Compact Llama 3.2 3B for efficient inference.
OffRail routes requests to the best providers that are able to handle your prompt size and parameters.
Compact Llama 3.2 3B for efficient inference. You can access it through OffRail's OpenAI-compatible API with automatic provider routing, fallback, and cost analytics.
Pricing for Llama 3.2 3B Instruct on OffRail starts at $0.03 per million input tokens and $0.05 per million output tokens, depending on the provider. The pricing table above always reflects the current per-provider rates.
Llama 3.2 3B Instruct supports a context window of up to 32,768 tokens on its largest provider deployment.
Llama 3.2 3B Instruct is served by NovitaAI through OffRail. Requests are automatically routed to the best available provider, with fallback when a provider has issues.
Llama 3.2 3B Instruct supports soft JSON output, but not tool calling or strict JSON output schema.
Llama 3.2 3B Instruct was released on September 18, 2024.
Muse Spark 1.2
1,048,576 context$1.25 in / $4.25 out per 1M
Muse Spark 1.1
1,048,576 context$1.25 in / $4.25 out per 1M
Llama 3.1 Nemotron Ultra 253B
128,000 context$0.60 in / $1.80 out per 1M
Llama 4 Scout 17B Instruct
131,072 context$0.17 in / $0.59 out per 1M
Llama 4 Maverick 17B Instruct
1,048,576 context$0.24 in / $0.85 out per 1M
Llama 3.3 70B Instruct
131,072 context$0.13 in / $0.40 out per 1M