OpenBMB's compact multimodal model with strong image and video understanding at an efficient 8B scale.
OffRail routes requests to the best providers that are able to handle your prompt size and parameters.
OpenBMB's compact multimodal model with strong image and video understanding at an efficient 8B scale. You can access it through OffRail's OpenAI-compatible API with automatic provider routing, fallback, and cost analytics.
Pricing for MiniCPM-V 4.5 on OffRail starts at $0.66 per million input tokens and $1.11 per million output tokens, depending on the provider. The pricing table above always reflects the current per-provider rates.
MiniCPM-V 4.5 supports a context window of up to 32,000 tokens on its largest provider deployment.
MiniCPM-V 4.5 is served by Nebius AI through OffRail. Requests are automatically routed to the best available provider, with fallback when a provider has issues.
MiniCPM-V 4.5 supports soft JSON output, but not tool calling or strict JSON output schema.
MiniCPM-V 4.5 was released on August 26, 2025.