Start free trial

Meta: Llama 4 Maverick

meta-llama/llama-4-maverick
CompareAPITry this model

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

Modalities
In / out per 1M$0.19 / $0.65
Context1M
ReleasedApr 5, 2025

Providers

4 providers serve this model upstream.

Providers serving this model
ProviderInput /MOutput /MCache read /MLatency P50Throughput P50Uptime
DigitalOcean$0.19$0.65$0.050.99s14 tps99.94%
Parasailfp8$0.35$1.00$0.170.56s59 tps99.77%
NovitaAIfp8$0.27$0.85Variable0.60s26 tps99.68%
Google Vertexus-east5$0.35$1.15Variable———

Market-wide measurements, refreshed every 15 minutes. They describe who serves Llama 4 Maverick in general, not how ProjectCOZY routes your requests.

Pricing

List rates per 1M tokens — what Llama 4 Maverick costs pay-as-you-go elsewhere, not what you pay here.

Input
$0.19
per 1M tokens
Output
$0.65
per 1M tokens
Cache read
$0.05
per 1M cached tokens
Included in every pass
Llama 4 Maverick is included in every ProjectCOZY pass at no extra cost — one flat rate, no per-token metering. The rates above are there for comparison.

Performance

Time to first token and output speed across every provider, over the last 3 days.

0.0s1.0s2.0s3.0s4.0s
Oct 16, 12 AMOct 16, 8 AMOct 16, 4 PMOct 17, 12 AMOct 17, 8 AMOct 17, 4 PMOct 18, 12 AMOct 18, 8 AMOct 18, 4 PMOct 19, 12 AMOct 19, 8 AM
DigitalOcean Parasail NovitaAI
0 tok/s50 tok/s100 tok/s150 tok/s200 tok/s
Oct 16, 12 AMOct 16, 8 AMOct 16, 4 PMOct 17, 12 AMOct 17, 8 AMOct 17, 4 PMOct 18, 12 AMOct 18, 8 AMOct 18, 4 PMOct 19, 12 AMOct 19, 8 AM
DigitalOcean Parasail NovitaAI

Uptime

100% of requests were served successfully over the last 3 days, across all providers.

Last 3 daysAvailability 99.94%
Oct 16, 9:00 AMNow
Availability over the last 24 hoursAvailability 99.97%
100% 98% 97% 95%
Oct 18, 9:50 AMNow

Apps

Tools that most often run Llama 4 Maverick, by tokens this week.

Chatters Inner Circle32.4% of tokens1.7Bpreference-falsification pilot31.4% of tokens1.6BPortkey AIProgramming App · 12.6% of tokens660.5McClassTrib11.9% of tokens626.4MPocket Girl AI11.7% of tokens615.0M

Activity

68.8B tokens processed market-wide in the last month.

01.0B2.0B3.0B4.0B
Sep 19Sep 24Sep 29Oct 4Oct 9Oct 14Oct 19
Tokens

FAQ

Which model id do I use for Llama 4 Maverick?
meta-llama/llama-4-maverick. Send it as the model field from any OpenAI-compatible client, against http://192.168.1.55/v1.
How much context does Llama 4 Maverick hold?
1,048,576 tokens per request, of which up to 16,384 can be the response.
What can it accept and return?
Input: text, image. Output: text.
What does Llama 4 Maverick cost on a pass?
Nothing beyond the pass itself. Pay-as-you-go elsewhere it lists at $0.19 per 1M input tokens and $0.65 per 1M output tokens.
How current is its knowledge?
Training data runs to Aug 2024. Anything later has to come from your prompt or a tool call.
Who built Llama 4 Maverick?
Meta, in the Llama family.

Explore

Other models your pass can call.

Aion 3.5aion-labs/aion-3.5256KAionAion 3.5 Miniaion-labs/aion-3.5-mini256KAionAion-2.0aion-labs/aion-2.0128KAionAion-3.0aion-labs/aion-3.0128KAionAion-3.0-Miniaion-labs/aion-3.0-mini128KAionAion-RP 1.0 (8B)aion-labs/aion-rp-llama-3.1-8b32KAion