B Instruct (128E), a multimodal mixture-of-experts model with 128 experts and 17 billion active parameters. The listing reports a 524,288-token context window, text and image inputs, text outputs, structured outputs, tool calling, and broad sampling controls. Its stated knowledge cutoff is August 31, 2024. The pack also contains catalog benchmark entries, but no independent model card, so capabilities should be treated as catalog-reported and validated on target workloads.[1]
Strengths
Limitations
- Evidence is limited to the OpenRouter catalog; no independent model card was available, so workload validation remains necessary.[1]
- Outputs are limited to text; the listing provides no image or audio output modality.[1]
- The catalog does not identify a dedicated reasoning capability, and the stated knowledge cutoff is August 31, 2024.[1]
Where to use it
- Consider for image-aware assistants and document workflows where a very large context window matters.[1]
- Potentially suitable for API applications that need tool calls or machine-readable structured outputs.[1]
- For coding, agentic, or interface-related tasks, treat the catalog benchmark entries as a starting point and test against your workload.[1]
Sources
- [1] OpenRouter catalog · Meta: Llama 4 MaverickSources checked: Nov 13, 2026
About this model
Description below is the original text supplied by OpenRouter, shown in the source language.
Llama 4 Maverick 17B Instruct (128E) is a high-capacity multimodal language model from Meta, built on a mixture-of-experts (MoE) architecture with 128 experts and 17 billion active parameters per forward...
Specifications
- Model ID
- meta-llama/llama-4-maverick
- Canonical ID
- meta-llama/llama-4-maverick-17b-128e-instruct
- Creator
- meta-llama
- Added to OpenRouter
- 05.04.2025
- Context length
- 524,288
- Modality
- text+image->text
- Input modalities
- text, image
- Output modalities
- text
- Token pricing
- USD per 1M tokens: in $0.350 / out $1
- Knowledge cutoff
- 31.08.2024
- Expiration date
- —
Tasks and capabilities
A grade appears only where the source supplies a matching measurement for that task, the model is active and the cohort holds at least 10 comparable models. The capability column lists facts the source declares — supported formats, reasoning and tool parameters — which are not measured quality.
| Task | Grade | Source-declared capability |
|---|---|---|
| General quality | No measurement | — |
| Coding | CC — below the B band | — |
| Agents | CC — below the B band | parameters: structured_outputs, tool_choice, tools |
| Writing | No measurement | output: text |
| Reasoning | No measurement | — |
| Document analysis | No measurement | — |
| Vision | No measurement | input: image |
| Image generation | No measurement | — |
| Audio | No measurement | — |
| Video | No measurement | — |
| Embeddings | No measurement | — |
Evaluations
| Source | Benchmark | Value | Grade | Data retrieved |
|---|---|---|---|---|
| Artificial Analysis | Coding index | 16.3 | CC — below the B band | 13.11.2026 |
| Artificial Analysis | Agentic index | 0.6 | CC — below the B band | 13.11.2026 |
| Design Arena | models · 3dwin rate 40.2% · rank 130 | 884Elo | CC — below the B band | 13.11.2026 |
| Design Arena | models · codecategorieswin rate 35.8% · rank 142 | 870Elo | CC — below the B band | 13.11.2026 |
| Design Arena | models · datavizwin rate 38.4% · rank 133 | 882Elo | CC — below the B band | 13.11.2026 |
| Design Arena | models · gamedevwin rate 33.7% · rank 143 | 828Elo | CC — below the B band | 13.11.2026 |
| Design Arena | models · uicomponentwin rate 40.8% · rank 137 | 890Elo | CC — below the B band | 13.11.2026 |
| Design Arena | models · websitewin rate 34.4% · rank 145 | 864Elo | CC — below the B band | 13.11.2026 |
How grades work
Each letter grade compares a model only against other models scored by the same source and metric in the current snapshot. S means the top 10%, A the next 20%, B the next 30%, C the rest. Models without a published measurement are shown as not rated — a supported format alone never implies measured quality.
- S — S — top 10% of the cohort
- A — A — next 20% of the cohort
- B — B — next 30% of the cohort
- C — C — below the B band
Providers
Optional live provider statistics from OpenRouter. Missing values are unknown, not zero.
| Provider | Context length | Price in /1M | Price out /1M | Latency p50 (30m, s) | Throughput p50 (30m, tok/s) | Uptime (30m) |
|---|---|---|---|---|---|---|
| Parasailfp8 | 524,288 | $0.350 | $1 | — | — | 100% |
| 524,288 | $0.350 | $1.15 | — | — | — |
Provider data retrieved: 13.11.2026
Related articles
No published articles identify this model yet.