Price first — DeepSeek V4 Pro is cheaper on both sides
DeepSeek V4 Pro at $1.80 input / $3.60 output per 1M tokens. A95B at $2.00 / $6.00. On a 1:3 input:output workload the blended rate is $2.70 on V4 Pro against $5.00 on A95B — V4 Pro is 46% cheaper on the same workload. The gap holds at 1:1 ($2.70 vs $4.00) and widens at 1:9 ($1.98 vs $2.40) because V4 Pro's output is half the price.
| Workload (input:output) | Qwen3.8-2.4T-A95B | DeepSeek V4 Pro | Saving on V4 Pro |
|---|---|---|---|
| 1:1 (chat-shaped) | $4.00 / 1M blended | $2.70 / 1M blended | 32% |
| 1:3 (agent-shaped) | $5.00 / 1M blended | $2.70 / 1M blended | 46% |
| 1:9 (long-output) | $2.40 / 1M blended | $1.98 / 1M blended | 18% |
| Input only (rerank / classify) | $2.00 / 1M | $1.80 / 1M | 10% |
| Output only (synthesis) | $6.00 / 1M | $3.60 / 1M | 40% |
Both are open-weight frontier MoE checkpoints
A95B: 2.4T total parameters, 95B active per token, 262K native context extensible to 1M via YaRN. DeepSeek V4 Pro: published in DeepSeek V4 series as the Pro tier; exact parameter count and active count not consistently reported by the vendor. Both ship under open-weight terms. Both route through OneInfer via OpenAI-compatible endpoints.
No published same-harness benchmark table
Neither vendor publishes a side-by-side table for the two models. A95B scores 86.6 on Terminal Bench 2.1, 92.6 on GPQA Diamond, 67.7 on SWE-bench Pro, 73.5 on FrontierSWE, 56.6 on DeepSWE 1.1 — all on Qwen's published harnesses. DeepSeek V4 Pro's published numbers are on DeepSeek's own eval harness and are not directly comparable.
When to pick DeepSeek V4 Pro
- Per-token cost dominates the buying decision (high-volume agentic workloads, batch offline jobs).
- Output-heavy workloads (long-form synthesis, doc generation) where the $3.60 output rate compounds.
- You do not need the explicit 262K native context — V4 Pro's published window is sufficient for your workload.
Ready to test the workflow?
Create account & add creditsWhen to pick A95B
- Long-context workloads (262K native or 1M extended via YaRN) are the buying constraint.
- You need the Qwen vendor benchmark record reproduced on Anthropic / OpenAI / Google frontier harnesses.
- You are running workloads where the 46% saving on V4 Pro does not justify a model switch (low volume, pilot, evaluation).
Caveats
- V4 Pro per-token rates can change without notice; record the rate and date alongside any benchmark or production decision.
- Cache-read rates for V4 Pro are not consistently published across providers; the headline rates above are uncached.
- A95B requires thinking mode on every call. V4 Pro has not been documented as requiring thinking mode.
Frequently asked questions
Is DeepSeek V4 Pro cheaper than Qwen3.8-2.4T-A95B?
Yes, on both sides: $1.80 input vs $2.00, $3.60 output vs $6.00 per 1M tokens. On a 1:3 input:output workload the blended rate is $2.70 against $5.00 — 46% saving on V4 Pro.
Are Qwen3.8-2.4T-A95B and DeepSeek V4 Pro the same kind of model?
Both are open-weight frontier MoE checkpoints with comparable published context windows. They differ on parameter count and active count per token, and the two vendors publish benchmark numbers on different harnesses that are not directly comparable.
Where is the canonical Qwen3.8-2.4T-A95B model page?
The canonical model page with current OneInfer pricing, capabilities, and availability is /models/Qwen/Qwen3.8-2.4T-A95B. This comparison is a focused facet of that entity, not a replacement for it.
How should I treat benchmark or price claims on this page?
Check each claim's provenance label and observed date. Vendor-reported and independently verified numbers are shown as separate evidence classes on this hub.
Is Qwen3.8-2.4T-A95B open source?
Yes — weights are released under the qwen3.8-max license. Confirm the license tag against the official Hugging Face repository before self-hosting at scale.
Put Qwen3.8-2.4T-A95B to work
Fund a controlled evaluation, start with a prepared prompt, and measure quality and cost on your own workload.