Kokoro 82M
Open weightsKokoro 82M is a speech model from Hexgrad. Provider list price is $4 per M characters; on Allocate you pay $4.28 with the 7% transaction fee. The weights are open under Apache 2.0, so you can fine-tune it and own the result.
Pricing
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, Kokoro 82M against its nearest speech peers by price.
What a real workload costs
Synthesizing 10M characters of speech copy costs 10 × $4 = $40 at list, or $42.80 billed on Allocate with the 7% transaction fee included.
Kokoro 82M 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 hexgrad/kokoro-82m and the endpoint never changes; swap the model behind it whenever you want.
curl https://api.allocate.network/v1/chat/completions \ -H "Authorization: Bearer $ALLOCATE_KEY" \ -d '{ "model": "hexgrad/kokoro-82m", "messages": [{"role": "user", "content": "Summarise the attached contract."}] }'
Common questions
How much does Kokoro 82M cost?
Provider list price is $4 per M characters. On Allocate you pay list plus the 7% transaction fee: $4.28.
Can I fine-tune Kokoro 82M?
Yes. Kokoro 82M 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 Kokoro 82M on Allocate?
Send hexgrad/kokoro-82m 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.