Deepinfra Llama 4 Maverick 17B 128e Instruct
Llama · → text
Input$0.33 /M
Output$1.32 /M
← ModelsDeepinfra Llama 4 Maverick 17B 128e Instruct
Grok 4.5
Deepinfra Llama 4 Maverick 17B 128e Instruct vs Grok 4.5
Compare Deepinfra Llama 4 Maverick 17B 128e Instruct from Llama and Grok 4.5 from Grok on key metrics including benchmarks, price, context length, and other model features. Access both models and hundreds of others through the AIHubMix API.
Deepinfra Llama 4 Maverick 17B 128e InstructGrok 4.5+ Add model · 2/4
Grok 4.5
Grok · text, image → text
Grok 4.5 was trained on datasets spanning knowledge in coding, science, engineering, and math. With both intelligent and efficient reasoning, Grok 4.5 excels at real engineering tasks and exceeds comparable leading models at these tasks.
Input$2 /M
Output$6 /M
Cache read$0.5 /M
Pricing & Specifications
Prices are per million tokens. Time to First Token and throughput are rolling averages measured on AIHubMix.
Deepinfra Llama 4 Maverick 17B 128e Instruct
Grok 4.5
Input /M
$0.33
$2
Output /M
$1.32
$6
Cache read /M
-
$0.5
Context length
0
500,000
Max output
0
500,000
Time to First Token
2.2 s
4.4 s
Throughput
45.1 tok/s
34.2 tok/s
Modalities
textimage
Supported Parameters
thinkingtoolsfunction callingstructured outputslong context
API Formats
Released
-
July 2026
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.
deepinfra-llama-4-maverick-17b-128e-instructgrok-4.5
Tokens / day
-
Requests / day
-
Performance Past 3 Days
Measured on real AIHubMix traffic, hourly buckets. Gaps mean no traffic in that hour.
deepinfra-llama-4-maverick-17b-128e-instructgrok-4.5
Throughput (tok/s)
-
TTFT (s)
-
Uptime (%)
-
LMArena Benchmarks
LMArena ratings by capability (Bradley-Terry, commonly called Elo). Higher is better.
Text
deepinfra-llama-4-maverick-17b-128e-instructgrok-4.5
1280136014401520
Overall
13271471
Coding
13731523
Math
13171479
Hard prompts
13381495
Instruction following
13131466
Multi-turn
13261476
Creative writing
13071451
Longer query
13341487
Chinese
13331512
English
13401476
Vision
deepinfra-llama-4-maverick-17b-128e-instructgrok-4.5
1120118012401300
Overall
11451282
OCR
11531294
Diagram
11521319
Homework
11651324
Source: LMArena (arena.ai) leaderboard, imported by AIHubMix. Models without published ratings are omitted per chart.
Cost calculator
Estimate your monthly bill for the same workload on each model.
Deepinfra Llama 4 Maverick 17B 128e Instruct
$39.60 /mo
Grok 4.5
$210 /mo
Monthly = daily × 30. Discounted rates applied where a promotion is active.
FAQ
Which is cheaper: Deepinfra Llama 4 Maverick 17B 128e Instruct, Grok 4.5?
Deepinfra Llama 4 Maverick 17B 128e Instruct: $1.32/M output tokens; Grok 4.5: $6/M. Use the cost calculator above to estimate your own workload.
How do their coding arena scores compare?
Grok 4.5: 1523; Deepinfra Llama 4 Maverick 17B 128e Instruct: 1373 (LMArena coding leaderboard).
Which responds faster?
Deepinfra Llama 4 Maverick 17B 128e Instruct: 2.2s time to first token measured on AIHubMix; see the live performance charts above for how each model behaves across the day.
Which one generates tokens faster?
Deepinfra Llama 4 Maverick 17B 128e Instruct at 45.1 tok/s and Grok 4.5 at 34.2 tok/s, measured as output throughput on AIHubMix — a separate metric from time to first token.
Can I call Deepinfra Llama 4 Maverick 17B 128e Instruct and Grok 4.5 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.
