The Orchestrator › Models › Meta Llama
Meta Llama: Meta: Llama 4 Maverick
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
| Provider | Meta Llama |
| Model ID | meta-llama/llama-4-maverick |
| Context window | 524K tokens (524,288) |
| Modalities | text + image → text |
| Tokenizer | Llama4 |
| Router sources | OpenRouter, TrustedRouter |
| Released | 2025-04-05 |
| 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-4-maverick | $0.35 | $1.00 | 524K |
| standard | TrustedRouter | meta-llama/llama-4-maverick | $0.369 | $1.06 | 524K |
Recorded price history
| Date | Input / 1M | Output / 1M | Context |
|---|---|---|---|
| 2026-11-14 | $0.369 | $1.06 | 524K |
| 2026-11-14 | $0.35 | $1.00 | 524K |
Capabilities
Vision (image input)Agentic tool useStructured outputs256K+ context windowNo content storage (attested)Zero data retention
Trust flags come from TrustedRouter's per-provider attestations.
Supported parameters
frequency_penalty, logit_bias, logprobs, max_tokens, presence_penalty, repetition_penalty, response_format, seed, stop, structured_outputs, temperature, tool_choice, tools, top_k, top_logprobs, top_p