Model catalog
O

Orpheus 3B 0.1 FT

Open weights

Orpheus 3B 0.1 FT is a speech model from Canopy Labs. Provider list price is $15 per M characters; on Allocate you pay $16.05 with the 7% transaction fee. The weights are open under Apache 2.0, so you can fine-tune it and own the result.

Pricing

Provider listOn Allocate
Price, per M characters$15$16.05

Token usage bills at the provider list price plus the 7% transaction fee. Prices checked 2026-07-08.

Price against its peers

Provider list prices per M characters, Orpheus 3B 0.1 FT against its nearest speech peers by price.

What a real workload costs

Synthesizing 10M characters of speech copy costs 10 × $15 = $150 at list, or $160.50 billed on Allocate with the 7% transaction fee included.

Orpheus 3B 0.1 FT is an open-weights model under the Apache 2.0 license. Fine-tune it on your own data and the weights stay inside your boundary; they belong to you.

Example usage

Point a route at canopy/orpheus-3b-0.1-ft and the endpoint never changes; swap the model behind it whenever you want.

api.allocate.network
curl https://api.allocate.network/v1/chat/completions \
  -H "Authorization: Bearer $ALLOCATE_KEY" \
  -d '{
    "model": "canopy/orpheus-3b-0.1-ft",
    "messages": [{"role": "user",
      "content": "Summarise the attached contract."}]
  }'
200 · canopy/orpheus-3b-0.1-ft · inside your boundary

Common questions

How much does Orpheus 3B 0.1 FT cost?

Provider list price is $15 per M characters. On Allocate you pay list plus the 7% transaction fee: $16.05.

Can I fine-tune Orpheus 3B 0.1 FT?

Yes. Orpheus 3B 0.1 FT is an open-weights model under the Apache 2.0 license. The license is permissive, so the fine-tuned weights are yours to use commercially. On Allocate the trained weights stay inside your boundary and belong to you.

How do I call Orpheus 3B 0.1 FT on Allocate?

Send canopy/orpheus-3b-0.1-ft in the model field of the OpenAI-compatible endpoint at api.allocate.network/v1, or point a route name (like prod/support-agent) at it so you can swap the model later without a deploy.