inference

Inference

All current catalogue offerings from this provider. Documentation remains authoritative.

Fresh · fetched 2026-08-17T02:11:57.739Z · Models.dev(opens in a new tab)

9 offerings

ModelContext / outputCapabilitiesLowest inputProviders
Llama 3.2 3B Instructllama-3.2-3b-instruct · llama128KOutput 128K
Tool callingReasoningJSONOpen weights
$0.00out $0.0010fresh
Llama 3.2 1b Instructmeta/llama-3.2-1b-instruct128KOutput 4K
Tool callingJSONOpen weights
$0.00out $0.002fresh
Llama-3.1-8B-Instructllama-3.1-8b-instruct · llama128KOutput 128K
Tool callingReasoningJSONOpen weights
$0.00out $0.0012fresh
Llama 3.2 11b Vision Instructmeta/llama-3.2-11b-vision-instruct128KOutput 4K
Tool callingImage inputJSONOpen weights
$0.00out $0.002fresh
Qwen3-Embedding 4Bqwen3-embedding-4b · qwen32KOutput 32K
Open weights
$0.010out $0.004fresh
Google Gemma 3google/gemma-3 · gemma125KOutput 4K
Tool callingImage inputOpen weights
$0.15out $0.301fresh
Osmosis Structure 0.6Bosmosis/osmosis-structure-0.6b · osmosis4KOutput 2K
Tool callingOpen weights
$0.10out $0.501fresh
Qwen 2.5 7B Vision Instructqwen/qwen-2.5-7b-vision-instruct · qwen125KOutput 4K
Tool callingImage inputOpen weights
$0.20out $0.201fresh
Mistral Nemo 12B Instructmistral/mistral-nemo-12b-instruct · mistral-nemo16KOutput 4K
Tool callingOpen weights
$0.038out $0.101fresh

Provider documentation remains authoritative. Catalogue presence is not an uptime, security, or quality endorsement.