# Fireworks AI vs Boundless

> Fireworks sells fast open-model inference with SFT, DPO and RL fine-tuning. Boundless tunes and runs open models for you but offers no fine-tuning.

Canonical: https://www.subconscious.dev/compare/fireworks-vs-boundless · By The Subconscious Team · Updated October 29, 2026

## How they compare

Fireworks serves 400+ models with full 1M context on DeepSeek V4.1 Flash, GLM 5.3 and Kimi K3, and third-party tests put it at 167 to 174 tokens per second on DeepSeek V4 Pro. It runs SFT, DPO and reinforcement fine-tuning, serves fine-tunes at base price, holds SOC 2, HIPAA and ISO certifications, and rents dedicated H100s at $8 an hour. Boundless also offers 1M context on those three models. Vercel's AI Gateway measured it at 121 tokens per second on DeepSeek V4.1 Flash, 134 on GLM-5.3 and 138 on Kimi K3, and Boundless publishes no benchmarks of its own.

Fireworks is the pick for post-training an open model and serving it at base price. Boundless fits teams that want engineers to pick a model on their evals and run it on reserved capacity against uptime, throughput and time-to-first-token targets in the contract. It also resells GPT and Claude through the same OpenAI and Anthropic compatible API.

## What each one does

### Fireworks AI

Fireworks AI was founded in 2022 by former Meta PyTorch engineers led by CEO Lin Qiao, and it sells speed on open models. Its custom serving stack has posted 167 to 174 tokens per second on DeepSeek V4 Pro in third-party measurements, several times what most GPU peers hit on the same model. The catalog holds 400+ models across text, vision, audio and embeddings, served through an OpenAI compatible API. In July 2026 it raised a $1.505B Series D at a $17.5B valuation, with a reported $1B+ run rate and 40T+ tokens a day.

### Boundless

Boundless launched in September 2026 as an inference partner for AI-native startups. It sells two things. The Model API serves pre-tuned models on shared capacity, billed per token from prepaid credits with a budget per API key. Tailored inference reserves capacity for one customer, and Boundless engineers pick the model on the customer’s own evals, tune precision, batching, caching, speculative decoding and parallelism, then run the deployment against uptime, throughput and latency targets written into the contract. A free two-week evaluation tests those targets on real traffic against the customer’s current provider first.

## Which is best, and when

### Choose Fireworks AI for

- SFT, DPO and RL fine-tuning
- Fine-tunes served at base price
- Buyers who need SOC 2 or HIPAA

### Choose Boundless for

- Hands-off tuning on reserved capacity
- GPT and Claude on the same API
- A free trial against your current provider

## At a glance

| Attribute | Fireworks AI | Boundless |
|---|---|---|
| Model access | Open weights | Open weights, plus closed GPT and Claude |
| Flagship models | DeepSeek V4.1 Flash, GLM 5.3, Kimi K3 | GLM-5.3, DeepSeek V4.1 Flash, Kimi K3 |
| Speed | 167–174 tok/s on DeepSeek V4 Pro | 342 tok/s on DeepSeek V4.1 Flash 1017 (Vercel) |
| Price | Fine-tunes served at base price | $0.04–$2.30 in, $0.21–$11.40 out per 1M (open) |
| Customization | SFT, DPO, RFT; Training API | Serving-stack tuning, no fine-tuning |
| Deployment | Serverless, dedicated GPUs | Serverless API, reserved tailored capacity |
| Long context | Full 1M on DeepSeek V4.1 Flash, GLM 5.3 | 1M context on most models |

## FAQ

### What is the difference between Fireworks AI and Boundless?

Fireworks sells fast open-model inference with SFT, DPO and RL fine-tuning. Boundless tunes and runs open models for you but offers no fine-tuning.

### When should I choose Fireworks AI over Boundless?

SFT, DPO and RL fine-tuning; Fine-tunes served at base price; Buyers who need SOC 2 or HIPAA.

### When should I choose Boundless over Fireworks AI?

Hands-off tuning on reserved capacity; GPT and Claude on the same API; A free trial against your current provider.

### Is Fireworks AI or Boundless cheaper?

Fireworks AI: Fine-tunes served at base price. Boundless: $0.04–$2.30 in, $0.21–$11.40 out per 1M (open). The cheaper choice depends on the model and workload.

### Which has more context, Fireworks AI or Boundless?

Fireworks AI: Full 1M on DeepSeek V4.1 Flash, GLM 5.3. Boundless: 1M context on most models.

## Running long-horizon agents?

If your agents run past 200K tokens, compare both against Subconscious: [Subconscious vs Fireworks AI](https://www.subconscious.dev/compare/subconscious-vs-fireworks.md), [Subconscious vs Boundless](https://www.subconscious.dev/compare/subconscious-vs-boundless.md).

Full profiles: [Fireworks AI](https://www.subconscious.dev/providers/fireworks.md), [Boundless](https://www.subconscious.dev/providers/boundless.md).