Llama 4 Maverick API model profile

Evidence snapshot: 2026-09-06

Llama 4 Maverick is a Meta model profile with a 1,048,576-token context window. The dated catalog snapshot records text, image modalities and interfaces for reasoning, structured output, text generation, tool calling, tools.

Llama 4 Maverick 17B Instruct (128E) is a high-capacity multimodal language model from Meta, built on a mixture-of-experts (MoE) architecture with 128 experts and 17 billion active parameters per forward...

Llama 4 Maverick is worth reaching for when you need a route carrying one of the widest context windows in the catalog. The conditions below are the ones its own numbers support.

Llama 4 Maverick is available under the Kendr alias kc-llama-4-maverick. Current account availability and customer credit quotes come from Kendr's live public model API and applicable account policy.

Llama 4 Maverick accepts text and image and returns text. The snapshot records reasoning, structured output, text generation, tool calling, tools, vision, and web search as capabilities or interfaces.

The dated reference snapshot lists $0.2 input and $0.696 output per million tokens. Cached input is $0.17 per million tokens. The separately published provider-route reference is $0.24 / $0.97.

No comparable popularity rank or traffic share is present in the 2026-09-06 snapshot. No comparable routing rank or traffic-share observation is attached to this dated profile; missing adoption evidence is not estimated.

Profile data was reviewed for the 2026-09-06 snapshot. Claims retain their source dates, and unavailable fields are shown as unavailable instead of estimated.

Profile facts

Profile type: Kendr API model
Kendr API alias: kc-llama-4-maverick
Model developer: Meta
Kendr route provider: Meta
Context window: 1M
Snapshot date: 2026-09-06
Knowledge cutoff: 2024-08-31
Reference catalog ID: meta-llama/llama-4-maverick

When to pick Llama 4 Maverick

Llama 4 Maverick is worth reaching for when you need a route carrying one of the widest context windows in the catalog. The conditions below are the ones its own numbers support.

Each condition below is derived from this model's own values in the 2026-09-06 snapshot, compared only against models publishing the same field.

Reach for it when a whole corpus has to fit in one prompt. The 1.05M-token context window is in the top quarter of the 163 models publishing a limit here, so long documents can go in whole rather than chunked.
Reach for it when the input includes images. The snapshot records image input, so screenshots, scans, and diagrams can be sent directly instead of described.
Reach for it when the model has to call tools. Tool calling is recorded in the snapshot, so this route can drive an agent loop rather than only answer in prose.

Context, modalities, and identity

Model developer: Meta
Kendr route provider: Meta
Context window: 1M
Maximum output: 115,200 tokens
Input modalities: text and image
Output modalities: text
Knowledge cutoff: 2024-08-31

Model overview

Reference model ID: meta-llama/llama-4-maverick
Canonical version: meta-llama/llama-4-maverick-17b-128e-instruct
Hugging Face ID: meta-llama/Llama-4-Maverick-17B-128E-Instruct

Capabilities and supported controls

Capabilities and parameters are reported from the dated catalog and source records; their presence does not guarantee identical behavior across every provider route.

Supported parameters: frequency_penalty, logit_bias, logprobs, max_tokens, min_p, presence_penalty, repetition_penalty, response_format, seed, stop, structured_outputs, temperature, tool_choice, tools, top_k, top_logprobs, top_p

reasoning
structured output
text generation
tool calling
tools
vision
web search

Dated pricing snapshot

The dated reference snapshot lists $0.2 input and $0.696 output per million tokens. Cached input is $0.17 per million tokens. The separately published provider-route reference is $0.24 / $0.97.

Reference figures are dated 2026-09-06; the live Kendr quote can differ by selected provider route, context tier, caching, tools, region, and current rate card.

Price date: 2026-09-06
Input: $0.2 per 1M tokens
Cached input: $0.17 per 1M tokens
Output: $0.696 per 1M tokens

Provider routes, performance, and uptime

The snapshot retains 5 provider endpoints. Provider prices, context limits, p50 performance, and uptime can differ by route and are not Kendr guarantees.

Active provider endpoints: 5
Best p50 latency: No recent metric
Best p50 throughput: No recent metric
Availability with routing: No recent metric
Availability without routing: No recent metric
Performance date: 2026-09-06

Provider	Quantization	Input / 1M	Output / 1M	Cache read / 1M	Context	p50 latency	p50 throughput	Uptime (1d)
DigitalOcean	unknown	$0.2 / 1M	$0.696 / 1M	No verified rate	128,000 tokens	No recent p50	No recent p50	99.92%
DeepInfra	fp8	$0.2 / 1M	$0.8 / 1M	No verified rate	1,048,576 tokens	No recent p50	No recent p50	99.73%
Novita	fp8	$0.27 / 1M	$0.85 / 1M	No verified rate	1,048,576 tokens	No recent p50	No recent p50	99.47%
Parasail	fp8	$0.35 / 1M	$1 / 1M	$0.17 / 1M	524,288 tokens	No recent p50	No recent p50	99.90%
Google	unknown	$0.35 / 1M	$1.15 / 1M	No verified rate	524,288 tokens	No recent p50	No recent p50	99.20%

Benchmark evidence and limitations

Third-party catalog fields normalized from the cited model dataset; benchmark methodology and coverage differ by source.

Coding Index: 16.3
Agentic Index: 0.6

Design Arena category	Elo	Win rate	Rank
3d	937	40.2%	#108
codecategories	896	35.8%	#120
dataviz	900	38.4%	#116
gamedev	867	33.7%	#120
uicomponent	921	40.8%	#112
website	884	34.4%	#123

Popularity and market context

Third-party catalog rank: No verified rank
Global market share: Not inferred
Observation date: 2026-09-06

OpenAI-compatible API example

This example applies to the published Kendr alias on this hosted profile. Check the live public catalog before use.

curl https://api.kendr.org/v1/chat/completions \
  -H "Authorization: Bearer $KENDR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"kc-llama-4-maverick","messages":[{"role":"user","content":"Hello"}]}'

Frequently asked questions

When should I use Llama 4 Maverick?

Llama 4 Maverick is worth reaching for when you need a route carrying one of the widest context windows in the catalog. The conditions below are the ones its own numbers support. Reach for it when a whole corpus has to fit in one prompt: The 1.05M-token context window is in the top quarter of the 163 models publishing a limit here, so long documents can go in whole rather than chunked. Reach for it when the input includes images: The snapshot records image input, so screenshots, scans, and diagrams can be sent directly instead of described. Reach for it when the model has to call tools: Tool calling is recorded in the snapshot, so this route can drive an agent loop rather than only answer in prose.

What is Llama 4 Maverick?

What context window does Llama 4 Maverick have?

The dated profile lists 1M of context and up to 115,200 output tokens. Provider routes, variants, and runtime configuration can impose lower effective limits.

What benchmark evidence is available for Llama 4 Maverick?

The 2026-09-06 snapshot includes 2 Artificial Analysis indexes and 6 Design Arena categories. Publisher-reported launch results are labeled and are not presented as Kendr measurements; scores from different suites are not treated as interchangeable. Third-party catalog fields normalized from the cited model dataset; benchmark methodology and coverage differ by source.

What is the Kendr API alias for Llama 4 Maverick?

Use kc-llama-4-maverick as the model value. The live public model API and signed-in catalog remain authoritative for route availability and customer credit quotes.

How is Llama 4 Maverick priced on Kendr?

The dated reference snapshot lists $0.2 input and $0.696 output per million tokens. Cached input is $0.17 per million tokens. The separately published provider-route reference is $0.24 / $0.97. Kendr applies one 5% markup to configured provider model cost; the live quote and settled routing receipt are authoritative for a request.

Sources and evidence dates

Llama 4 Maverick third-party catalog record (catalog, checked 2026-09-06)
Third-party model catalog methodology (methodology, checked 2026-09-06)
Meta official model documentation (primary, checked 2026-09-06)
Artificial Analysis capability indices methodology (benchmark, checked 2026-09-06)
Design Arena leaderboard and methodology (benchmark, checked 2026-09-06)
Llama 4 Maverick provider or route reference (primary, checked 2026-09-06)