Models
The catalog is short on purpose: a few small open-weight models, each served under a configuration we publish in full. The human-readable version is at /models.
Model ids
Ids are slugs of the form tokencannon/<name>, for example tokencannon/qwen3-0.6b. They are stable across upstream repository renames.
Listing models
shell
curl https://main-api.dev.tokencannon.io/v1/models \
-H "Authorization: Bearer $TOKENCANNON_API_KEY"The response is the OpenAI list shape ({ object: "list", data: [...] }) with the extra fields below on every entry.
Configuration fields
| Field | Meaning |
|---|---|
id | The stable slug you pass as `model`. |
hf_repo | The Hugging Face repository the weights come from. |
hf_revision | The exact commit we serve. Never a branch name. |
dtype | Weight precision as loaded, e.g. bfloat16. |
quantization | Quantization scheme, or `none`. |
context_len | The context we allocate KV cache for, in tokens. |
engine | The serving engine. |
engine_version | Its pinned version. |
price_in_micros_per_mtok | Input price in micro-dollars per million tokens. |
price_out_micros_per_mtok | Output price in micro-dollars per million tokens. Reasoning tokens are output. |
price_cache_read_micros_per_mtok | Price for prompt tokens served from the prefix cache. |
price_cache_write_micros_per_mtok | Price for prompt tokens written into the cache ($0 under automatic caching). |
status | Whether the model is currently accepting requests. |