granite-4.2-8b vs Mercury 2
API pricing, benchmark indices and specs — updated 19 October 2026.
ibm-granite · A · Open weights
Params
8.8 B
Context
131,072
30d
80 K
apache-2.0 · commercial OK
inception · B · API-only
Input / 1M
$0.25
Output / 1M
$0.75
AA index
10.8
proprietary · 128K context
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | granite-4.2-8b | Mercury 2 |
|---|---|---|
| Deployment | Open weights · also via API | API-only (closed weights) |
| Parameters | 8.8 B | n/a — API-only |
| Architecture | GraniteForCausalLM | n/a — API-only |
| Context length | 131,072 | 128,000 |
| Licence | apache-2.0 | Proprietary |
| Commercial use | Allowed | Per API terms |
| Languages | 12 | n/a — API-only |
| Downloads 30d | 80,469 | n/a — API-only |
| Downloads all time | 192 K | n/a — API-only |
| Quantizations on the Hub | SAFETENSORS | n/a — API-only |
| Gated | No | n/a — API-only |
| First seen on the Hub | 2026-08-07 | n/a — API-only |
| API input price / 1M tokens | $0.06 | $0.25 |
| API output price / 1M tokens | $0.25 | $0.75 |
| Est. cost per 1M input + 1M output tokens | $0.31 | $1.00 |
| Cached input / 1M tokens | $0.015 | $0.025 |
| AA Intelligence Index | 11.1 | 10.8 |
| AA Coding Index | 22.4 | 31.1 |
| AA Agentic Index | 1.3 | 1.6 |
| Max output tokens | 117,964 | 50,000 |
| API providers | 2 | 1 |
| Tool calling | Yes | Yes |
| Reasoning mode | Yes | Yes |
API cost
Estimated cost of 1M input + 1M output tokens via OpenRouter
granite-4.2-8b
$0.31
Mercury 2
$1.00
granite-4.2-8b is 3.2× cheaper at list price.
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
granite-4.2-8b · fp16 @ 128K ctx
40.9 GB / 24 GB