vs
RunInfra vs Dolphin
RunInfra serves curated open models and builds deployments. Dolphin serves one model very cheaply on a decentralized network of consumer GPUs.
By The Subconscious Team · Updated
RunInfra vs Dolphin: key differences
RunInfra offers hosted open models like Nemotron 3.5 Lightning 30B and Qwen 3.8 27B, coding plans from $10 a month, and an agent that builds endpoints for your own uploads up to 50 GB. Dolphin launched its API in October 2026 with DeepSeek V4.1 Flash at $0.01 in and $0.07 out on idle consumer GPUs, with no published speed, context or SLA, and signup through a crypto wallet and Telegram.
RunInfra fits developers who want a cheap open model inside agent tools or a custom deployment. Dolphin fits latency-tolerant background calls on its one model and products that need uncensored models. Both are young with little independent benchmarking.
What RunInfra and Dolphin 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
Dolphin
Dolphin began in 2023 as Eric Hartford's series of open-source, uncensored fine-tunes, trained to drop the refusals and baked-in guidelines of their base models so that the developer sets the rules through the system prompt. Current releases include Dolphin Llama 3.1 8B and Dolphin Mistral 24B Venice Edition, built with Venice, and the project publishes nearly 100 models on Hugging Face. It also runs a chat app, a Telegram bot and a synthetic data service that generates answers to commonly refused prompts.
Example models: DeepSeek V4.1 Flash, Dolphin Mistral 24B
Full Dolphin profileShould you choose RunInfra or Dolphin?
RunInfra vs Dolphin at a glance
| Attribute | RunInfra |  Dolphin |
|---|---|---|
| Model access | Open weights | Open weights, uncensored fine-tunes |
| Flagship models | Nemotron 3.5 Lightning 30B, Qwen 3.8 27B | DeepSeek V4.1 Flash, Dolphin Mistral 24B |
| Speed | ~541 tok/s on Nemotron 3.5 Lightning 30B (vendor); cold starts under 2s | Unknown |
| Price | From $0.05 in, $0.15 out; coding plans from $10 a month | $0.01 in, $0.07 out (DeepSeek V4.1 Flash) |
| Customization | Uploads up to 50 GB; auto-quantization | Own uncensored fine-tunes |
| Deployment | Model APIs, agent-built endpoints | Decentralized serverless API |
| Long context | Varies by model | Unknown |
Frequently asked questions
What is the difference between RunInfra and Dolphin?
RunInfra serves curated open models and builds deployments. Dolphin serves one model very cheaply on a decentralized network of consumer GPUs.
When should I choose RunInfra over Dolphin?
Flat-rate coding plans for agent CLIs; Custom model uploads and endpoints; Auto-tuned GPU and quantization choice.
When should I choose Dolphin over RunInfra?
Very cheap DeepSeek V4.1 Flash calls; Models without vendor-imposed refusals; Latency-tolerant background jobs.
Is RunInfra or Dolphin cheaper?
RunInfra: From $0.05 in, $0.15 out; coding plans from $10 a month. Dolphin: $0.01 in, $0.07 out (DeepSeek V4.1 Flash). The cheaper choice depends on the model and workload.
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.