vs
RunInfra vs Inception
RunInfra serves mid-size open models and builds tuned deployments for you. Inception serves its own closed diffusion models built for fast output.
By The Subconscious Team · Updated
RunInfra vs Inception: key differences
RunInfra hosts a small library, including Nemotron 3.5 Lightning 30B and Qwen 3.8 27B, with coding plans from $10 a month that plug into Claude Code, Codex and other agent CLIs. Its agent benchmarks models across GPUs, tries quantized variants and ships an endpoint that scales to zero with cold starts under two seconds, and paid plans accept uploads up to 50 GB. Inception's Mercury 2.5 is a closed reasoning model with tool use and 260K context at $0.20 in and $0.75 out. Inception reports over 1,100 tokens per second; Artificial Analysis measures about 640.
RunInfra is the pick for flat-rate coding plans and deploying your own tuned open model without ML ops staff. Inception is the pick when raw output speed matters, like autocomplete or voice, and a closed single-vendor model is fine. Both sit below frontier quality.
What RunInfra and Inception do
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.
Example models: Nemotron 3.5 Lightning 30B, Qwen 3.8 27B
Full RunInfra profile
Inception
Inception builds diffusion large language models (dLLMs). Every other LLM on this list generates text one token at a time; Inception's Mercury models start from a rough draft of a whole block and refine it over a few passes, producing many tokens in parallel. That ties speed less to output length and lets the models run fast on ordinary NVIDIA GPUs rather than custom chips. The company was founded by professors from Stanford, UCLA and Cornell behind core work on diffusion, Flash Attention and DPO, and is led by Stanford's Stefano Ermon. It raised a $50M seed in November 2025 led by Menlo Ventures, with Mayfield, M12, NVentures, Snowflake and Databricks, plus Andrew Ng and Andrej Karpathy as angels.
Example models: Mercury 2.5, Mercury 2
Full Inception profileShould you choose RunInfra or Inception?
RunInfra vs Inception at a glance
| Attribute | RunInfra |  Inception |
|---|---|---|
| Model access | Open weights | Closed weights (Mercury dLLMs) |
| Flagship models | Nemotron 3.5 Lightning 30B, Qwen 3.8 27B | Mercury 2.5, Mercury 2 |
| Speed | ~541 tok/s on Nemotron 3.5 Lightning 30B (vendor); cold starts under 2s | 1,100+ tok/s (vendor); ~640 measured |
| Price | From $0.05 in, $0.15 out; coding plans from $10 a month | $0.20 in, $0.75 out (Mercury 2.5) |
| Customization | Uploads up to 50 GB; auto-quantization | Fine-tuning on request |
| Deployment | Model APIs, agent-built endpoints | Serverless API, Bedrock, Azure, private |
| Long context | Varies by model | 260K |
Frequently asked questions
What is the difference between RunInfra and Inception?
RunInfra serves mid-size open models and builds tuned deployments for you. Inception serves its own closed diffusion models built for fast output.
When should I choose RunInfra over Inception?
Flat-rate coding plans for agent CLIs; Deploying your own open model with auto-tuning; Voice pipelines without ML ops staff.
When should I choose Inception over RunInfra?
Very fast output for real-time loops; Cheap reasoning with tool use; Buying through Bedrock or Azure.
Is RunInfra or Inception cheaper?
RunInfra: From $0.05 in, $0.15 out; coding plans from $10 a month. Inception: $0.20 in, $0.75 out (Mercury 2.5). The cheaper choice depends on the model and workload.
Which has more context, RunInfra or Inception?
RunInfra: Varies by model. Inception: 260K.
Related comparisons
Running long-horizon agents?
If your agents run past 200K tokens, compare both against Subconscious. Our inference stack treats a long-horizon trace as the primary workload, so speed, cost, and accuracy hold up deep into the trace.