Llama 4 Maverick
by NanoGPT · family llama · listed Sep 2025TV
Open multimodal Llama model for strong reasoning and fast responses
Current rates USD per 1M tokens
Input$0.18
Output$0.80
Cache read—
Cache write—
Against the market
On the record
- Model id
meta-llama/llama-4-maverick- Context window
- 1.0M tokens
- Max output
- 66K tokens
- Input modalities
- text, image
- Output modalities
- text
- Reasoning
- no
- Tool calls
- yes
- Open weights
- no
- Knowledge cutoff
- —
- Released
- 2025-09-05
- Last updated
- 2025-09-05
- Provider docs
- docs.nano-gpt.com
Back of the envelope
≈
Also listed at
- Vercel AI Gatewayfree in · free out
- Cortecs$0.124 in · $0.603 out
- Helicone$0.15 in · $0.60 out
- Kilo Gateway$0.15 in · $0.60 out
- OpenRouter$0.15 in · $0.60 out
- DigitalOcean$0.25 in · $0.87 out