Skip to main content

Qwen3.8 2.4T A95B

Qwen3.8 2.4T A95B is an open-weight sparse mixture-of-experts model from Qwen and the open-weight variant of Qwen3.8 Max, with 95 billion active parameters out of 2.4 trillion total.

Model card on Hugging Face
Input / output price
$2.00 / $6.00 per 1M
Context
1M tokens
Released
Aug 12, 2026
Agent setup

Paste into Claude Code, Cursor, or Codex

Help me set up the Respan gateway: fetch and follow https://www.respan.ai/docs/agent-setup.md. Use model "qwen/qwen3.8-2.4t-a95b".

Read docs

Providers

5 providers, cheapest first, OpenRouter last, priced per 1M tokens after gateway discounts.

ProviderInputOutput
Chuteschutes/qwen3.8-2.4t-a95b
$2.00/M$6.00/M
Concentrateconcentrate/qwen3.8-2.4t-a95b
$2.00/M$6.00/M
Novitanovita/qwen3.8-2.4t-a95b
$2.00/M$6.00/M
Qwenqwen/qwen3.8-2.4t-a95b
$2.00/M$6.00/M
OpenRouteropenrouter/qwen3.8-2.4t-a95b
$2.00/M$6.00/M

Is a provider down? OpenRouter status

Pricing

Averaged across 5 providers, in USD per 1M tokens after gateway discounts.

Average input
$2.00 per 1M
Average output
$6.00 per 1M
Average cache read
$0.25 per 1M
Average cache write
$2.50 per 1M

Cost by volume

Total cost from 0 to 1T tokens.

$2.00/MChutes, Concentrate, Novita, Qwen, and OpenRouter

Throughput and latency

30-day averages from requests through the Respan gateway. Under each figure, every model on the gateway by its average, this one in blue.

Output speed

Higher is better

12tokens/sacross providers

Faster than 22% of the other 599 models on the gateway

Time to first token

Lower is better

2.7sacross providers

Faster than 34% of the other 150 models on the gateway

Response latency

Lower is better

55sacross providers

Faster than 3% of the other 780 models on the gateway

Benchmarks

5 published scores from 2 sources, each linked to where it was published.

Published scores

BenchmarkScore
OSWorlddocs.modelstudio.console.alibabacloud.com86.1%

Apps

Use Qwen3.8 2.4T A95B in the tools you already run. Each guide points the app at the Respan gateway.

Setup guides for more apps are in the integration docs.

Qwen3.8 2.4T A95B FAQ

Short answers, built from the data on this page.

Qwen3.8 2.4T A95B is a model from Qwen, released on Aug 12, 2026. Qwen3.8 2.4T A95B is an open-weight sparse mixture-of-experts model from Qwen and the open-weight variant of Qwen3.8 Max, with 95 billion active parameters out of 2.4 trillion total.

On the Respan gateway, Qwen3.8 2.4T A95B costs $2.00 per 1M input tokens and $6.00 per 1M output tokens on every provider, after gateway discounts.

Qwen3.8 2.4T A95B is available through 5 providers: Chutes, Concentrate, Novita, Qwen, and OpenRouter.

Qwen3.8 2.4T A95B accepts up to 1M tokens of context on its largest provider route.

Point any OpenAI-compatible SDK at https://gateway.respan.ai/v1 with your Respan API key and set the model to "qwen/qwen3.8-2.4t-a95b". To set it up with a coding agent, copy the agent setup prompt at the top of this page.

Qwen3.8 2.4T A95B has 5 published benchmark scores, including OSWorld 86.1%, GPQA Diamond 92.6%, and BabyVision 82%. Each score links to where it was published; the data is collected by Respan.

Certified where it counts.

Built to meet the security and privacy standards that enterprise and healthcare teams require.

ISO 27001

The internationally recognized standard for information security management.

SOC 2

Secure, compliant management of your data across all of our systems.

GDPR

Operated under GDPR, the world's strictest standard for data privacy.

HIPAA

HIPAA compliant, with a BAA available for healthcare teams.

Works with your entire stack

Use Respan with your favorite frameworks and tools.

AnthropicAI21 LabsxAIVercel AI SDK
LangChainOpenRouterAssemblyAICursor
LiteLLMGroqBasetenMem0
CohereCogneeLlamaIndexFireworks
DeepSeekLinkupHaystackTogether AI
PerplexityInference.netPostHogRubyLLM
SlackMastraAzure OpenAIMistral
AWS BedrockMoonshotHyperspellBAML
ModaInstructorGoogle GeminiParasail
ReductoZapierAgnoNebius
OpenAINovita AIReplicateSuperagent

Built for AI agents.
Break less.
Ship more.