Consumer apps US

Poe.

Quora's multi-model platform — chat across many proprietary and open-weight bots from a single subscription, plus a creator tool for building custom bots.

At a glance

Service type: Consumer apps
Trust tier: Tier 2
Headquarters: US
OpenAI-compat: No
Open weights: Yes
Proprietary: Yes

When to pick Poe

Best for

End users — chat, projects, file uploads, agents, image gen all in one product.
Workflows that don't need a programmable API (writing, research, drafting).
Comparing models side-by-side in a single subscription (Poe).

Avoid for

Programmatic integration — use the maker's first-party API instead.
Workloads needing reproducible outputs across requests.

Models on Poe

Pricing + measured speed + self-host alternative, one row per model. Click a column header to sort.

1 models · 0 benchmarked

Model ↕	Maker ↕	Access ↕	$/M in ↕	$/M out ↕	Tokens/sec ↕	TTFT ↕	Self-host on ↕
Claude Sonnet 4.6	Anthropic	chat ui	—	—	—	—	API only	Open →

Peers in the same bucket

Sanity-check before you commit.

FAQ

Frequently asked.

How does Poe bill for inference?

Most inference providers bill per million input + output tokens. Some (like Replicate, fal.ai) use per-second billing where you pay for actual compute time on the underlying GPU. Per-token rates are listed on each model's access row.

Does Poe offer an OpenAI-compatible API?

Not by default. Use Poe's native SDK — most clients support a thin OpenAI compatibility wrapper if you need it.

Which models does Poe host?

See the model list on this page. Each row links to a per-model show page where you can compare across every provider that carries the same SKU.

What's the difference between Poe and a GPU rental host?

Poe hosts inference for you — you pay per token, the provider runs the GPU. GPU rental (Vast.ai, Lambda, RunPod) gives you the raw GPU at $/hr and you run the model yourself. Both have catalog pages on RentGPU; pick based on whether you want managed inference or full control.