# RunInfra vs General Compute

> RunInfra sells cheap open models and an agent that builds GPU deployments. General Compute serves open models with decode on ASICs.

Canonical: https://www.subconscious.dev/compare/runinfra-vs-general-compute · By The Subconscious Team · Updated October 27, 2026

## How they compare

RunInfra's hosted library has five models, from Nemotron 3.5 Lightning 30B at $0.05 in and $0.15 out per million tokens to DeepSeek V4.1 Flash at $0.14 in and $0.58 out, behind one key for the OpenAI and Anthropic SDKs. Coding plans start at $10 a month. Its deployment agent benchmarks GPUs from L4 to B200, tries quantized variants and ships endpoints that scale to zero. General Compute runs decode on Cerebras, SambaNova and other ASICs, and in its own benchmark measured over 1,000 tokens per second on GPT-OSS 120B, which it sells at $0.21 in and $0.79 out.

Pick RunInfra for a cheap flat-rate model in Claude Code or Codex, or a tuned GPU endpoint built without ML ops staff. Pick General Compute when output speed on larger models like MiniMax M2.7 matters more than the lowest price, or when you need dedicated racks with a throughput SLA.

## What each one does

### RunInfra

RunInfra pitches open models built for agents, with two ways in. Its hosted Model APIs serve a five-model library, including Nemotron 3.5 Lightning 30B, Qwen 3.8 27B, Ornith 1.5 35B, GLM 5.3 Flash and DeepSeek V4.1 Flash, behind one key that works with both the OpenAI and Anthropic SDKs. Prices run from $0.05 in and $0.15 out on Nemotron to $0.14 in and $0.58 out on DeepSeek V4.1 Flash, and cached input starts at $0.01. Coding plans start at $10 a month with limits that reset every five hours and every week, and they plug into Claude Code, Codex, OpenCode, Cline, Aider and dozens of other agent CLIs.

### General Compute

General Compute is a San Francisco inference cloud built on alternative chips. It splits each request across hardware, with NVIDIA GPUs handling prefill and ASICs from Cerebras, SambaNova, Positron AI and d-Matrix handling decode. In its own open benchmark on GPT-OSS 120B it measured 1,025 to 1,234 output tokens per second against 100 to 121 on an unnamed GPU cloud, and up to 16.2x faster end to end. Founders Finn Puklowski and Jason Goodison raised a $15M seed led by FUSE, an up to $400M debt facility from Upper90 and, on October 27, 2026, a $100M Series A co-led by Blackbird and Abstract.

## Which is best, and when

### Choose RunInfra for

- Flat-rate coding plans from $10 a month
- Automated GPU benchmarking and quantization
- Scale-to-zero custom endpoints

### Choose General Compute for

- Fast decode on larger open models
- Private fine-tuned checkpoints
- Dedicated racks with SLAs

## At a glance

| Attribute | RunInfra | General Compute |
|---|---|---|
| Model access | Open weights | Open weights |
| Flagship models | Nemotron 3.5 Lightning 30B, Qwen 3.8 27B | MiniMax M2.7, DeepSeek V3.2, GPT-OSS 120B |
| Speed | ~541 tok/s on Nemotron 3.5 Lightning 30B (vendor); cold starts under 2s | 1,000+ tok/s on GPT-OSS 120B (vendor) |
| Price | From $0.05 in, $0.15 out; coding plans from $10 a month | $0.21–$0.28 in, $0.38–$1.20 out per 1M |
| Customization | Uploads up to 50 GB; auto-quantization | Custom LoRA and fine-tuned checkpoints |
| Deployment | Model APIs, agent-built endpoints | Serverless API, dedicated racks, bare metal |
| Long context | Varies by model | 192K (MiniMax M2.7) |

## FAQ

### What is the difference between RunInfra and General Compute?

RunInfra sells cheap open models and an agent that builds GPU deployments. General Compute serves open models with decode on ASICs.

### When should I choose RunInfra over General Compute?

Flat-rate coding plans from $10 a month; Automated GPU benchmarking and quantization; Scale-to-zero custom endpoints.

### When should I choose General Compute over RunInfra?

Fast decode on larger open models; Private fine-tuned checkpoints; Dedicated racks with SLAs.

### Is RunInfra or General Compute cheaper?

RunInfra: From $0.05 in, $0.15 out; coding plans from $10 a month. General Compute: $0.21–$0.28 in, $0.38–$1.20 out per 1M. The cheaper choice depends on the model and workload.

### Which has more context, RunInfra or General Compute?

RunInfra: Varies by model. General Compute: 192K (MiniMax M2.7).

## Running long-horizon agents?

If your agents run past 200K tokens, compare both against Subconscious: [Subconscious vs RunInfra](https://www.subconscious.dev/compare/subconscious-vs-runinfra.md), [Subconscious vs General Compute](https://www.subconscious.dev/compare/subconscious-vs-general-compute.md).

Full profiles: [RunInfra](https://www.subconscious.dev/providers/runinfra.md), [General Compute](https://www.subconscious.dev/providers/general-compute.md).