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 3.1 70B Instruct
- Cost
- $0.40 in · $0.40 out per 1M tokensBudget
- Memory
- 131K tokens — about 200 pages
- Reads
- Text
- Can do
- Use tools (agents)
- Structured output
- Thinking mode (not supported)
- Reliability
- 99.83% uptime, last 24h
- Released
- Jul 23, 2024
Advanced details
- API model ID
meta-llama/llama-3.1-70b-instruct- Max output
- 16K tokens
- Knowledge cutoff
- 2023-12-31
- Tokenizer
- Llama3
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 |
|---|---|---|---|---|---|
| DeepInfra · turbo | $0.40 | $0.40 | — | 16K | 97.18% |
| Amazon Bedrock | $0.72 | $0.72 | — | 8K | 99.83% |
Supported parameters
- frequency_penalty
- logit_bias
- max_tokens
- min_p
- presence_penalty
- repetition_penalty
- response_format
- seed
- stop
- structured_outputs
- temperature
- tool_choice
- tools
- top_k
- top_p
Live from OpenRouter, refreshed hourly.
Key info
- Pricing
- Open source
- Category
- Models
- Best for
- Intermediate
- Made by
- Meta
- Weights
- Open
- Good for
- Local setups, where tooling support is widest