Meta
Llama 4 Maverick
Released 2025-04-05 · Knowledge up to 2024-08-31
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...
You send / 1M
$0.188
tokens in
It replies / 1M
$0.652
tokens out
Memory
524K
tokens it can read at once
Typical request
$0.0006
1,000 words in, 400 out
Data privacy
No training or retention: Yes. At least one provider serves it with zero data retention.
| Provider | You send / 1M | It replies / 1M | Uptime | Privacy policy |
|---|---|---|---|---|
| DigitalOcean | $0.188 | $0.652 | 100% | Read |
| Parasail · fp8 | $0.350 | $1.00 | 100% | Read |
| $0.350 | $1.15 | n/a | Read |
Based on OpenRouter and Vercel AI Gateway data. Confirm terms with the provider before sending sensitive data.
What it can do
- Reads: text, image
- Writes: text
- Reasoning: No
- Tool calling: Yes
- Longest reply: 16K tokens
- Repeated text is billed at $0.050 per 1M (prompt caching)
- Intelligence score: 9.3 / 100 (Artificial Analysis)
Similar models
- Qwen3 VL 30B A3B InstructQwen · $0.150 in / $0.600 out per 1M
- GPT-4o-miniOpenAI · $0.150 in / $0.600 out per 1M
- GPT-4o-mini (2024-07-18)OpenAI · $0.150 in / $0.600 out per 1M
- Qwen3 VL 8B InstructQwen · $0.250 in / $0.750 out per 1M
- Mistral Small 3.1 24BMistral · $0.351 in / $0.555 out per 1M
- Qwen2.5 VL 72B InstructQwen · $0.800 in / $1.00 out per 1M
Appears in
Top No-Training AI ModelsTop No-Training Zero Data Retention AI ModelsTop No-Training Zero Data Retention Cheap AI ModelsTop No-Training Zero Data Retention Vision AI ModelsTop No-Training Zero Data Retention Tool-Calling AI ModelsTop No-Training Cheap AI ModelsTop No-Training Cheap Vision AI ModelsTop No-Training Cheap Tool-Calling AI Models