Llama 4 Maverick API pricing
Meta · Budget price tier · Llama 4 · released 2025-04. Prices in USD per 1 million tokens. Data snapshot: 2026-11-12.
A support ticket workload of 100K requests a month costs $102.50 on Llama 4 Maverick; the next cheaper model in the Budget price tier for this workload, DeepSeek V3 0324, does it for $100.50. The price we quote for Llama 4 Maverick has changed 5 times since 2026-08-15, most recently on 2026-11-05 when the quoted host changed (+56.9%); it is now the 118th cheapest of 160 models in the Budget price tier. None of its 2 hosts undercuts the price we quote. It is rated a stable release but does not meet all four criteria of the FinOps Friendly badge.
- Input: $0.35 per 1M tokens
- Output: $1.00 per 1M tokens
- Batch API (in/out): Not published
- Prompt-cache read: $0.17 per 1M tokens
- Context window: 524K tokens
- Arena ELO: 1287 as of 2026-11-08
Available on
AWS Bedrock, Azure AI Foundry, Google Vertex, OpenRouter
AWS Bedrock regions: us-east-1, us-east-2, us-west-2
Curated by hand; check with the provider before committing.
Market position
On blended price ($0.805 per 1M tokens at 30% input, 70% output) it is cheaper than 26% of models in the Budget price tier: 118th cheapest of 160. Across every price tier it is cheaper than 61% of priced text models in the catalogue: 118th cheapest of 303. Its Arena ELO of 1287 ranks 138th of the 160 models that carry one, above 14% of them. With an Arena score of 1287, Llama 4 Maverick sits below OptimNow's lowest working quality threshold, Standard (Arena 1420+), so the quality-bar method would not shortlist it for any of the 8 use cases the table prices. Each threshold is a distance below the best ranked model, which scores 1530 on Arena scores as of 8 Nov 2026.
Licence, size and capabilities
Llama 4 Maverick is open weights, which is not the same as open source: the weights are published, but under Llama 4, a licence that restricts some uses. Read it before self-hosting commercially. Its published size is 400B parameters. Listed capabilities: Text, Vision, Agents. Filling its 524K context window once costs $0.1834 in input tokens at list price.
Pricing by host
A host is a company that runs the model and sells it by the token: the model maker, a cloud platform like Amazon Bedrock, Azure or Vertex, or an independent host. One model, several hosts, and often several prices. This model is sold by 2 different hosts. The price we quote elsewhere on this page is marked. We quote one host's rate so that models stay comparable; it is not a recommendation to buy there.
The price we quote is already the cheapest of the 2 hosts: Parasail at $0.35 input / $1.00 output per 1M tokens. It serves a quantized fp8 build, which is not the same product as the full-precision model. The dearest, Google, charges 1.1x the cheapest.
| Host | Input $/1M | Output $/1M | Precision |
|---|---|---|---|
| Parasail (price we quote) | $0.35 | $1.00 | fp8 |
| $0.35 | $1.15 | not declared |
List prices as published on 2026-11-12, via OpenRouter. Negotiated rates, committed-use discounts and provisioned capacity are not shown.
Monthly cost at 100K requests, by business use case
From the after-discounts figure (prompt caching on the cached input share, batch API for async workloads, only where Meta publishes those rates), which assumes you implement both, to the list price. One figure means no discount is published.
| Use case | Tokens (in/out) | Monthly (after discounts – list) |
|---|---|---|
| Support Ticket | 1,500 / 500 | $86 – $102 |
| Knowledge Q&A | 2,000 / 800 | $125 – $150 |
| Meeting Summary | 10,000 / 1,200 | $452 – $470 |
| Marketing Content | 2,500 / 1,800 | $258 – $268 |
| Coding Task | 3,000 / 2,000 | $278 – $305 |
| Invoice Processing | 1,500 / 600 | $104 – $112 |
| Call Summary | 2,000 / 700 | $136 – $140 |
| Agent Workflow | 6,000 / 3,000 | $434 – $510 |
Price history
Llama 4 Maverick has been in our daily price archive since tracking began on 2026-08-15, when it listed at $0.20 input / $0.80 output per 1M tokens. The price we quote has changed 5 times since then, 4 of them a change of quoted host rather than a repricing. The latest change, on 2026-11-05, was +56.9% on the blended price (30% input, 70% output), to $0.35 input / $1.00 output (quoted host changed, not a repricing). Net of all changes, the blended price is +29.8% against 2026-08-15.
| Date | Old price (in / out) | New price (in / out) | Blended change |
|---|---|---|---|
| 2026-11-05 | $0.1875 / $0.6525 | $0.35 / $1.00 | +56.9% (quoted host changed, not a repricing) |
| 2026-09-22 | $0.20 / $0.80 | $0.1875 / $0.6525 | -17.3% (quoted host changed, not a repricing) |
| 2026-09-21 | $0.1875 / $0.6525 | $0.20 / $0.80 | +20.9% (quoted host changed, not a repricing) |
| 2026-09-15 | $0.20 / $0.696 | $0.1875 / $0.6525 | -6.3% |
| 2026-08-31 | $0.20 / $0.80 | $0.20 / $0.696 | -11.7% (quoted host changed, not a repricing) |
Alternatives to Llama 4 Maverick
4 of the 4 comparable models below cost less than Llama 4 Maverick: Gemma 3 4B undercuts it by 89%, and scores 4 Arena points higher.
- Next cheaper model in the Budget price tier: Qwen3 Next 80B A3B Instruct (Alibaba) at $0.797 blended, 1% less.
- Next more expensive: GLM 4.5 Air (Zhipu) at $0.83 blended, 3% more.
The nearest models in the Budget price tier on Arena ELO, each with its blended price and score difference against Llama 4 Maverick.
- gpt-oss-20b (OpenAI): $0.03 in / $0.13 out per 1M, Arena ELO 1288 (88% cheaper, 1 ELO point higher)
- GPT-4o-mini (OpenAI): $0.15 in / $0.60 out per 1M, Arena ELO 1286 (42% cheaper, 1 ELO point lower)
- GPT-4.1 Nano (OpenAI): $0.10 in / $0.40 out per 1M, Arena ELO 1285 (61% cheaper, 2 ELO points lower)
- Gemma 3 4B (Google): $0.05 in / $0.10 out per 1M, Arena ELO 1291 (89% cheaper, 4 ELO points higher)
- Cheapest within 15 Arena points: Gemma 3 4B (Google), 89% cheaper, 4 ELO points higher, out of 9 models in that band.
- Highest Arena ELO within 20% of this price: MiMo-V2.6-Pro (Xiaomi), 8% cheaper, 205 ELO points higher, out of 22 models in that price band.
Llama 4 Maverick head to head
Other models from Meta
The 8 nearest to Llama 4 Maverick in price, of 16 other Meta models in the catalogue. Prices per 1M tokens, input then output.
- Llama 3.2 3B Instruct: $0.05 / $0.33
- Muse Ember: $0.10 / $0.50
- Llama 3.3 70B Instruct: $0.71 / $0.71
- Llama 3.1 70B Instruct: $0.72 / $0.72
- Muse Glimmer 30B: $0.30 / $1.20
- Muse Spark 1.1: $1.25 / $4.25
- Muse Spark 1.2: $1.25 / $4.25
- Muse Spark 1.3: $1.25 / $4.25
Common questions about Llama 4 Maverick pricing
- How much does Llama 4 Maverick cost?
- Llama 4 Maverick costs $0.35 per 1M input tokens and $1.00 per 1M output tokens at Parasail, the host whose rate we quote. Parasail serves a quantized fp8 build, which is not the same product as the full-precision model. Prices as listed on 2026-11-12.
- Which host is cheapest for Llama 4 Maverick?
- The price we quote is already the cheapest of the 2 hosts: Parasail at $0.35 input / $1.00 output per 1M tokens. It serves a quantized fp8 build, which is not the same product as the full-precision model. The dearest, Google, charges 1.1x the cheapest. Host rates as listed on 2026-11-12.
- Does Llama 4 Maverick offer batch or cached pricing?
- Yes, for prompt caching only. Cache reads cost $0.17 per 1M tokens, as listed on 2026-11-12. No batch pricing is published.
- What would Llama 4 Maverick cost per month?
- With the Support Ticket profile (1,500 input and 500 output tokens per request), 100,000 requests a month cost about $102 on Llama 4 Maverick at the list price quoted on 2026-11-12.
- Can Llama 4 Maverick be self-hosted?
- Yes, within the terms of its licence. Llama 4 Maverick is open weights, which is not the same as open source: the weights are published, but under Llama 4, a licence that restricts some uses. Read it before self-hosting commercially.
- Has the price of Llama 4 Maverick changed?
- Llama 4 Maverick has been in our daily price archive since tracking began on 2026-08-15, when it listed at $0.20 input / $0.80 output per 1M tokens. The price we quote has changed 5 times since then, 4 of them a change of quoted host rather than a repricing. The latest change, on 2026-11-05, was +56.9% on the blended price (30% input, 70% output), to $0.35 input / $1.00 output (quoted host changed, not a repricing). Net of all changes, the blended price is +29.8% against 2026-08-15.
Its weights are published, which changes what you may run yourself: the cost gap between open weights and proprietary APIs.
These are list prices. Your real cost also depends on caching and batching, negotiated discounts, marketplace agreements, and the contracts you already have. OptimNow audits exactly that.
Build the business case · Get a FinOps review
LLM pricing · Models by maker · Cloud compute pricing · Compare models · Price barometer · FinOps guides · API and MCP server