Qwen3.5-122B-A10B vs Qwen3.5-397B-A17B
Qwen3.5-122B-A10B (2026) and Qwen3.5-397B-A17B (2026) are frontier-tier reasoning models from Alibaba. Qwen3.5-122B-A10B ships a 262k-token context window, while Qwen3.5-397B-A17B ships a 262k-token context window. On MMLU PRO, Qwen3.5-397B-A17B leads by 1.1 pts. On pricing, Qwen3.5-122B-A10B costs $0.26/1M input tokens versus $0.39/1M for the alternative. This comparison covers specs, pricing, API access, capabilities, benchmarks, input and output token costs, and production fit for coding and agent workloads.
Qwen3.5-122B-A10B is ~50% cheaper at $0.26/1M; pay for Qwen3.5-397B-A17B only for vision-heavy evaluation.
Decision scorecard
Local evidence first| Signal | Qwen3.5-122B-A10B | Qwen3.5-397B-A17B |
|---|---|---|
| Best for | reasoning-heavy apps, multimodal apps, and tool-calling agents | reasoning-heavy apps, multimodal apps, and tool-calling agents |
| Decision fit | Coding, RAG, and Agents | Coding, RAG, and Agents |
| Context window | 262k | 262k |
| Cheapest output | $2.08/1M tokens | $2.34/1M tokens |
| Provider routes | 3 tracked | 4 tracked |
| Shared benchmarks | 8 rows | MMLU PRO leader |
Decision tradeoffs
- Qwen3.5-122B-A10B has the lower cheapest tracked output price at $2.08/1M tokens.
- Local decision data tags Qwen3.5-122B-A10B for Coding, RAG, and Agents.
- Qwen3.5-397B-A17B holds a shared-benchmark lead on MMLU PRO, ahead by 1.1 points.
- Qwen3.5-397B-A17B has broader tracked provider coverage for fallback and procurement flexibility.
- Local decision data tags Qwen3.5-397B-A17B for Coding, RAG, and Agents.
Monthly cost at traffic
Estimate token spend from the cheapest tracked input and output route or tier on this page.
Qwen3.5-122B-A10B
$728
Cheapest tracked route/tier: OpenRouter
Qwen3.5-397B-A17B
$897
Cheapest tracked route/tier: OpenRouter
Estimated monthly gap: $169. Batch, cache, alternate speed tiers, and negotiated pricing are excluded from this local estimate.
Switch friction
- Provider overlap exists on OpenRouter, Alibaba Cloud PAI-EAS, and Novita AI; start route-level A/B tests there.
- Qwen3.5-397B-A17B is $0.26/1M tokens higher on cheapest tracked output pricing, so quality gains need to justify the spend.
- Provider overlap exists on OpenRouter, Alibaba Cloud PAI-EAS, and Novita AI; start route-level A/B tests there.
- Qwen3.5-122B-A10B is $0.26/1M tokens lower on cheapest tracked output pricing before cache, batch, or negotiated discounts.
Specs
| Specification | ||
|---|---|---|
| Released | 2026-02-24 | 2026-02-16 |
| Context window | 262k | 262k |
| Parameters | 122B | 397B |
| Architecture | mixture of experts | MoE |
| License | Apache 2.0(OSI) | Apache 2.0(OSI) |
| Openness | Open source | Open source |
| Commercial use | Commercial use allowed | Commercial use allowed |
| Knowledge cutoff | - | - |
Pricing and availability
| Pricing attribute | Qwen3.5-122B-A10B | Qwen3.5-397B-A17B |
|---|---|---|
| Input price | $0.26/1M tokens | $0.39/1M tokens |
| Output price | $2.08/1M tokens | $2.34/1M tokens |
| Providers |
Capabilities
| Capability | Qwen3.5-122B-A10B | Qwen3.5-397B-A17B |
|---|---|---|
| Vision | Yes | Yes |
| Multimodal | Yes | Yes |
| Reasoning | Yes | Yes |
| Function calling | Yes | Yes |
| Tool use | Yes | Yes |
| Structured outputs | Yes | Yes |
| Code execution | No | No |
| IDE integration | No | No |
| Computer use | No | No |
| Parallel agents | No | No |
Benchmarks
| Benchmark | Qwen3.5-122B-A10B | Qwen3.5-397B-A17B |
|---|---|---|
| MMLU PRO | 86.7 | 87.8 |
| SWE-bench Verified | 72.0 | 76.2 |
| Google-Proof Q&A | 85.7 | 89.3 |
| LiveCodeBench | 78.9 | 83.6 |
| Humanity's Last Exam | 25.3 | 28.7 |
| τ-bench | 79.5 | 86.7 |
| MultiChallenge | 61.5 | 67.6 |
| Berkeley Function Calling Leaderboard v3 | 72.2 | 72.9 |
Deep dive
On shared benchmark coverage, MMLU PRO has Qwen3.5-122B-A10B at 86.7 and Qwen3.5-397B-A17B at 87.8, with Qwen3.5-397B-A17B ahead by 1.1 points; SWE-bench Verified has Qwen3.5-122B-A10B at 72 and Qwen3.5-397B-A17B at 76.2, with Qwen3.5-397B-A17B ahead by 4.2 points; Google-Proof Q&A has Qwen3.5-122B-A10B at 85.7 and Qwen3.5-397B-A17B at 89.3, with Qwen3.5-397B-A17B ahead by 3.6 points. The largest visible gap is 4.2 points on SWE-bench Verified, which matters most when that benchmark mirrors your workload. Treat isolated benchmark wins as directional, because provider routing, prompt style, and tool access can move real application results.
The capability footprint is close: both models cover vision, multimodal input, reasoning mode, function calling, and tool use. That makes context budget, benchmark fit, and provider maturity more important than a simple checklist. If your application depends on one integration detail, verify it against the provider route you plan to use, not just the base model listing.
For cost, Qwen3.5-122B-A10B lists $0.26/1M input and $2.08/1M output tokens on the cheapest tracked provider, while Qwen3.5-397B-A17B lists $0.39/1M input and $2.34/1M output tokens on the cheapest tracked provider. A 70/30 input-output blend puts Qwen3.5-122B-A10B lower by about $0.17 per million blended tokens. Availability is 3 providers versus 4, so concentration risk also matters.
Choose Qwen3.5-122B-A10B when vision-heavy evaluation and lower input-token cost are central to the workload. Choose Qwen3.5-397B-A17B when vision-heavy evaluation and broader provider choice are more important. For production, rerun your own prompts through the exact provider, region, and tool stack you plan to ship.
FAQ
Which has a larger context window, Qwen3.5-122B-A10B or Qwen3.5-397B-A17B?
Qwen3.5-122B-A10B supports 262k tokens, while Qwen3.5-397B-A17B supports 262k tokens. That gap matters most for long documents, large codebases, retrieval-heavy agents, and conversations where earlier context must remain visible. Use this as a quick comparison signal, then confirm the provider-specific limits before committing to production.
Which is cheaper, Qwen3.5-122B-A10B or Qwen3.5-397B-A17B?
Qwen3.5-122B-A10B is cheaper on tracked token pricing. Qwen3.5-122B-A10B costs $0.26/1M input and $2.08/1M output tokens. Qwen3.5-397B-A17B costs $0.39/1M input and $2.34/1M output tokens. Provider discounts or batch pricing can still change the final bill.
Is Qwen3.5-122B-A10B or Qwen3.5-397B-A17B open source?
Qwen3.5-122B-A10B is listed under Apache 2.0. Qwen3.5-397B-A17B is listed under Apache 2.0. License labels affect whether you can self-host, redistribute weights, or rely only on hosted APIs, so confirm the upstream license before deployment.
Which is better for vision, Qwen3.5-122B-A10B or Qwen3.5-397B-A17B?
Both Qwen3.5-122B-A10B and Qwen3.5-397B-A17B expose vision. The better choice depends on benchmark fit, context budget, pricing, and whether your provider route exposes the same capability surface. Use this as a quick comparison signal, then confirm the provider-specific limits before committing to production.
Which is better for multimodal input, Qwen3.5-122B-A10B or Qwen3.5-397B-A17B?
Both Qwen3.5-122B-A10B and Qwen3.5-397B-A17B expose multimodal input. The better choice depends on benchmark fit, context budget, pricing, and whether your provider route exposes the same capability surface. Use this as a quick comparison signal, then confirm the provider-specific limits before committing to production.
Where can I run Qwen3.5-122B-A10B and Qwen3.5-397B-A17B?
Qwen3.5-122B-A10B is available on OpenRouter, Alibaba Cloud PAI-EAS, and Novita AI. Qwen3.5-397B-A17B is available on OpenRouter, Together AI, Alibaba Cloud PAI-EAS, and Novita AI. Provider coverage can affect latency, region availability, compliance posture, and fallback options.
Continue comparing
Last reviewed: 2026-06-04. Data sourced from public model cards and provider documentation.