Inkling-Small vs Gemini 3 Flash Preview
API pricing, benchmark indices and specs — updated 19 October 2026.
thinkingmachines · A · Open weights
Params
266.0 B
Context
—
30d
884 K
apache-2.0 · commercial OK
google · B · API-only
Input / 1M
$0.50
Output / 1M
$3.00
AA index
26.3
proprietary · 1M context
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | Inkling-Small | Gemini 3 Flash Preview |
|---|---|---|
| Deployment | Open weights · also via API | API-only (closed weights) |
| Parameters | 266.0 B | n/a — API-only |
| Architecture | InklingForConditionalGeneration | n/a — API-only |
| Context length | 524,288 | 1,048,576 |
| Licence | apache-2.0 | Proprietary |
| Commercial use | Allowed | Per API terms |
| Languages | — | n/a — API-only |
| Downloads 30d | 884,226 | n/a — API-only |
| Downloads all time | 1.5 M | n/a — API-only |
| Quantizations on the Hub | SAFETENSORS | n/a — API-only |
| Gated | No | n/a — API-only |
| First seen on the Hub | 2026-07-27 | n/a — API-only |
| API input price / 1M tokens | $0.45 | $0.50 |
| API output price / 1M tokens | $1.20 | $3.00 |
| Est. cost per 1M input + 1M output tokens | $1.65 | $3.50 |
| Cached input / 1M tokens | $0.10 | $0.05 |
| AA Intelligence Index | 25.7 | 26.3 |
| AA Coding Index | 52.9 | — |
| AA Agentic Index | 23.5 | — |
| Max output tokens | 262,144 | 65,536 |
| API providers | 1 | 2 |
| Tool calling | Yes | Yes |
| Reasoning mode | Yes | Yes |
API cost
Estimated cost of 1M input + 1M output tokens via OpenRouter
Inkling-Small
$1.65
Gemini 3 Flash Preview
$3.50
Inkling-Small is 2.1× cheaper at list price.
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
Inkling-Small · fp16
625.5 GB / 24 GB