NovitaAI
Llama 4 Maverick Instruct
Canonical ID:
novita_ai/meta-llama/llama-4-maverick-17b-128e-instruct-fp8
Llama 4 Maverick Instruct is listed under NovitaAI in LLM Directory with pricing, context limits, modalities, and capability metadata for quick comparison.
Overview
- Provider
-
NovitaAI
- Release date
- 2025-04-06
- Last updated
- 2025-04-06
- Input modalities
- text, image
- Output modalities
- text
Pricing and Limits
Token pricing
- Input
- $0.27/1M
- Output
- $0.85/1M
- Cached input
- N/A
Context and output
- Context window
- 1,048,576
- Max output tokens
- 8,192
- Qualified ID
- novita_ai/meta-llama/llama-4-maverick-17b-128e-instruct-fp8
Model Summary
Llama 4 Maverick Instruct is a model listing in the NovitaAI provider catalog. It is categorized under the llama-4-maverick-17b-128e-instruct-fp8 family.
The model supports text, image modalities across input/output paths. Reported context capacity is 1,048,576. Pricing is listed at $0.27/1M input and $0.85/1M output.
More From NovitaAI
Related models from the same provider catalog.
NovitaAI
AutoGLM-Phone-9B-Multilingual
novita_ai/zai-org/autoglm-phone-9b-multilingual
NovitaAI
baichuan-m2-32b
novita_ai/baichuan/baichuan-m2-32b
NovitaAI
deepseek/deepseek-ocr-2
novita_ai/deepseek/deepseek-ocr-2
NovitaAI
DeepSeek-OCR
novita_ai/deepseek/deepseek-ocr
NovitaAI
Deepseek Prover V2 671B
novita_ai/deepseek/deepseek-prover-v2-671b
NovitaAI
DeepSeek R1 0528
novita_ai/deepseek/deepseek-r1-0528
NovitaAI
DeepSeek R1 0528 Qwen3 8B
novita_ai/deepseek/deepseek-r1-0528-qwen3-8b
NovitaAI
DeepSeek R1 Distill LLama 70B
novita_ai/deepseek/deepseek-r1-distill-llama-70b
Same Family: llama-4-maverick-17b-128e-instruct-fp8
Comparable models in the same family across providers.
| Model | Provider | Context | Input | Output | Flags |
|---|---|---|---|---|---|
|
Llama 4 Maverick 17B 128E Instruct
io_net/meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8
|
IO.NET
|
430,000 | $0.15/1M | $0.6/1M |
Tools
|
|
Llama 4 Maverick 17B 128E Instruct FP8
azure/llama-4-maverick-17b-128e-instruct-fp8
|
Azure
|
128,000 | $0.25/1M | $1/1M |
Tools
|
|
Llama 4 Maverick 17B 128E Instruct FP8
abacus/meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8
|
Abacus
|
1,000,000 | $0.14/1M | $0.59/1M |
Tools
|
|
Llama 4 Maverick 17B 128E Instruct FP8
azure_cognitive_services/llama-4-maverick-17b-128e-instruct-fp8
|
Azure Cognitive Services
|
128,000 | $0.25/1M | $1/1M |
Tools
|
|
Llama 4 Maverick 17B 128E Instruct FP8
github_models/meta/llama-4-maverick-17b-128e-instruct-fp8
|
GitHub Models
|
128,000 | $0/1M | $0/1M |
Reasoning
Tools
|
|
Llama-4-Maverick-17B-128E-Instruct-FP8
synthetic/hf:meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8
|
Synthetic
|
524,000 | $0.22/1M | $0.88/1M |
Tools
|