impulse

Llama 4 Maverick 17B

Open weights
API id llama-4-maverick-17b
Input / 1M
$0.371
at IBM watsonx.ai
Output / 1M
$1.48
at IBM watsonx.ai
Context window
131K
tokens
Max output
8K
tokens per reply
Hosts
1
1 listings
Released
-
date not published

Pricing

List prices at IBM watsonx.ai, in US dollars per million tokens.

TierInput / 1MOutput / 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
Use your own numbers

Where to run it

1 host serve Llama 4 Maverick 17B. The comparison is on blended price, 3 parts input to 1 part output.

HostIn / out per 1M
llama-4-maverick-17b
$0.371 / $1.48

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 License
Runtimes: 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

Other frontier labs

  • GPT-5.4 Nano
    OpenAI · on OpenAI
    $0.20 / $1.25
    Has every key capability
    29% less
  • Claude Haiku 5.5
    Anthropic · on Anthropic
    $0.10 / $0.50
    Has every key capability
    69% less
  • GPT-6 Luna
    OpenAI · on OpenAI
    $0.10 / $0.50
    Has every key capability
    69% less
  • GPT-4o Mini
    OpenAI · on OpenAI
    $0.15 / $0.60
    Has every key capability
    60% less

Open-weight picks

  • Inkling Small
    Independent · on DeepInfra
    $0.45 / $1.20
    Has every key capability
    2% less
  • DeepSeek Flash
    DeepSeek · on DeepSeek
    $0.30 / $1.20
    Has every key capability
    19% less
  • Qwen3.7 Plus
    Alibaba Qwen · on Replicate
    $0.276 / $1.10
    Has every key capability
    26% less
  • GLM 4 6v
    Zhipu AI · on Novita AI
    $0.30 / $0.90
    Has every key capability
    31% less

Call it

Using IBM watsonx.ai's API.

Python
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"
}