Last refreshed 2026-11-19. Next refresh: weekly.
Why use Olala 1.0 mini 7A1B on OVHcloud AI Endpoints?
OVHcloud AI Endpoints offers Olala 1.0 mini 7A1B with free input token pricing. OVHcloud’s hosted model inference API.
Input / 1M
Free
Output / 1M
Free
Cache
Not sourced
Batch
Not sourced
Setup recipe
Docs fallbackInstall
Use the provider REST API or SDKAuth
Create a provider API keyCall
model: Olala-v1.0-mini-7A1BModel ID
Olala-v1.0-mini-7A1BRequest example
Curated snippets for this provider are not sourced yet. Use OVHcloud AI Endpoints documentation with model ID
Olala-v1.0-mini-7A1B.Gotchas
- Use provider model ID "Olala-v1.0-mini-7A1B", not the LLMReference slug "olala-v1.0-mini-7a1b".
Pricing
| Type | Price (per 1M) |
|---|---|
| Input tokens | Free |
| Output tokens | Free |
Capabilities
ReasoningJSON / Tool use
About Olala 1.0 mini 7A1B
Olala 1.0 mini 7A1B is OVHcloud’s post-trained reasoning and tool-use language model. It uses a hybrid Mamba-3 and attention architecture with mixture-of-experts layers. Public weights are licensed under Apache 2.0.
Model Specs
Released2026-11-19
Parameters6.8B (1B active)
Context32K