Models

llama-4-maverick vs llama2-70b-40960

Output tokens cost $0.20 per million on llama-4-maverick and $0.50 per million on llama2-70b-40960. Input tokens cost $0.20 per million on llama-4-maverick and $0.50 per million on llama2-70b-40960. Cached input tokens are billed at $0.20 per million on llama-4-maverick and $0.50 per million on llama2-70b-40960.

Llamallama-4-maverickLlamallama2-70b-40960
Llama logo
llama-4-maverick
Llama · text, image → text

Llama 4 Maverick is a high-capacity Mixture-of-Experts (MoE) model from Meta, featuring 400B total parameters and 128 experts, while activating an efficient 17B parameters per inference. Engineered for peak performance, it excels at advanced multimodal tasks. Maverick natively supports text and image input, producing multilingual text and code. With a 1-million-token context window and instruction tuning, it is optimized for complex image reasoning and general-purpose assistant-like interactions. Released under the Llama 4 Community License, Maverick is ideal for research and commercial applications demanding state-of-the-art multimodal understanding and high throughput.

Input$0.20 /M
Output$0.20 /M
Llama logo
llama2-70b-40960
Llama · → text

Input$0.50 /M
Output$0.50 /M

Pricing & Specifications

Prices are per million tokens. Time to First Token and throughput are rolling averages measured on AIHubMix.

llama-4-maverick
llama2-70b-40960
Input /M
$0.20
$0.50
Output /M
$0.20
$0.50
Cache read /M
$0.20
$0.50
Context length
1,048,576
0
Max output
32,000
0
Time to First Token
0.2 s
-
Throughput
97.8 tok/s
-
Modalities
textimage
Supported Parameters
toolsfunction callingstructured outputs
API Formats

Promotional prices show the discounted rate; see each model page for promotion windows.

Activity Past 30 Days

Daily traffic served through AIHubMix — how demand for each model is trending.

llama-4-maverickllama2-70b-40960

Tokens / day

-

Requests / day

-

Performance Past 3 Days

Measured on real AIHubMix traffic, hourly buckets. Gaps mean no traffic in that hour.

llama-4-maverickllama2-70b-40960

Throughput (tok/s)

-

TTFT (s)

-

Uptime (%)

-

Cost calculator

Estimate your monthly bill for the same workload on each model.

llama-4-maverick
$15.00 /mo
llama2-70b-40960
$37.50 /mo

Monthly = daily × 30. Discounted rates applied where a promotion is active.

FAQ

Which is cheaper: llama-4-maverick, llama2-70b-40960?

llama-4-maverick: $0.20/M output tokens; llama2-70b-40960: $0.50/M. Use the cost calculator above to estimate your own workload.

Can I call llama-4-maverick and llama2-70b-40960 with the same API key?

Yes. AIHubMix serves every model on this page behind one OpenAI-compatible endpoint, so switching between them is a one-line change to the model field — no second account, key or SDK.

Popular comparisons

Related model match-ups readers also look at.