Model Catalog › openrouter

Qwen: Qwen3.8 2.4T A95B

qwen/qwen3.8-2.4t-a95b

CHAT High tier Reasoning Open-weight

Qwen: Qwen3.8 2.4T A95B (qwen/qwen3.8-2.4t-a95b) is a chat model from openrouter with a 1.0M-token context window; open-weight; capabilities tools, reasoning; input text; output text.

1.0MContext
131.1KMax output
$2$ / 1M in
38.27tok / s

Pricing

Input
$2 / 1M tokens
Output
$6 / 1M tokens
Currency
USD
Note
Indicative US list price — verify with the vendor.

Indicative US list price — a reference only, verify with the vendor. Source: litellm. Last verified 2026-09-26.

Performance

Throughput
38.27 tokens/s
Latency (TTFT)
1.935 s

Cited speed metrics — a reference, verify at the source. Source: Artificial Analysis. Last verified 2026-10-30.

Specifications

Context window
1,048,576 tokens (1.0M)
Max output
131,072 tokens
Weights
Open-weight
Input modalities
text
Output modalities
text
Release date
2026-08-12

Capabilities

tools reasoning

Provenance

artificial-analysiscommittedmodels-devopenrouter-api
Last verified: 2026-10-30

Related models

MoonshotAI: Kimi K3.1 Pro
moonshotai/kimi-k3.1-pro
openrouter · CHAT · 1.0M ctx
MoonshotAI: Kimi K3
moonshotai/kimi-k3
openrouter · CHAT · 1.0M ctx
Meta: Muse Wonder
meta/muse-wonder
openrouter · CHAT · 1.0M ctx
xAI: Grok 4.5
x-ai/grok-4.5
openrouter · CHAT · 500K ctx
Meta: Muse Spark 1.3
meta/muse-spark-1.3
openrouter · CHAT · 1.0M ctx
SpaceXAI: Grok 4.7
x-ai/grok-4.7
openrouter · CHAT · 500K ctx