The Orchestrator › Models › Meta Llama
Meta Llama: Meta: Llama 3.3 70B Instruct
The Meta Llama 3.3 multilingual large language model (LLM) is a pretrained and instruction tuned generative model in 70B (text in/text out). The Llama 3.3 instruction tuned text only model...
Specifications
| Provider | Meta Llama |
| Model ID | meta-llama/llama-3.3-70b-instruct |
| Context window | 131K tokens (131,072) |
| Modalities | text → text |
| Tokenizer | Llama3 |
| Router sources | OpenRouter, TrustedRouter |
| Released | 2024-12-06 |
| Tracked since | 2026-11-14 |
| Popularity | Not in the ranked set |
| Reasoning | — |
Pricing (per million tokens)
| Variant | Source | API ID | Input | Output | Context |
|---|---|---|---|---|---|
| standard | OpenRouter | meta-llama/llama-3.3-70b-instruct | $0.71 | $0.71 | 131K |
| standard | TrustedRouter | meta-llama/llama-3.3-70b-instruct | $0.142 | $0.422 | 128K |
Recorded price history
| Date | Input / 1M | Output / 1M | Context |
|---|---|---|---|
| 2026-11-14 | $0.142 | $0.422 | 128K |
| 2026-11-14 | $0.71 | $0.71 | 131K |
Capabilities
Agentic tool useStructured outputsNo content storage (attested)Zero data retention
Trust flags come from TrustedRouter's per-provider attestations.
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