Qwen3-VL-30B-A3B-Thinking vs Mistral Large 3 2512
API pricing, benchmark indices and specs — updated 19 October 2026.
Qwen · A · Open weights
Params
31.1 B
Context
—
30d
16 K
apache-2.0 · commercial OK
mistralai · B · API-only
Input / 1M
$0.50
Output / 1M
$1.50
AA index
9.3
proprietary · 262.1K context
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | Qwen3-VL-30B-A3B-Thinking | Mistral Large 3 2512 |
|---|---|---|
| Deployment | Open weights · also via API | API-only (closed weights) |
| Parameters | 31.1 B | n/a — API-only |
| Architecture | Qwen3VLMoeForConditionalGeneration | n/a — API-only |
| Context length | 262,144 | 262,144 |
| Licence | apache-2.0 | Proprietary |
| Commercial use | Allowed | Per API terms |
| Languages | — | n/a — API-only |
| Downloads 30d | 15,613 | n/a — API-only |
| Downloads all time | 1.1 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 | 2025-09-30 | n/a — API-only |
| API input price / 1M tokens | $0.29 | $0.50 |
| API output price / 1M tokens | $1.00 | $1.50 |
| Est. cost per 1M input + 1M output tokens | $1.29 | $2.00 |
| Cached input / 1M tokens | — | $0.05 |
| AA Intelligence Index | 9.5 | 9.3 |
| AA Coding Index | — | 20.1 |
| AA Agentic Index | — | 1 |
| Max output tokens | 235,929 | 209,715 |
| API providers | 1 | 1 |
| Tool calling | Yes | Yes |
| Reasoning mode | Yes | No |
API cost
Estimated cost of 1M input + 1M output tokens via OpenRouter
Qwen3-VL-30B-A3B-Thinking
$1.29
Mistral Large 3 2512
$2.00
Qwen3-VL-30B-A3B-Thinking is 1.6× cheaper at list price.
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
Qwen3-VL-30B-A3B-Thinking · fp16
73.5 GB / 24 GB