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 |
|---|---|---|---|---|
| gemini-2.5-pro Unclassified | Not yet measured | — | — | $1.25 / $10 |
| gemini-3-flash-preview Unclassified | Not yet measured | — | — | $0.5 / $3 |
| gemini-3-pro-preview Unclassified | Not yet measured | — | — | $2 / $12 |
| gemini-3.1-flash-lite Unclassified | Not yet measured | — | — | $0.25 / $1.5 |
| gemini-3.1-flash-lite-preview Unclassified | Not yet measured | — | — | $0.25 / $1.5 |
| gemini-3.5-flash-lite Unclassified | Not yet measured | — | — | $0.3 / $2.5 |
| gemini-3.6-flash Unclassified | Not yet measured | — | — | $1.5 / $7.5 |
| gemini-3.8-flash Unclassified | Not yet measured | — | — | $0.75 / $3.75 |
| gemini-embedding-001 Unclassified | Not yet measured | — | — | $0.15 / $0 |
| glm-5.2 Unclassified | Not yet measured | — | — | $1.4 / $4.4 |
| google.gemma-3-12b-it Unclassified | Not yet measured | — | — | $0.09 / $0.29 |
| google.gemma-3-4b-it Unclassified | Not yet measured | — | — | $0.04 / $0.08 |
| gpt-5.2 Unclassified | Not yet measured | — | — | $1.75 / $14 |
| gpt-5.3-codex Unclassified | Not yet measured | — | — | $1.75 / $14 |
| gpt-oss-120b Unclassified | Not yet measured | — | — | $0.15 / $0.6 |
| gpt-oss-20b Unclassified | Not yet measured | — | — | $0.07 / $0.3 |
| llama3-3-70b Unclassified | Not yet measured | — | — | $0.72 / $0.72 |
| llama4-maverick-17b Unclassified | Not yet measured | — | — | $0.24 / $0.97 |
| llama4-scout-17b Unclassified | Not yet measured | — | — | $0.17 / $0.66 |
| magistral-small-2509 Unclassified | Not yet measured | — | — | $0.5 / $1.5 |