Llama4 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…
llama4-maverickReleased 5 Apr 2025 (Apr 2025)Pricing
List prices at Snowflake, in US dollars per million tokens.
| Tier | Input / 1M | Output / 1M | |
|---|---|---|---|
| Standard | $0.24 | $0.97 |
What it costs a month
At Snowflake list prices, 30 days.
- Chat assistant5,000 requests a day, 2K in / 0.5K out$145
- RAG over documents2,000 requests a day, 8K in / 0.6K out$150
- Coding agent1,000 requests a day, 40K in / 2K out$346
- Overnight batch20,000 requests a day, 4K in / 0.4K out$809
Where to run it
1 host serve Llama4 Maverick. The comparison is on blended price, 3 parts input to 1 part output.
| Host | In / out per 1M | Model id | |
|---|---|---|---|
SnowflakeCloud llama4-maverick | $0.24 / $0.97 | llama4-maverick |
Capabilities
Core
- Streaming
- Function calling
- JSON mode
- Structured outputs
Multimodal
- Vision
- Image input
- Audio
- Image generation
- Video
Advanced
- Reasoning
- Tool calling
- MCP
- Prompt caching
- Batch API
- Embeddings
- Takes in
- Text
- Produces
- Text
- Open weights
- License: Llama Community LicenseRuns in about 963.8 GB of GPU memoryRuntimes: Ollama, TGI, llama.cpp, vLLM
Cheaper alternatives
Current models that cost less and keep most of what this one can do: tools, vision, reasoning, structured output, caching and enough context.
Same model, cheaper host
No host sells it for less than Snowflake.
Smaller Meta models
- 70% less
- 53% less
Other frontier labs
- 53% less
- 53% less
- 38% less
Open-weight picks
- 7% less
- 12% less
- 17% less
- 38% less
Model line
Newer and older versions, at each lab's own price.
- Apr 2025Llama 4 MaverickLatest$0.20 / $0.60
- Apr 2025Llama4 MaverickThis page$0.24 / $0.97
Call it
Using Snowflake's API.
from litellm import completion
response = completion(
model="snowflake/llama4-maverick",
messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)Quick answers
How much does Llama4 Maverick cost?
On Snowflake, Llama4 Maverick costs $0.24 per million input tokens and $0.97 per million output tokens.
Which APIs offer Llama4 Maverick?
Llama4 Maverick runs on 1 API: Snowflake.
What is Llama4 Maverick's context window?
128K tokens, with up to 16K tokens in one reply.
Is Llama4 Maverick being retired?
No retirement date is scheduled for it on any API we track.
Is there a newer version of Llama4 Maverick?
Yes. Llama 4 Maverick is the newest model in this line, released on 5 Apr 2025.
What are cheaper alternatives to Llama4 Maverick?
Models that cost less and keep most of what it can do: Muse Spark 1.3 Contributor on Meta Model API (70% less), Claude Haiku 5.5 on Anthropic (53% less), GPT-6 Luna on OpenAI (53% less) and MiniMax M3 on EmpirioLabs AI (7% less). Savings are on a mix of 3 input tokens to 1 output token.
When was Llama4 Maverick released?
Meta released it on 5 Apr 2025.
What is Llama4 Maverick's API model id?
Use llama4-maverick with Snowflake.
Sources
Raw catalog entry for llama4-maverick on Snowflake
{
"max_input_tokens": 128000,
"max_output_tokens": 16384,
"input_cost_per_token": 2.4e-7,
"output_cost_per_token": 9.7e-7,
"litellm_provider": "snowflake",
"mode": "chat",
"supports_function_calling": true,
"supports_system_messages": true
}