Llama 4 Maverick 17B
llama-4-maverick-17bPricing
List prices at IBM watsonx.ai, in US dollars per million tokens.
| Tier | Input / 1M | Output / 1M | |
|---|---|---|---|
| Standard | $0.371 | $1.48 |
What it costs a month
At IBM watsonx.ai list prices, 30 days.
- Chat assistant5,000 requests a day, 2K in / 0.5K out$223
- RAG over documents2,000 requests a day, 8K in / 0.6K out$232
- Coding agent1,000 requests a day, 40K in / 2K out$534
- Overnight batch20,000 requests a day, 4K in / 0.4K out$1,247
Where to run it
1 host serve Llama 4 Maverick 17B. The comparison is on blended price, 3 parts input to 1 part output.
| Host | In / out per 1M | Model id | |
|---|---|---|---|
IBM watsonx.aiCloud llama-4-maverick-17b | $0.371 / $1.48 | llama-4-maverick-17b |
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
- Features
- Parallel tool calls
- Open weights
- License: Llama Community LicenseRuntimes: 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 IBM watsonx.ai.
Smaller Meta models
- 81% less
- 69% less
Other frontier labs
- 29% less
- 69% less
- 69% less
- 60% less
Open-weight picks
- 2% less
- 19% less
- 26% less
- 31% less
Call it
Using IBM watsonx.ai's API.
from litellm import completion
response = completion(
model="watsonx/llama-4-maverick-17b",
messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)Quick answers
How much does Llama 4 Maverick 17B cost?
On IBM watsonx.ai, Llama 4 Maverick 17B costs $0.371 per million input tokens and $1.48 per million output tokens.
Which APIs offer Llama 4 Maverick 17B?
Llama 4 Maverick 17B runs on 1 API: IBM watsonx.ai.
What is Llama 4 Maverick 17B's context window?
131K tokens, with up to 8K tokens in one reply.
Is Llama 4 Maverick 17B being retired?
No retirement date is scheduled for it on any API we track.
What are cheaper alternatives to Llama 4 Maverick 17B?
Models that cost less and keep most of what it can do: Muse Spark 1.3 Contributor on Meta Model API (81% less), GPT-5.4 Nano on OpenAI (29% less), Claude Haiku 5.5 on Anthropic (69% less) and Inkling Small on DeepInfra (2% less). Savings are on a mix of 3 input tokens to 1 output token.
What is Llama 4 Maverick 17B's API model id?
Use llama-4-maverick-17b with IBM watsonx.ai.
Sources
Raw catalog entry for llama-4-maverick-17b on IBM watsonx.ai
{
"max_input_tokens": 131072,
"max_output_tokens": 8192,
"input_cost_per_token": 3.71e-7,
"output_cost_per_token": 0.000001484,
"litellm_provider": "watsonx",
"mode": "chat",
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_vision": false,
"source": "https://dataplatform.cloud.ibm.com/docs/content/wsj/analyze-data/fm-models.html?context=wx"
}