Serving provider
Neurometric
Neurometric-managed model deployments, including task-optimized models. Published task evidence shows where each model has been evaluated.
← All providers
Serving capacity can use Amazon Bedrock, GCP, Together AI, and self-hosted GPUs. Availability varies by model.
59 models with current observed prices · 7 with published task results
| Model | Evidence | Cheapest passing | Median quality | Input / output per 1M |
|---|---|---|---|---|
| minimax-m2 Unclassified | Not yet measured | — | — | $0.3 / $1.2 |
| ministral-3-14b Unclassified | Not yet measured | — | — | $0.2 / $0.2 |
| mistral-7b Unclassified | Not yet measured | — | — | $0.15 / $0.2 |
| mistral-large-2402 Unclassified | Not yet measured | — | — | $8 / $24 |
| mistral-large-3-675b Unclassified | Not yet measured | — | — | $0.5 / $1.5 |
| mistral.ministral-3-3b-instruct Unclassified | Not yet measured | — | — | $0.1 / $0.1 |
| mistral.ministral-3-8b-instruct Unclassified | Not yet measured | — | — | $0.15 / $0.15 |
| muse-glimmer-30B Unclassified | Not yet measured | — | — | $0.35 / $1.5 |
| nemotron-nano-12b-v2 Unclassified | Not yet measured | — | — | $0.2 / $0.6 |
| nemotron-nano-3-30b Unclassified | Not yet measured | — | — | $0.06 / $0.24 |
| nova-2-lite Unclassified | Not yet measured | — | — | $0.3 / $2.5 |
| nova-lite Unclassified | Not yet measured | — | — | $0.06 / $0.24 |
| nova-pro Unclassified | Not yet measured | — | — | $0.8 / $3.2 |
| qwen3-32b Unclassified | Not yet measured | — | — | $0.15 / $0.6 |
| qwen3-coder-30b-a3b Unclassified | Not yet measured | — | — | $0.15 / $0.6 |
| qwen3-coder-480b-a35b Unclassified | Not yet measured | — | — | $0.22 / $1.8 |
| qwen3-next-80b-a3b Unclassified | Not yet measured | — | — | $0.15 / $1.2 |
| qwen3-vl-235b-a22b Unclassified | Not yet measured | — | — | $0.53 / $2.66 |
| qwen3.5-9B Unclassified | Not yet measured | — | — | $0.17 / $0.25 |