granite-4.0-h-micro vs GPT-3.5 Turbo
API pricing, benchmark indices and specs — updated 19 October 2026.
ibm-granite · A · Open weights
Params
3.2 B
Context
131,072
30d
9 K
apache-2.0 · commercial OK
openai · B · API-only
Input / 1M
$0.50
Output / 1M
$1.50
AA index
5.5
proprietary · 16.4K context
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | granite-4.0-h-micro | GPT-3.5 Turbo |
|---|---|---|
| Deployment | Open weights · also via API | API-only (closed weights) |
| Parameters | 3.2 B | n/a — API-only |
| Architecture | GraniteMoeHybridForCausalLM | n/a — API-only |
| Context length | 131,072 | 16,385 |
| Licence | apache-2.0 | Proprietary |
| Commercial use | Allowed | Per API terms |
| Languages | — | n/a — API-only |
| Downloads 30d | 9,011 | n/a — API-only |
| Downloads all time | 254 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 | 2025-09-16 | n/a — API-only |
| API input price / 1M tokens | $0.017 | $0.50 |
| API output price / 1M tokens | $0.11 | $1.50 |
| Est. cost per 1M input + 1M output tokens | $0.13 | $2.00 |
| Cached input / 1M tokens | — | — |
| AA Intelligence Index | 5.1 | 5.5 |
| AA Coding Index | — | 10.7 |
| AA Agentic Index | — | — |
| Max output tokens | 117,900 | 4,096 |
| API providers | 1 | 1 |
| Tool calling | No | Yes |
| Reasoning mode | No | No |
API cost
Estimated cost of 1M input + 1M output tokens via OpenRouter
granite-4.0-h-micro
$0.13
GPT-3.5 Turbo
$2.00
granite-4.0-h-micro is 15.5× cheaper at list price.
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
granite-4.0-h-micro · fp16 @ 128K ctx
15.2 GB / 24 GB