Llama
Meta's open-weight family, and the reason local models took off.
Llama is Meta's open-weight family and the one that made running a serious model on your own hardware normal — most local tooling was built for it first, so support is everywhere. The Llama 4 models are mixture-of-experts and multimodal, with very large context windows, and the line includes Llama Guard, a classifier for filtering input and output rather than a chat model. Meta's newer work ships under a different name, so check the dates on this family before choosing it.
At a glance — Llama 4 Maverick
- Cost
- $0.188 in · $0.653 out per 1M tokensBudget
- Memory
- 1M tokens — about 1,550 pages
- Reads
- Text · Images
- Can do
- Use tools (agents)
- Structured output
- Thinking mode (not supported)
- Good at
- Coding: better than 15% · Agentic work: better than 2%
- Reliability
- 99.86% uptime, last 24h
- Released
- Apr 5, 2025
Advanced details
- API model ID
meta-llama/llama-4-maverick- Max output
- 16K tokens
- Knowledge cutoff
- 2024-08-31
- Tokenizer
- Llama4
- Coding index
- 16.3
- Agentic work index
- 0.6
Providers
The same model, hosted by different companies. OpenRouter picks one per request and falls back to the next if it fails.
| Provider | Input /1M | Output /1M | Cached /1M | Max output | Uptime 24h |
|---|---|---|---|---|---|
| DigitalOcean | $0.188 | $0.653 | — | 16K | 99.86% |
| DeepInfra · base | $0.20 | $0.80 | — | 16K | 99.32% |
| Novita · fp8 | $0.27 | $0.85 | — | 8K | 99.64% |
| Parasail · fp8 | $0.35 | $1.00 | $0.17 | 33K | 99.55% |
| Google · us-east5 | $0.35 | $1.15 | — | 8K | — |
Supported parameters
- frequency_penalty
- logit_bias
- logprobs
- max_tokens
- min_p
- presence_penalty
- repetition_penalty
- response_format
- seed
- stop
- structured_outputs
- temperature
- tool_choice
- tools
- top_k
- top_logprobs
- top_p
Live from OpenRouter, refreshed hourly. Scores from Artificial Analysis.
Key info
- Pricing
- Open source
- Category
- Models
- Best for
- Intermediate
- Made by
- Meta
- Weights
- Open
- Good for
- Local setups, where tooling support is widest