Magnum v4 72B
Magnum v4 72B is a community fine-tune. Behaviour and benchmarks track the upstream base model the fine-tune was trained from. Available via Anthracite. 32,768-token context. Mid-tier pricing. Inherits weights from an upstream open-weights base; benchmarks track the base model unless the fine-tuner publishes their own.
Magnum v4 72B is a efficient AI model from Anthracite. It costs $2.50 per million input tokens and $5.00 per million output tokens (blended $3.25/M), with a 32,768-token context window.
RatesUSD per million tokens. Blend is 70% input, 30% output, our calculation.
From OpenRouter's listing, read on 17 Nov 2026.
- Persona/tuning beyond the base model
- Persona/style adherence beyond the base model
- Specific domain (RP, instruction, etc.) tuning
- Inherits base-model capability
- Roleplay and creative chat
- Domain-specific assistants
- Custom persona deployments
Benchmarks
Price history
1 recorded change| Date | Rate | Was | Now | Change |
|---|---|---|---|---|
| 10 Nov 2026 | Input | $3.00 | $2.50 | -17% |
Rates per million tokens, as published by the provider or its router listing. Tracking runs since 3 May; anything earlier is not on record. See every tracked price change.
Frequently asked questions
How much does Magnum v4 72B cost?
Magnum v4 72B costs $2.50 per million input tokens and $5.00 per million output tokens, for a blended reference rate of $3.25 per million tokens.
What is Magnum v4 72B's context window?
Magnum v4 72B supports up to 32,768 tokens of context in a single request.
What is Magnum v4 72B best for?
Magnum v4 72B is well suited to Persona/tuning beyond the base model, Persona/style adherence beyond the base model and Specific domain (RP, instruction, etc.) tuning.
Who makes Magnum v4 72B?
Magnum v4 72B is developed and served by Anthracite.
