← Models

Meta · current

Llama 4 Maverick 17B 128E Instruct FP8

Llama 4 Maverick 17B 128E Instruct FP8 is attributed to Meta in the catalog. It accepts text and image input and produces text output. Reported capabilities include tool calling.

Compare model

Modalities

Hosted provider token rates

$0.24 / $0.97

USD per 1M input / output tokens · Vercel AI Gateway

Context

1M

Released

2025-04-05

Knowledge cutoff

Aug 2024

No recent lab-operated provider rate is available. Showing the third-party host with the lowest input rate + ¼ output rate. This is one offering, not an average; other providers, modalities, tiers, and fees may differ.

Where to use it

6 observed offerings · token prices in USD per million where available

Estimate your workload cost
Vercel AI Gateway

meta/llama-4-maverick

current

Input

$0.24

Output

$0.97

Cache

—

Context

128K

Max output

8K
Reasoning
No
Tool calling
Yes
Structured output
Unknown
Temperature
Yes

Recent price

Azure

llama-4-maverick-17b-128e-instruct-fp8

current

Input

$0.25

Output

$1

Cache

—

Context

1M

Max output

16K
Reasoning
No
Tool calling
Yes
Structured output
Unknown
Temperature
Yes

Recent price

Llama

llama-4-maverick-17b-128e-instruct-fp8

deprecated

Input

$0

Output

$0

Cache

—

Context

128K

Max output

4K
Reasoning
No
Tool calling
Yes
Structured output
Unknown
Temperature
Yes

Historical price

watsonx.ai

meta-llama/llama-4-maverick-17b-128e-instruct-fp8

current

Input

$0.371

Output

$1.484

Cache

—

Context

131K

Max output

8K
Reasoning
No
Tool calling
Yes
Structured output
Unknown
Temperature
Yes

Recent price

Azure Cognitive Services

llama-4-maverick-17b-128e-instruct-fp8

current

Input

$0.25

Output

$1

Cache

—

Context

1M

Max output

16K
Reasoning
No
Tool calling
Yes
Structured output
Unknown
Temperature
Yes

Recent price

Deep Infra

meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8

deprecated

Input

$0.20

Output

$0.80

Cache

—

Context

1.05M

Max output

16K
Reasoning
No
Tool calling
No
Structured output
Yes
Temperature
Yes

Not a current offering

Limits and capabilities reflect each provider’s listed offering. Unknown means support was not reported.

Capabilities and limits

Input
text, image
Output
text
Max output
16K
Weights
Open (source-reported)
Release
2025-04-05
Knowledge cutoff
Aug 2024
Family
llama

Tool calling · Vision

Provider-specific limits and support can differ.

Plan a model evaluation

Evaluate quality and latency on examples from your intended use before choosing a model.

Explore available evidence

Models to compare

Candidates match reported specifications; they are not tested replacements.

Model and price history

Latest recorded change: price change · 2026-10-22

Model changes (4)
  • price change · 2026-10-22
    {
      "before": {
        "input": "0.00000000",
        "output": "0.00000000",
        "provider": "Vercel AI Gateway"
      },
      "after": {
        "input": 0.24,
        "output": 0.97,
        "provider": "Vercel AI Gateway"
      }
    }
  • source refresh · 2026-10-21
    {
      "before": {
        "knowledge_cutoff_reported": null
      },
      "after": {
        "knowledge_cutoff_reported": "2024-08"
      }
    }
  • source refresh · 2026-10-12
    {
      "before": {
        "knowledge_cutoff_reported": null
      },
      "after": {
        "knowledge_cutoff_reported": "2024-08"
      }
    }
  • source refresh · 2026-10-07
    {
      "before": {
        "status": "current"
      },
      "after": {
        "status": "deprecated"
      }
    }
Price history (220 observations)
DateProviderInput / output
2026-11-02Azure Cognitive Services$0.25 / $1
2026-11-02Azure$0.25 / $1
2026-11-02Vercel AI Gateway$0.24 / $0.97
2026-11-02watsonx.ai$0.371 / $1.484
2026-11-02Deep Infra$0.20 / $0.80
2026-11-01Vercel AI Gateway$0.24 / $0.97
2026-11-01Azure$0.25 / $1
2026-11-01Azure Cognitive Services$0.25 / $1
2026-11-01watsonx.ai$0.371 / $1.484
2026-11-01Deep Infra$0.20 / $0.80
2026-10-31Azure$0.25 / $1
2026-10-31Vercel AI Gateway$0.24 / $0.97
2026-10-31watsonx.ai$0.371 / $1.484
2026-10-31Azure Cognitive Services$0.25 / $1
2026-10-31Deep Infra$0.20 / $0.80
2026-10-30Azure$0.25 / $1
2026-10-30Vercel AI Gateway$0.24 / $0.97
2026-10-30watsonx.ai$0.371 / $1.484
2026-10-30Azure Cognitive Services$0.25 / $1
2026-10-30Deep Infra$0.20 / $0.80
2026-10-29Vercel AI Gateway$0.24 / $0.97
2026-10-29watsonx.ai$0.371 / $1.484
2026-10-29Azure$0.25 / $1
2026-10-29Azure Cognitive Services$0.25 / $1
2026-10-29Deep Infra$0.20 / $0.80
2026-10-28Vercel AI Gateway$0.24 / $0.97
2026-10-28Azure Cognitive Services$0.25 / $1
2026-10-28watsonx.ai$0.371 / $1.484
2026-10-28Azure$0.25 / $1
2026-10-28Deep Infra$0.20 / $0.80
2026-10-27Azure$0.25 / $1
2026-10-27watsonx.ai$0.371 / $1.484
2026-10-27Vercel AI Gateway$0.24 / $0.97
2026-10-27Azure Cognitive Services$0.25 / $1
2026-10-27Deep Infra$0.20 / $0.80
2026-10-27Azure$0.25 / $1
2026-10-27Azure Cognitive Services$0.25 / $1
2026-10-27watsonx.ai$0.371 / $1.484
2026-10-27Vercel AI Gateway$0.24 / $0.97
2026-10-27Deep Infra$0.20 / $0.80
2026-10-27Azure$0.25 / $1
2026-10-27Vercel AI Gateway$0.24 / $0.97
2026-10-27watsonx.ai$0.371 / $1.484
2026-10-27Azure Cognitive Services$0.25 / $1
2026-10-27Deep Infra$0.20 / $0.80
2026-10-27watsonx.ai$0.371 / $1.484
2026-10-27Vercel AI Gateway$0.24 / $0.97
2026-10-27Azure Cognitive Services$0.25 / $1
2026-10-27Azure$0.25 / $1
2026-10-27Deep Infra$0.20 / $0.80
2026-10-26Vercel AI Gateway$0.24 / $0.97
2026-10-26watsonx.ai$0.371 / $1.484
2026-10-26Azure$0.25 / $1
2026-10-26Azure Cognitive Services$0.25 / $1
2026-10-26Deep Infra$0.20 / $0.80
2026-10-25watsonx.ai$0.371 / $1.484
2026-10-25Vercel AI Gateway$0.24 / $0.97
2026-10-25Azure Cognitive Services$0.25 / $1
2026-10-25Azure$0.25 / $1
2026-10-25Deep Infra$0.20 / $0.80
2026-10-24watsonx.ai$0.371 / $1.484
2026-10-24Azure Cognitive Services$0.25 / $1
2026-10-24Azure$0.25 / $1
2026-10-24Vercel AI Gateway$0.24 / $0.97
2026-10-24Deep Infra$0.20 / $0.80
2026-10-24Azure$0.25 / $1
2026-10-24watsonx.ai$0.371 / $1.484
2026-10-24Azure Cognitive Services$0.25 / $1
2026-10-24Vercel AI Gateway$0.24 / $0.97
2026-10-24Deep Infra$0.20 / $0.80
2026-10-24Vercel AI Gateway$0.24 / $0.97
2026-10-24Azure Cognitive Services$0.25 / $1
2026-10-24watsonx.ai$0.371 / $1.484
2026-10-24Azure$0.25 / $1
2026-10-24Deep Infra$0.20 / $0.80
2026-10-23Azure Cognitive Services$0.25 / $1
2026-10-23Azure$0.25 / $1
2026-10-23Vercel AI Gateway$0.24 / $0.97
2026-10-23watsonx.ai$0.371 / $1.484
2026-10-23Deep Infra$0.20 / $0.80
2026-10-23Azure Cognitive Services$0.25 / $1
2026-10-23Vercel AI Gateway$0.24 / $0.97
2026-10-23watsonx.ai$0.371 / $1.484
2026-10-23Azure$0.25 / $1
2026-10-23Deep Infra$0.20 / $0.80
2026-10-23Azure Cognitive Services$0.25 / $1
2026-10-23Vercel AI Gateway$0.24 / $0.97
2026-10-23watsonx.ai$0.371 / $1.484
2026-10-23Azure$0.25 / $1
2026-10-23Deep Infra$0.20 / $0.80
2026-10-23Azure$0.25 / $1
2026-10-23Vercel AI Gateway$0.24 / $0.97
2026-10-23watsonx.ai$0.371 / $1.484
2026-10-23Azure Cognitive Services$0.25 / $1
2026-10-23Deep Infra$0.20 / $0.80
2026-10-23Vercel AI Gateway$0.24 / $0.97
2026-10-23Azure$0.25 / $1
2026-10-23watsonx.ai$0.371 / $1.484
2026-10-23Azure Cognitive Services$0.25 / $1
2026-10-23Deep Infra$0.20 / $0.80
2026-10-22Vercel AI Gateway$0.24 / $0.97
2026-10-22Azure$0.25 / $1
2026-10-22Llama$0 / $0
2026-10-22Azure Cognitive Services$0.25 / $1
2026-10-22watsonx.ai$0.371 / $1.484
2026-10-22Deep Infra$0.20 / $0.80
2026-10-21watsonx.ai$0.371 / $1.484
2026-10-21Azure Cognitive Services$0.25 / $1
2026-10-21Llama$0 / $0
2026-10-21Azure$0.25 / $1
2026-10-21Vercel AI Gateway$0 / $0
2026-10-21Deep Infra$0.20 / $0.80
2026-10-20Azure$0.25 / $1
2026-10-20watsonx.ai$0.371 / $1.484
2026-10-20Llama$0 / $0
2026-10-20Vercel AI Gateway$0 / $0
2026-10-20Azure Cognitive Services$0.25 / $1
2026-10-20Deep Infra$0.20 / $0.80
2026-10-19Azure$0.25 / $1
2026-10-19Llama$0 / $0
2026-10-19watsonx.ai$0.371 / $1.484
2026-10-19Vercel AI Gateway$0 / $0
2026-10-19Azure Cognitive Services$0.25 / $1
2026-10-19Deep Infra$0.20 / $0.80
2026-10-18Vercel AI Gateway$0 / $0
2026-10-18watsonx.ai$0.371 / $1.484
2026-10-18Llama$0 / $0
2026-10-18Azure Cognitive Services$0.25 / $1
2026-10-18Azure$0.25 / $1
2026-10-18Deep Infra$0.20 / $0.80
2026-10-17watsonx.ai$0.371 / $1.484
2026-10-17Azure Cognitive Services$0.25 / $1
2026-10-17Azure$0.25 / $1
2026-10-17Llama$0 / $0
2026-10-17Vercel AI Gateway$0 / $0
2026-10-17Deep Infra$0.20 / $0.80
2026-10-12Vercel AI Gateway$0 / $0
2026-10-12Azure$0.25 / $1
2026-10-12Llama$0 / $0
2026-10-12watsonx.ai$0.371 / $1.484
2026-10-12Azure Cognitive Services$0.25 / $1
2026-10-12Deep Infra$0.20 / $0.80
2026-10-12Llama$0 / $0
2026-10-12Vercel AI Gateway$0 / $0
2026-10-12Azure Cognitive Services$0.25 / $1
2026-10-12watsonx.ai$0.371 / $1.484
2026-10-12Azure$0.25 / $1
2026-10-12Deep Infra$0.20 / $0.80
2026-10-11watsonx.ai$0.371 / $1.484
2026-10-11Vercel AI Gateway$0 / $0
2026-10-11Azure Cognitive Services$0.25 / $1
2026-10-11Azure$0.25 / $1
2026-10-11Llama$0 / $0
2026-10-11Deep Infra$0.20 / $0.80
2026-10-10Azure$0.25 / $1
2026-10-10watsonx.ai$0.371 / $1.484
2026-10-10Vercel AI Gateway$0 / $0
2026-10-10Azure Cognitive Services$0.25 / $1
2026-10-10Llama$0 / $0
2026-10-10Deep Infra$0.20 / $0.80
2026-10-09Azure$0.25 / $1
2026-10-09Vercel AI Gateway$0 / $0
2026-10-09watsonx.ai$0.371 / $1.484
2026-10-09Llama$0 / $0
2026-10-09Azure Cognitive Services$0.25 / $1
2026-10-09Deep Infra$0.20 / $0.80
2026-10-09watsonx.ai$0.371 / $1.484
2026-10-09Llama$0 / $0
2026-10-09Azure Cognitive Services$0.25 / $1
2026-10-09Azure$0.25 / $1
2026-10-09Vercel AI Gateway$0 / $0
2026-10-09Deep Infra$0.20 / $0.80
2026-10-08Azure$0.25 / $1
2026-10-08Azure Cognitive Services$0.25 / $1
2026-10-08Vercel AI Gateway$0 / $0
2026-10-08Llama$0 / $0
2026-10-08watsonx.ai$0.371 / $1.484
2026-10-08Deep Infra$0.20 / $0.80
2026-10-07Azure Cognitive Services$0.25 / $1
2026-10-07Llama$0 / $0
2026-10-07Azure$0.25 / $1
2026-10-07watsonx.ai$0.371 / $1.484
2026-10-07Vercel AI Gateway$0 / $0
2026-10-07Deep Infra$0.20 / $0.80
2026-09-22Vercel AI Gateway$0 / $0
2026-09-22Azure$0.25 / $1
2026-09-22Azure Cognitive Services$0.25 / $1
2026-09-22watsonx.ai$0.371 / $1.484
2026-09-22Llama$0 / $0
2026-09-22Deep Infra$0.20 / $0.80
2026-09-21Azure Cognitive Services$0.25 / $1
2026-09-21Azure$0.25 / $1
2026-09-21Llama$0 / $0
2026-09-21Vercel AI Gateway$0 / $0
2026-09-21watsonx.ai$0.371 / $1.484
2026-09-21Deep Infra$0.20 / $0.80
2026-09-20watsonx.ai$0.371 / $1.484
2026-09-20Azure$0.25 / $1
2026-09-20Llama$0 / $0
2026-09-20Azure Cognitive Services$0.25 / $1
2026-09-20Vercel AI Gateway$0 / $0
2026-09-20Deep Infra$0.20 / $0.80
2026-09-19Llama$0 / $0
2026-09-19Azure Cognitive Services$0.25 / $1
2026-09-19watsonx.ai$0.371 / $1.484
2026-09-19Vercel AI Gateway$0 / $0
2026-09-19Azure$0.25 / $1
2026-09-19Deep Infra$0.20 / $0.80
2026-09-18Azure Cognitive Services$0.25 / $1
2026-09-18Azure$0.25 / $1
2026-09-18watsonx.ai$0.371 / $1.484
2026-09-18Llama$0 / $0
2026-09-18Vercel AI Gateway$0 / $0
2026-09-18Deep Infra$0.20 / $0.80
2026-09-17Azure$0.25 / $1
2026-09-17Llama$0 / $0
2026-09-17Vercel AI Gateway$0 / $0
2026-09-17Azure Cognitive Services$0.25 / $1
2026-09-17watsonx.ai$0.371 / $1.484
2026-09-17Deep Infra$0.20 / $0.80