llama-4-maverick-128e-instruct
Developer: Meta
Also known as
Llama 4 Maverick 128e Instruct by Meta is available through 21 API providers on LMSpeed. Compare API pricing from $0.0005 to $75.00 per million input tokens across providers. Free API access is offered by 1 provider. In speed benchmarks, the fastest provider reaches 826 tok/s.
Compare Llama 4 Maverick 128e Instruct API pricing across 20 providers. Input prices range from $0.0005 to $75.00 per million input. 91VIP offers the lowest rate at $0.0005/M.
| Provider | Model Variant | Input ($/M) | Output ($/M) | Speed (t/s) |
|---|---|---|---|---|
| MapleLeaf API | meta/llama-4-maverick-17b-128e-instruct | Free | Free | — |
| 91VIP | llama-4-maverick-17b-128e-instruct | $0.0005 | $0.0008 | — |
| Futureppo | llama-4-maverick-17b-128e-instruct | $0.0005 | $0.0008 | — |
| 素墨API | llama-4-maverick-17b-128e-instruct | $0.010 | $0.010 | — |
| 素墨API | meta/llama-4-maverick-17b-128e-instruct | $0.010 | $0.010 | — |
 星见雅 API | 英伟达/meta/llama-4-maverick-17b-128e-instruct | $0.100 | $0.100 | — |
| 对空六课 API | 英伟达/meta/llama-4-maverick-17b-128e-instruct | $0.100 | $0.100 | — |
| WSocket AI | meta/llama-4-maverick-17b-128e-instruct | $0.200 | $0.200 | — |
| 人人 API | llama-4-maverick-17b-128e-instruct | $0.300 | $0.500 | — |
| SWT-API | llama-4-maverick-17b-128e-instruct | $0.375 | $0.375 | — |
| Synapse | Llama-4-Maverick-17B-128E-Instruct | $1.00 | $1.00 | — |
| 钱多多 API | meta/llama-4-maverick-17b-128e-instruct | $2.00 | $2.00 | — |
| Seamee API | LLM-Research/Llama-4-Maverick-17B-128E-Instruct | $2.00 | $2.00 | — |
 天絮 API | llama-4-maverick-17b-128e-instruct | $75.00 | $75.00 | — |
| 天絮 API | meta/llama-4-maverick-17b-128e-instruct | $75.00 | $75.00 | — |
 IXIOCCAPI | llama-4-maverick-17b-128e-instruct | $75.00 | $75.00 | — |
| MIX API | meta/llama-4-maverick-17b-128e-instruct | $75.00 | $75.00 | — |
| Seamee API | Meta/Llama-4-Maverick-17B-128E-Instruct | $75.00 | $75.00 | — |
| Seamee API | meta/llama-4-maverick-17b-128e-instruct | $75.00 | $75.00 | — |
| 温云 | meta/llama-4-maverick-17b-128e-instruct | $75.00 | $75.00 | — |
Pricing data from provider public APIs
Llama 4 Maverick 128e Instruct is free to use through 1 provider with no per-token charges. These providers offer free API credits or a free tier:
| Provider | Speed (t/s) |
|---|---|
| MapleLeaf API | — |
Compare speed and latency performance across all API providers.
Showing 1-3 of 3 providers
| Provider | Speed | Latency | Tests |
|---|---|---|---|
 GPT Load (Shiho)llama-4-maverick-17b-128e-instruct | 825.70 tok/s | 0.41s | 5 |
 meta/llama-4-maverick-17b-128e-instruct | 131.83 tok/s | 0.48s | 5 |
 meta/llama-4-maverick-17b-128e-instruct | 100.41 tok/s | 0.21s | 15 |
Latest benchmark results measuring API response speed and first-token latency.
| Time | Model | Speed | Latency |
|---|---|---|---|
| 03/31/2026, 10:16 | meta/llama-4-maverick-17b-128e-instruct | 107.02 tok/s | 0.32s |
| 03/31/2026, 10:16 | meta/llama-4-maverick-17b-128e-instruct | 98.43 tok/s | 0.19s |
| 03/31/2026, 10:16 | meta/llama-4-maverick-17b-128e-instruct | 93.75 tok/s | 0.18s |
| 03/31/2026, 10:16 | meta/llama-4-maverick-17b-128e-instruct | 106.97 tok/s | 0.17s |
| 03/31/2026, 10:16 | meta/llama-4-maverick-17b-128e-instruct | 104.39 tok/s | 0.17s |
| 03/31/2026, 10:15 | meta/llama-4-maverick-17b-128e-instruct | 104.12 tok/s | 0.29s |
| 03/31/2026, 10:15 | meta/llama-4-maverick-17b-128e-instruct | 96.01 tok/s | 0.17s |
| 03/31/2026, 10:15 | meta/llama-4-maverick-17b-128e-instruct | 93.31 tok/s | 0.17s |
| 03/31/2026, 10:15 | meta/llama-4-maverick-17b-128e-instruct | 101.97 tok/s | 0.22s |
| 03/31/2026, 10:15 | meta/llama-4-maverick-17b-128e-instruct | 105.10 tok/s | 0.17s |
| 03/31/2026, 10:14 | meta/llama-4-maverick-17b-128e-instruct | 98.62 tok/s | 0.30s |
| 03/31/2026, 10:14 | meta/llama-4-maverick-17b-128e-instruct | 98.75 tok/s | 0.21s |
| 03/31/2026, 10:14 | meta/llama-4-maverick-17b-128e-instruct | 89.16 tok/s | 0.19s |
| 03/31/2026, 10:14 | meta/llama-4-maverick-17b-128e-instruct | 108.21 tok/s | 0.20s |
| 03/31/2026, 10:14 | meta/llama-4-maverick-17b-128e-instruct | 100.29 tok/s | 0.19s |
| 03/13/2026, 21:30 | meta/llama-4-maverick-17b-128e-instruct | 140.78 tok/s | 0.56s |
| 03/13/2026, 21:30 | meta/llama-4-maverick-17b-128e-instruct | 125.11 tok/s | 0.56s |
| 03/13/2026, 21:30 | meta/llama-4-maverick-17b-128e-instruct | 124.89 tok/s | 0.46s |
| 03/13/2026, 21:30 | meta/llama-4-maverick-17b-128e-instruct | 124.47 tok/s | 0.40s |
| 03/13/2026, 21:30 | meta/llama-4-maverick-17b-128e-instruct | 143.88 tok/s | 0.39s |
