vs
Baseten vs Dolphin
Baseten is production infrastructure for open and custom models with a 99.99% uptime SLA. Dolphin is a new decentralized network serving one cheap model on consumer GPUs.
By The Subconscious Team · Updated
Baseten vs Dolphin: key differences
Baseten serves about a dozen curated open models plus anything packaged with Truss, with the lowest measured time to first token, OpenAI and Anthropic-compatible endpoints, and self-host and HIPAA options. Dolphin's API launched in October 2026 with one model, DeepSeek V4.1 Flash, at $0.01 in and $0.07 out per million, served on idle consumer GPUs. Validators spot-check outputs against a trusted copy of the model, but Dolphin publishes no speed, context or SLA.
Baseten fits user-facing products and regulated buyers that need predictable latency and uptime. Dolphin fits cheap background jobs and teams that want uncensored models, if they can sign up with a crypto wallet and Telegram.
What Baseten and Dolphin do
Baseten
Baseten runs two products. Model APIs serve a curated set of about a dozen open models, including GLM 5.3, DeepSeek V4.1 Flash, DeepSeek V4 Pro 0813, Kimi K3 and gpt-oss 120B, over endpoints that speak both the OpenAI Chat Completions shape and the Anthropic Messages shape. That dual compatibility means an existing OpenAI or Claude SDK, or a coding agent, points at Baseten with a base URL change. Dedicated deployments take any model you package with the open-source Truss CLI and bill per GPU minute, with an H100 at about $6.50 an hour.
Example models: GLM 5.3, gpt-oss 120B
Full Baseten 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 Baseten or Dolphin?
Baseten vs Dolphin at a glance
| Attribute | Baseten |  Dolphin |
|---|---|---|
| Model access | Open weights, about a dozen curated | Open weights, uncensored fine-tunes |
| Flagship models | GLM 5.3, DeepSeek V4.1 Flash, Kimi K3, gpt-oss 120B | DeepSeek V4.1 Flash, Dolphin Mistral 24B |
| Speed | 0.49s TTFT, lowest measured | Unknown |
| Price | H100 about $6.50/hr dedicated | $0.01 in, $0.07 out (DeepSeek V4.1 Flash) |
| Customization | Deploy any model with Truss | Own uncensored fine-tunes |
| Deployment | Model APIs, dedicated, self-host | Decentralized serverless API |
| Long context | Varies by model | Unknown |
Frequently asked questions
What is the difference between Baseten and Dolphin?
Baseten is production infrastructure for open and custom models with a 99.99% uptime SLA. Dolphin is a new decentralized network serving one cheap model on consumer GPUs.
When should I choose Baseten over Dolphin?
User-facing apps that need low latency; Custom and fine-tuned model serving; Uptime SLA and regulated deployments.
When should I choose Dolphin over Baseten?
Very cheap background calls; Uncensored models without vendor refusals; Jobs that tolerate variable uptime.
Is Baseten or Dolphin cheaper?
Baseten: H100 about $6.50/hr dedicated. 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.