Open multimodal Llama model for strong reasoning and fast responses
| Provider | Tier | Input | Output | Cache read | Cache write | Context | Output limit | Status |
|---|---|---|---|---|---|---|---|---|
| LlamaOfficial | First-party | Free | — | — | 128,000 | 4,096 | ||
| Vercel AI Gateway meta/llama-4-maverick | Cloud | Free | — | — | 128,000 | 4,096 | ||
| Deep Infra meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8 | Cloud | $0.20 | $0.80 | — | — | 1,048,576 ⚠ | 16,384 | deprecated |
| NovitaAI | Gateway | $0.27 | $0.85 | — | — | 1,048,576 ⚠ | 8,192 | |
| Azure | Cloud | $0.25 | $1.00 | — | — | 1,000,000 ⚠ | 16,384 | |
| Azure Cognitive Services | Cloud | $0.25 | $1.00 | — | — | 1,000,000 ⚠ | 16,384 | |
| watsonx.ai | Cloud | $0.37 | $1.48 | — | — | 131,072 ⚠ | 8,192 |
Sorted by blended price (input×0.75 + output×0.25) asc. The official channel always shows regardless of rank. Whether a gateway's low price is actually usable can't be verified.
2 more channels offer $0 (Llama, Vercel AI Gateway); free tiers usually have rate limits and no SLA, excluded from ranking.