Intelligence des modèles d'IA

Fournisseur · 2026-05-12

ollama-cloud

5 modèles canoniques21 entrées au total (dérivés inclus)
ModèleEntrée / 1MSortie / 1MContexteFournisseursTags
cogito-2.1:671bInconnuInconnu164K1tools · reasoning · open-weights
ministral-3:14bInconnuInconnu262K1tools · vision · open-weights
ministral-3:3bInconnuInconnu262K1tools · vision · open-weights
ministral-3:8bInconnuInconnu262K1tools · vision · open-weights
rnj-1:8bInconnuInconnu33K1tools · open-weights
deepseek-v3.1:671bdérivéInconnuInconnu164K1tools · reasoning · open-weights
devstral-2:123bdérivéInconnuInconnu262K1tools · open-weights
devstral-small-2:24bdérivéInconnuInconnu262K1tools · vision · open-weights
gemma3:12bdérivéInconnuInconnu131K1vision · open-weights
gemma3:27bdérivéInconnuInconnu131K1vision · open-weights
gemma3:4bdérivéInconnuInconnu131K1vision · open-weights
gemma4:31bdérivéInconnuInconnu262K1tools · reasoning · vision · open-weights
kimi-k2:1tdérivéInconnuInconnu262K1tools · open-weights
mistral-large-3:675bdérivéInconnuInconnu262K1tools · vision · open-weights
nemotron-3-nano:30bdérivéInconnuInconnu1.05M1tools · reasoning · open-weights
nemotron-3-superdérivéInconnuInconnu262K1tools · reasoning · open-weights
qwen3-coder:480bdérivéInconnuInconnu262K1tools · open-weights
qwen3-next:80bdérivéInconnuInconnu262K1tools · reasoning · open-weights
qwen3-vl:235bdérivéInconnuInconnu262K1tools · reasoning · vision · open-weights
qwen3-vl:235b-instructdérivéInconnuInconnu262K1tools · vision · open-weights
qwen3.5:397bdérivéInconnuInconnu262K1tools · reasoning · vision · open-weights

Frequently asked questions

How many AI models does ollama-cloud offer?

We track 5 canonical ollama-cloud models plus 16 community fine-tunes / derivatives (excluded from the main table). The list is recomputed daily from models.dev.

Which ollama-cloud model has the largest context window?

ministral-3:14b leads at 262K tokens. This is the total of prompt + completion.

Which ollama-cloud models support tool calling?

Multiple ollama-cloud models support tool calling, with cogito-2.1:671b being a popular pick. The capability column in the table above marks every model with ollama-cloud tool-calling support.

Which ollama-cloud models accept image input?

ministral-3:14b accepts image input. Other vision-capable ollama-cloud models are tagged 'vision' in the table above. See /capabilities/vision for a cross-vendor comparison.

What are the best alternatives to ollama-cloud?

Depends on the use case. For raw cost savings, look at /pricing/cheapest-llm-api. For agent-oriented workloads, /best/best-ai-model-for-agents. For long-document workflows, /best/best-long-context-llm.

How fresh is this ollama-cloud pricing data?

Daily. Our pipeline pulls models.dev each morning and rebuilds these pages on data change, so list-price moves and new model releases land within roughly 24 hours.

Dernière mise à jour :

Prices in USD per 1M tokens. Unknown means the provider does not publish per-token pricing.

Data is sourced from models.dev and normalized for comparison. Prices and capabilities may change. Always verify critical production decisions with the provider's official documentation.