← All models
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 pass (400B total). 1,048,576 token context window, maximum output of 16,384 tokens. Higher uptime with 5 providers. Includes independent benchmarks from Artificial Analysis.
chatstreamingvisionjson mode
Details
- Accepts
- text
- Context window
- 1M tokens
Pricing
- Input
- 25 cr / 1M tokens
- Output
- 87 cr / 1M tokens
Prices in credits (1 credit = $0.01).
Data schema
approximateInput
| Field | Type | Description |
|---|---|---|
| promptrequired | string | The text prompt. |
Output
| Field | Type | Description |
|---|---|---|
| text | string | Generated text (choices[0].message.content). |