Llama 4 Maverick API pricing.
Llama 4 Maverick by Meta costs $0.35 per million input tokens and $1.00 per million output tokens, with a 524K-token context window. That puts it in the budget range of the models we track. A support chatbot handling 10,000 conversations a month would cost about $10.25 a month in API fees.
Price
What Llama 4 Maverick costs per token
List prices, checked every hour. Blended assumes three input tokens for every output token. This model sits in the budget range of the models we track.
| Model | Provider | Input / 1M | Output / 1M | Blended / 1M | Context |
|---|---|---|---|---|---|
| Llama 4 Maverick | Meta | $0.35 | $1.00 | $0.513 | 524K |
Specs
What Llama 4 Maverick can do
From Llama 4 Maverick's entry in the OpenRouter model catalog.
- Reads
- text and images
- Writes
- text
- Context window
- 524K tokens
- Longest answer
- 33K tokens
- Tool calling
- Yes: it can call functions and APIs you define
- Structured output
- Yes: answers can follow a JSON schema
- Reasoning
- Not listed
- Cached input
- $0.17 per 1M tokens (51% off the input price)
- Open weights
- Yes: you can also run it on your own servers
- Knowledge cutoff
- August 2024
Monthly cost
What common workloads cost on Llama 4 Maverick
API fees only, at list price. The assumptions are shown, so you can scale them to your own volume.
Customer support chatbot
$10.25 / month
10,000 conversations a month, ~1,500 in and ~500 out each: 15M input and 5M output tokens.
Knowledge-base Q&A (RAG)
$36.00 / month
20,000 questions a month, ~4,000 in and ~400 out each: 80M input and 8M output tokens.
Document summaries and extraction
$10.00 / month
2,000 documents a month, ~12,000 in and ~800 out each: 24M input and 1.6M output tokens.
Coding assistant for a team of 10
$16.50 / month
10 developers a month, 3.0M in and 0.6M out each: 30M input and 6M output tokens.
Hosting, a vector database, monitoring and the build itself are extra. The free StackLift estimate adds them for your exact scope.
Per request
What one request costs on Llama 4 Maverick
A request costs its input tokens times the input price plus its output tokens times the output price. A typical assistant turn of 2,000 input and 500 output tokens on Llama 4 Maverick: 2,000 × $0.35 ÷ 1M + 500 × $1.00 ÷ 1M = $0.0012.
| Request | Input / output tokens | One request | 1,000 requests |
|---|---|---|---|
| Short chat reply | 500 / 200 | $0.0004 | $0.375 |
| Typical assistant turn | 2,000 / 500 | $0.0012 | $1.20 |
| Long document task | 20,000 / 1,500 | $0.0085 | $8.50 |
As you grow
Llama 4 Maverick cost at ten times less and ten times more
The same workloads at a tenth and at ten times the volume, at Llama 4 Maverick's list price.
| Workload | A tenth | Typical | Ten times |
|---|---|---|---|
| Customer support chatbot | $1.021,000 conversations | $10.2510,000 conversations | $102.5100,000 conversations |
| Knowledge-base Q&A (RAG) | $3.602,000 questions | $36.0020,000 questions | $360200,000 questions |
| Document summaries and extraction | $1.00200 documents | $10.002,000 documents | $10020,000 documents |
Fit
When Llama 4 Maverick is the right choice
Llama 4 Maverick is priced for volume: classification, extraction, routing and short replies, where thousands of requests a day must stay cheap. Hard reasoning may need a larger model for some steps.
Its 524K-token context window fits long contracts, codebases or document sets in one request, though sending that much text on every call raises the bill quickly.
Llama 4 Maverick reads images as well as text and can call tools and APIs and return structured JSON, so it can drive agents that act in your systems.
Its weights are published, so Llama 4 Maverick can also run on your own servers when data must stay in-house; the API price above is for hosted use.
Many products mix models: a cheaper one for simple steps and a stronger one where quality matters. Test a shortlist on your own examples before you commit.
Save
Ways to pay less for Llama 4 Maverick
1. Cache repeated instructions
Llama 4 Maverick charges $0.17 per million cached input tokens instead of $0.35. A 4,000-token system prompt sent with 10,000 requests a month costs $14.00 at the list price and about $6.80 when cached.
2. Route by difficulty
Llama 4 Scout costs 71% less per token than Llama 4 Maverick. Send simple requests there and keep Llama 4 Maverick for the steps that need it.
3. Batch what can wait
Overnight or bulk jobs often qualify for batch pricing, at a lower rate than live requests.
4. Ask for shorter answers
Output costs 2.9 times as much as input on Llama 4 Maverick, so a tight answer format (bullet points, JSON, a word limit) cuts the bill more than a shorter prompt.
Alternatives
Models priced closest to Llama 4 Maverick
From other providers, nearest on blended price. Quality and speed differ by task: test the shortlist on your own examples.
| Model | Provider | Input / 1M | Output / 1M | Blended / 1M | Context |
|---|---|---|---|---|---|
| Llama 4 Maverick | Meta | $0.35 | $1.00 | $0.513 | 524K |
| DeepSeek V3.1 Terminus | DeepSeek | $0.27 | $1.00 | $0.453 | 164K |
| DeepSeek V3 | DeepSeek | $0.257 | $1.03 | $0.45 | 164K |
| DeepSeek V3.1 | DeepSeek | $0.25 | $0.95 | $0.425 | 164K |
| Mistral Small 3.1 24B | Mistral | $0.351 | $0.555 | $0.402 | 128K |
| Qwen3.8 27B | Qwen | $0.035 | $1.50 | $0.401 | 1M |
Meta
Other Meta models
The same provider's newest models, for a quicker or more capable option.
| Model | Provider | Input / 1M | Output / 1M | Blended / 1M | Context |
|---|---|---|---|---|---|
| Llama 4 Scout | Meta | $0.10 | $0.30 | $0.15 | 1.3M |
| Llama 3.3 70B Instruct | Meta | $0.71 | $0.71 | $0.71 | 131K |
| Llama 3.2 3B Instruct | Meta | $0.05 | $0.33 | $0.12 | 131K |
Questions about Llama 4 Maverick pricing
How much does Llama 4 Maverick cost per 1,000 tokens?
$0.0003 per 1,000 input tokens and $0.0010 per 1,000 output tokens, from the list price of $0.35 and $1.00 per million.
Is Llama 4 Maverick cheaper than DeepSeek V3.1 Terminus?
No, on list price. Llama 4 Maverick averages $0.513 per million tokens (3 parts input to 1 output) against $0.453 for DeepSeek V3.1 Terminus. A pricier model can still cost less overall if it needs fewer retries or shorter prompts.
What is Llama 4 Maverick's context window?
524K tokens: the most text the model reads and writes in one request. Long documents beyond that are split, or retrieved in parts with RAG.
How much would a chatbot cost on Llama 4 Maverick?
About $10.25 a month for 10,000 conversations a month, ~1,500 in and ~500 out each. Caching repeated instructions and routing simple questions to a cheaper model lower it further.
Does Llama 4 Maverick support tool calling?
Yes. Llama 4 Maverick can call functions and APIs you describe to it, which is what lets an AI agent look up data or take actions. It can also return answers that follow a JSON schema.
Can Llama 4 Maverick read images or documents?
Yes. Besides text, Llama 4 Maverick reads images.
How long can Llama 4 Maverick's answers be?
Up to 33K tokens per answer (about 25,000 words), within a 524K tokens context window.
Does Llama 4 Maverick have prompt caching?
Yes. Input read from the cache costs $0.17 per million tokens, 51% less than the $0.35 list price, which suits long system prompts and shared context.
How do I estimate the AI cost of my own product?
Count the requests a month and the tokens in and out of each, then multiply by the prices here. StackLift's free estimate does this for your exact scope, alongside the cost to build it.
Build with it
Scope a product on Llama 4 Maverick
Pick your features and integrations; the estimate returns the build cost, timeline and team, and the model's monthly running cost. Free, no signup.