All comparisons


| Visit Crun | Visit Magnitude | |
|---|---|---|
| What it costs | ||
| Pricing | Paid | Open source |
| Pricing details | Prepaid credits from $5 (200 credits per dollar), improving to 206 at $50, 212 at $500 and 224 at $1,250 - higher-tier plans also unlock lower per-model costs | Free and Apache-2.0. Models run on your own machine, so there are no token costs, API keys or rate limits, and there is no paid tier or hosted option. |
| Price range | Usage based, no flat monthly plan | $0/mo |
| Free option | No free option | Free tier |
| What it is | ||
| What it does | Single API covering 400+ video, image, audio and LLM models including Veo, Seedance, Kling, Nano Banana, GPT, Claude and Gemini, on one prepaid credit balance. | An Apache-2.0 inference server that profiles your hardware, recommends models that fit with estimated tokens per second, and wires them into the agent you use. |
What it costs
- Pricing
- Paid
- Pricing details
- Prepaid credits from $5 (200 credits per dollar), improving to 206 at $50, 212 at $500 and 224 at $1,250 - higher-tier plans also unlock lower per-model costs
- Price range
- Usage based, no flat monthly plan
- Free option
- No free option
What it is
- What it does
- Single API covering 400+ video, image, audio and LLM models including Veo, Seedance, Kling, Nano Banana, GPT, Claude and Gemini, on one prepaid credit balance.
What it costs
- Pricing
- Open source
- Pricing details
- Free and Apache-2.0. Models run on your own machine, so there are no token costs, API keys or rate limits, and there is no paid tier or hosted option.
- Price range
- $0/mo
- Free option
- Free tier
What it is
- What it does
- An Apache-2.0 inference server that profiles your hardware, recommends models that fit with estimated tokens per second, and wires them into the agent you use.
Read the full reviews
What each one is actually like to use, tested by hand rather than summarised from the vendor’s own page.
























