Models
Open weights, verified builds.
Every model is pinned by SHA-256 — a node that serves a different
file than the catalog says fails verification. Ask for a model by name, or by
class (auto:small) and let the mesh pick.
| Model | API id | Params | Context | Interactive | Batch |
|---|---|---|---|---|---|
| Llama 3.2 3B Instruct | flock/llama-3.2-3b-instruct |
3B | 128K | $0.04 | $0.028 |
| Qwen 2.5 1.5B Instruct | flock/qwen2.5-1.5b-instruct |
1.5B | 32K | $0.04 | $0.028 |
| Llama 3.1 8B Instruct | flock/llama-3.1-8b-instruct |
8B | 128K | $0.1 | $0.07 |
| Qwen 2.5 7B Instruct | flock/qwen2.5-7b-instruct |
7B | 128K | $0.1 | $0.07 |
| Mistral Small 3 24B | flock/mistral-small-24b-instruct-2501 |
24B | 32K | $0.3 | $0.21 |
| Qwen 2.5 32B Instruct | flock/qwen2.5-32b-instruct |
32B | 128K | $0.3 | $0.21 |
| Llama 3.3 70B Instruct | flock/llama-3.3-70b-instruct |
70B | 128K | $0.7 | $0.49 |
| Nomic Embed Text v1.5 | flock/nomic-embed-text-v1.5 |
137M | 8K | $0.01 | $0.007 |
Per million tokens (prompt + completion). The launch catalog — it grows with the mesh's hardware. Want a model that isn't here? Tell us.