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 3.3 70B Instruct
- Cost
- $0.10 in · $0.32 out per 1M tokensBudget
- Memory
- 131K tokens — about 200 pages
- Reads
- Text
- Can do
- Use tools (agents)
- Structured output
- Thinking mode (not supported)
- Good at
- Coding: better than 8%
- Reliability
- 99.71% uptime, last 24h
- Released
- Dec 6, 2024
Advanced details
- API model ID
meta-llama/llama-3.3-70b-instruct- Max output
- 16K tokens
- Knowledge cutoff
- 2023-12-31
- Tokenizer
- Llama3
- Coding index
- 11.9
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 | $0.10 | $0.32 | — | 16K | 98.90% |
| Novita · bf16 | $0.135 | $0.40 | — | 11K | 99.51% |
| AkashML · fp8 | $0.20 | $0.52 | $0.10 | 128K | 99.54% |
| Parasail · fp8 | $0.22 | $0.50 | $0.11 | 16K | 99.52% |
| Cloudflare · fp8 | $0.293 | $2.253 | — | 22K | 98.52% |
| SambaNova | $0.45 | $0.90 | — | 3K | 99.25% |
| Groq | $0.59 | $0.79 | $0.295 | 33K | 99.69% |
| CoreWeave · fp16 | $0.71 | $0.71 | $0.71 | 115K | 99.71% |
| Google · us-central1 | $0.72 | $0.72 | — | 8K | — |
| $0.72 | $0.72 | — | 115K | — | |
| Together | $1.04 | $1.04 | — | 2K | 98.05% |
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