Same open weights, served by 1 provider.
| Provider | Their model id | Serving | Input | Output | Cached in | Blended 3:1 | Source | |
|---|---|---|---|---|---|---|---|---|
DeepInfra Deprecated, 2026-07-17 | meta-llama/Llama-3.2-11B-Vision-Instruct | standardFP8 | $0.345 | $0.345 | — | $0.345 | Verified 6h ago · Changed 8h ago | |
DeepInfra Deprecated, 2026-07-17 | meta-llama/Llama-3.2-11B-Vision-Instruct | priorityFP81.5× standard | $0.517 | $0.517 | — | $0.517 | Verified 6h ago · Changed 8h ago |
Same weights don't always mean identical outputs: quantization, context limits and serving stacks can change quality, especially for tool calling. Prices are USD per 1M tokens; hyperscaler prices are for the reference region shown.
| DeepInfra fp8 | $41.4/mo |
Cache hits use each provider's cached-input price where it has one. Cache write costs aren't included.