Kyma APIKyma API
Meta

Meta

Llama 4 Maverick

Meta's larger Llama 4 tier, above Scout. 1M context, vision, served from two independent providers.

Modalities

Text+Image → Text

Below release

fp8

Weights

Published

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

Where it sits in the catalogue Kyma measures

Every number against every text model Kyma prices per token — a stated rule, not a chosen line-up.

Price · input#17/71

$0.27

output $1.08

median $1.013 · best $0.0494

Price · output#17/70

$1.08

per 1M tokens generated

median $3.531 · best $0.218

Availability · 30d#1/70

100%

119 observations since 2026-08-01

median 100.0% · best 100.0%

Throughput#36/65

34 tok/s

probe median, one fixed prompt

median 35.7 tok/s · best 365.1 tok/s

Response time#3/65

1.08 s

probe median, to a complete answer

median 2.96 s · best 0.89 s

Context

1.05M

max output 16,384

published by Meta, not measured here

Tick above each rail is this model, below it the other 70. Dashed rule is the field median, solid is its best. Better is left; the axis stops at the 90th percentile, so a few models sit past its right edge.

Usage

How much this model is actually called here.

Rank

#60

of 101 active models

Tokens served

297.8K

all-time

Platform share

0.0%

of all tokens

Tokens · last 14 daysSep 26 → Oct 9

Pricing

Pay per token. Cached input bills at this model’s own cached rate, listed below.

$0.27 /1M input$1.08 /1M output
Hobby10 req/day · 2K in / 500 out
~$0.32/mo
Production1,000 req/day · 2K in / 500 out
~$32.40/mo
Scale20,000 req/day · 2K in / 500 out
~$648/mo
+ Estimate your workload
1,000
2,000
500

Estimated monthly cost

$32.40

$1.08 / day on Llama 4 Maverick

Same workload on:

Muse Spark 1.1$171+428%
Muse Spark 1.2$197+507%

Estimates use list pricing. Actual bills depend on real token counts, and every response includes its exact cost.

How it compares

Against the peers people actually weigh it against.

SpecLlama 4 MaverickMuse Spark 1.1Muse Spark 1.2
Input /1M$0.27$1.542$1.773
Output /1M$1.08$5.243$6.025
Context1M1M1M
ToolsYesYesYes
ReasoningNoYesYes
Throughput34 tok/s178 tok/s114 tok/s

Quick start

Up and running in under two minutes.

  1. 1

    Create an API key

    Sign up and grab a key from the dashboard — $0.50 free credit on the free tier, which covers Llama 4 Maverick. No card required.

    Get API key →
  2. 2

    Make your first request

    Drop in your key and send a chat completion — fully OpenAI-compatible.

    curl https://kymaapi.com/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "llama-4-maverick",
    "messages": [
      {"role": "user", "content": "Explain prompt caching in one paragraph."}
    ]
  }'
  3. 3

    Stream responses

    Add "stream": true to receive tokens as they arrive.

    curl https://kymaapi.com/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "llama-4-maverick",
    "stream": true,
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

FAQ

Common questions about this model.

What is the context window of Llama 4 Maverick?

Llama 4 Maverick has a 1M-token context window — roughly 1542 pages of text in a single request.

How much does the Llama 4 Maverick API cost?

$0.27 per 1M input tokens and $1.08 per 1M output tokens. No subscription; you pay only for what you use.

Does Llama 4 Maverick support function calling?

Yes — Llama 4 Maverick supports tool/function calling and structured outputs (JSON mode), so it works with agent frameworks out of the box.

Are the weights for Llama 4 Maverick publicly available?

Yes. Meta publishes Llama 4 Maverick's weights as meta-llama/Llama-4-Maverick-17B-128E-Instruct, so you can download and run the model yourself (https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E-Instruct, read 2026-08-14). Kyma serves it because it is convenient and has failover behind it, not because it is the only way to reach it.

Is Llama 4 Maverick ever served below the precision its creator released it at?

Sometimes. Llama 4 Maverick was released by Meta at bf16 (https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E-Instruct, read 2026-08-14), and at least one route serving it here reports fp8 — narrower than that. Weights compressed below the release usually answer close to it, but it is not the identical artefact, and nothing in the response tells you which one answered. Kyma checked the routes on 2026-09-21, so it is your call rather than a silent one.

How do I use Llama 4 Maverick?

Kyma is OpenAI-compatible: point your SDK's base URL at https://kymaapi.com/v1, use your Kyma API key, and set the model to llama-4-maverick. Signing up is free and includes $0.50 of credit on the free tier, which covers this model — no card required.

Start with $0.50 free credit on the free tier — no card required.Create account →

More models by Meta

ModelContextInputOutput
MetaMuse Spark 1.31M$1.688$5.738
MetaMuse Glimmer 30B131K$0.405$1.62
MetaMuse Spark 1.21M$1.773$6.025
MetaMuse Spark 1.11M$1.542$5.243
MetaLlama 3.3 70B128K$0.135$0.432