Qwen3-Coder-480B-A35B-Instruct vs Mercury 2.5

API pricing, benchmark indices and specs — updated 19 October 2026.

Qwen · A · Open weights

Params

480.2 B

Context

262,144

30d

54 K

apache-2.0 · commercial OK

inception · B · API-only

Input / 1M

$0.04

Output / 1M

$0.15

AA index

12.3

proprietary · 260K context

Specification comparison

Differences are highlighted; identical values are muted.

Specification	Qwen3-Coder-480B-A35B-Instruct	Mercury 2.5
Deployment	Open weights · also via API	API-only (closed weights)
Parameters	480.2 B	n/a — API-only
Architecture	Qwen3MoeForCausalLM	n/a — API-only
Context length	262,144	260,000
Licence	apache-2.0	Proprietary
Commercial use	Allowed	Per API terms
Languages	—	n/a — API-only
Downloads 30d	54,127	n/a — API-only
Downloads all time	1.2 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	2025-07-22	n/a — API-only
API input price / 1M tokens	$0.30	$0.04
API output price / 1M tokens	$1.00	$0.15
Est. cost per 1M input + 1M output tokens	$1.30	$0.19
Cached input / 1M tokens	$0.10	$0.004
AA Intelligence Index	11.9	12.3
AA Coding Index	—	—
AA Agentic Index	—	—
Max output tokens	65,536	65,536
API providers	3	1
Tool calling	Yes	Yes
Reasoning mode	No	Yes

Estimated cost of 1M input + 1M output tokens via OpenRouter

Qwen3-Coder-480B-A35B-Instruct $1.30

Mercury 2.5 $0.19

Mercury 2.5 is 6.8× cheaper at list price.

On RTX 4090 · 24 GB · 8K context unless noted

Qwen3-Coder-480B-A35B-Instruct · fp16 @ 256K ctx 3,361.6 GB / 24 GB

❌ Won’t fit