Open-weight sparse MoE (2.4T total, 95B active), the open-weight twin of Qwen3.8 Max for coding, research, complex reasoning, and agentic workflows
Qwen3.8 2.4T A95B by alibaba is offered by 20 providers on this page. Its reference price is $2.50 per 1M input tokens and $6.25 per 1M output tokens. The lowest paid channel is IteraCompute at $1.95 / $5.95 per 1M, about 1.3× below the reference price. That channel is a third-party gateway, so confirm its availability and rate limits before depending on it.
Artificial Analysis rates it 39.9 on the Intelligence Index, with 71.9 for coding and 50.1 for agentic tasks. Against its lowest blended price of $2.95 per 1M, that is roughly 14 index points per dollar, which is the value ratio the leaderboards rank on. Median output speed is 38 tokens per second, with 2.77s to the first token. Running one task of the Artificial Analysis suite costs about $2.1559, which reflects how many tokens its reasoning consumes rather than the unit price alone.
The context window is 262,144 tokens at the reference host, but hosts report different limits, from 262,000 to 1,049,000, so the usable window depends on the provider you pick. It supports reasoning, tool use, and structured output. Accepted input modalities are Text and Image. The weights are open, so it can also be self-hosted or served through a gateway of your choice. Providers report the capability flags inconsistently, so verify a specific feature against the host you plan to use.
Quality is independently evaluated by Artificial Analysis. Speed/latency are model-level medians.
| Provider | Tier | Input | Output | Cache read | Cache write | Context | Output limit | Status |
|---|---|---|---|---|---|---|---|---|
| IteraCompute | Gateway | $1.95 | $5.95 | $0.20 | — | 970,000 ⚠ | 131,072 | |
| Deep Infra Qwen/Qwen3.8-2.4T-A95B | Cloud | $2.00 | $6.00 | $0.20 | — | 262,144 | 131,072 | |
| SiliconFlow Qwen/Qwen3.8-2.4T-A95B | Cloud | $2.00 | $6.00 | $0.25 | — | 1,049,000 ⚠ | 131,000 | |
| Kilo Gateway | Gateway | $2.00 | $6.00 | $0.25 | $2.50 | 1,000,000 ⚠ | 131,072 | |
| OpenRouter | Gateway | $2.00 | $6.00 | $0.25 | — | 1,048,576 ⚠ | 131,072 | |
| Vercel AI Gateway | Cloud | $2.00 | $6.00 | $0.25 | — | 262,144 | 128,000 | |
| Charm Hyper | Gateway | $2.00 | $6.00 | $0.25 | — | 1,000,000 ⚠ | 128,000 | |
| Fireworks AI accounts/fireworks/models/qwen3p8-2p4t-a95b | Cloud | $2.00 | $6.00 | $0.25 | — | 262,144 | 131,072 | |
| AIHubMix | Gateway | $2.00 | $6.00 | $0.50 | — | 262,000 ⚠ | 262,000 | |
| Eden AI | Gateway | $2.00 | $6.00 | $0.25 | $2.50 | 1,000,000 ⚠ | 131,072 | |
Sorted by blended price (input×0.75 + output×0.25) asc. The official channel always shows regardless of rank. Whether a gateway's low price is actually usable can't be verified.
Interleaved thinking (reasoning between tool calls) is declared by 3 of 20 providers.
2 / 20 providers expose no reasoning control (reasoning_options: []).
Individual evaluations run by Artificial Analysis, on the same reasoning tier as the intelligence score above. Each benchmark has its own task set and harness, so rows are not comparable with one another. The Intelligence Index above draws on a different, newer set of evaluations.