Llama 4 Maverick benchmark, API pricing, and provider data cover 20 API providers, with prices starting at $0.0038/M. Llama 4 Maverick free API options are available from 2 providers.
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 forw...
Observed-capability estimates with uncertainty reported separately from independent benchmark families.
Input and output token limits for this model, plus how it ranks on long-context understanding.
1 metric
Third-party OpenRouter endpoint data, shown separately from LMSpeed measurements. Some 30-minute live performance fields only appear after syncing with an OpenRouter API key.
| Provider endpoint | Input | Output | 1d uptime | 30m latency | 30m throughput | Context / output |
|---|---|---|---|---|---|---|
Google google-vertex/us-east5 | $0.350/M | $1.15/M | 100.0% | — | — | 524.3K tokens / 8.2K tokens |
DigitalOcean digitalocean | $0.250/M | $0.870/M | 100.0% | — | — | 128K tokens / — |
Parasail parasail/fp8 | $0.350/M | $1/M | 100.0% | — | — | 524.3K tokens / 32.8K tokens |
DeepInfra deepinfra/base | $0.150/M | $0.600/M | 99.9% | — | — | 1.0M tokens / 16.4K tokens |
Novita novita/fp8 | $0.270/M | $0.850/M | 99.9% | — | — | 1.0M tokens / 8.2K tokens |
Compare Llama 4 Maverick API pricing across 18 providers. Prices range from $0.0038/M to $375.00/M. 云AI offers the lowest rate at $0.0038/M. 2 providers offer free API credits or a free tier.
| Provider | Health | Model Variant | Group | Input ($/M) | Output ($/M) | Speed (t/s) | First token | Audit |
|---|---|---|---|---|---|---|---|---|
Dext API Free | L1 98% | llama-4-maverick-17b-128e-instruct | 公益 | Free | Free | — | — | — |
L1 98% | meta-llama/llama-4-maverick | 逆向4 | -98%$0.0074/M | -96%$0.033/M | — | — | — | |
CM-API 公益站 Free | L1 98% | meta/llama-4-maverick-17b-128e-instruct | 国产模型 | Free | Free | — | — | — |
L1 98% | meta-llama/llama-4-maverick | default | $0.979/M | $3.67/M | — | — | — | |
L1 98% | meta-llama/llama-4-maverick-17b-128e-instruct | default | $10.27/M | $10.27/M | — | — | — | |
L1 98% | llama-4-maverick-17b-128e-instruct | nvidia | $150.00/M | $150.00/M | — | — | — | |
L1 98% | meta/llama-4-maverick-17b-128e-instruct | default | $375.00/M | $375.00/M | — | — | — | |
L1 96% | meta-llama/llama-4-maverick | default | $75.00/M | $75.00/M | — | — | — | |
L1 96% | llama-4-maverick-03-26-experimental | default | $75.00/M | $75.00/M | — | — | — | |
L1 96% | llama-4-maverick | default | $0.010/request | - | — | — | — | |
L1 96% | llama-4-maverick-17b-128e-instruct | 小叶币 | $0.050/request | - | — | — | — | |
L1 92% | llama-4-maverick | nvidia | $1.00/request | - | — | — | — | |
L1 23% | llama-4-maverick | mix | -99%$0.0038/M | -98%$0.019/M | — | — | — |
2 metrics
2 metrics
3 metrics · Estimated
6 metrics · Estimated
5 metrics · Rated
6 metrics · No data
4 metrics · Estimated
1 metric · No data
3 metrics · No data
2 metrics · No data
