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. It is suited for coding, research, complex reasoning, and agentic workflows.
Modalities
In / Out Price
$2 / $6per 1M
Context
1M
Released
Aug 12, 2026
Different companies host the same model. OpenRouter routes your request to one of them based on the routing mode you pick — Balanced (price + speed), Nitro (fastest), or Exacto (highest tool-calling accuracy).
The average price customers actually pay for this model, next to the prices providers post. Caching and discounts mean the price actually paid is often well below the listed one.
Throughput is how fast the model writes (tokens per second — higher is better). Latency is total round-trip time (lower is better). TTFT is time-to-first-token — how long before you see anything appear (lower is better).
Uptime is the percentage of the past 3 days that at least one provider was responding to requests. Availability is the percentage of time that inference was successfully served. OpenRouter continuously monitors and uses the next-best provider when one returns an error.
Scores on standardized evaluations. Higher percentages are better — and rank percentile shows where this model lands among all models on OpenRouter.
Public apps that send the most traffic to this model. Good signal for what real production workloads look like — and a hint at which use cases this model is best suited for.
Token volume and request traffic to this model over time.
Drop-in code to call this model. OpenRouter's API is OpenAI-compatible — most SDKs work by just swapping the base URL. The only thing that changes between models is the model slug below.
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. It is suited for coding, research, complex reasoning, and agentic workflows.
Qwen3.8 2.4T A95B costs $2.00/M input tokens and $6.00/M output tokens, with separate rates for Cache Read at $0.20/M tokens.
Qwen3.8 2.4T A95B has a 1,048,576 token context window. It supports up to 52,429 completion tokens.
Yes. Qwen3.8 2.4T A95B accepts tools and tool_choice for function calling. It also supports structured outputs via a JSON schema in response_format.
Qwen3.8 2.4T A95B is served by 7 providers on OpenRouter: DigitalOcean, DeepInfra, Modal, SiliconFlow, Alibaba Cloud Int., Together and Venice. Requests are routed to the best available provider, with automatic failover to the others, and you can pin or exclude providers with provider routing.
Qwen3.8 2.4T A95B was released on August 12, 2026.
| $2.00 | $6.00 | $0.20 | -- | -- | 1.52s | 73 tps | ||
| $2.00 | $6.00 | $0.20 | -- | -- | 1.48s | 97 tps | ||
| $2.00 | $6.00 | $0.25 | -- | -- | 1.71s | 94 tps | ||
| $2.00 | $6.00 | $0.25 | -- | -- | 2.32s | 53 tps | ||
| $2.00 | $6.00 | $0.25 | $2.50 | $0.17 | 1.28s | 33 tps | ||
| $2.50 | $6.25 | $0.50 | -- | -- | 4.98s | 76 tps | ||
| $2.50 | $7.50 | $0.3125 | -- | -- | 2.72s | 29 tps |
Throughput
97tok/s
P50, best across providers
Latency
1.28s
P50, best provider
100.00%
99.38%
When an error occurs in an upstream provider, we can recover by routing to another healthy provider, if your request filters allow it. You can access per-provider uptime data programmatically through the Endpoints API. Learn more about our load balancing and customization options.