DeepSeek: R1 0528 vs Qwen: Qwen3.6 35B A3B
Head-to-head API pricing and cost comparison between DeepSeek’s DeepSeek: R1 0528 and Qwen’s Qwen: Qwen3.6 35B A3B. Prices auto-refresh daily from OpenRouter.
Qwen: Qwen3.6 35B A3B is 72% cheaper for input tokens; Qwen: Qwen3.6 35B A3B also wins on output tokens.
Side-by-side comparison
| Spec | DeepSeek: R1 0528 | Qwen: Qwen3.6 35B A3B |
|---|---|---|
| Input price (per 1M) | $0.50 | $0.14 |
| Cached input (per 1M) | $0.35 | $0.05 |
| Output price (per 1M) | $2.15 | $1.00 |
| Batch input (per 1M) | — | — |
| Batch output (per 1M) | — | — |
| Reasoning price (per 1M) | — | — |
| Context window | 164K | 262K |
| Vision support | No | Yes |
| Caching support | Yes | No |
| Batch API | No | No |
| Reasoning capability | No | No |
Monthly cost at volume
Estimated monthly API spend at common production traffic levels (input/output tokens per request shown).
| Volume | DeepSeek: R1 0528 | Qwen: Qwen3.6 35B A3B | Savings |
|---|---|---|---|
1K req/day 500in / 200out tokens | $20.40 | $8.10 | $12.30 Qwen: Qwen3.6 35B A3B wins |
10K req/day 1500in / 500out tokens | $547.50 | $213.00 | $334.50 Qwen: Qwen3.6 35B A3B wins |
100K req/day 3000in / 800out tokens | $9,660 | $3,660 | $6,000 Qwen: Qwen3.6 35B A3B wins |
1M req/day 8000in / 2000out tokens | $249,000 | $93,600 | $155,400 Qwen: Qwen3.6 35B A3B wins |
Adjust input/output token counts, request volume, batch & cached pricing.
Related comparisons
Frequently asked questions
Which is cheaper, DeepSeek: R1 0528 or Qwen: Qwen3.6 35B A3B?
For input tokens, Qwen: Qwen3.6 35B A3B is roughly 72% cheaper at $0.14/1M vs $0.50/1M. For output tokens, Qwen: Qwen3.6 35B A3B wins at $1.00/1M. Real-world cost depends on your input/output ratio — use the calculator to model your actual workload.
What’s the context window difference?
DeepSeek: R1 0528 has a context window of 164K tokens. Qwen: Qwen3.6 35B A3B offers 262K tokens. Larger context windows are valuable for long documents, RAG pipelines, and multi-turn conversations — but they come with higher input-token bills if you fill them every request.
Should I use DeepSeek: R1 0528 or Qwen: Qwen3.6 35B A3B?
Choose DeepSeek: R1 0528 if you’re already on the DeepSeek stack, want broad ecosystem support, or prefer its feature set. Choose Qwen: Qwen3.6 35B A3B for Qwen’s ecosystem, native vision input, or its cheaper input tokens. Run a small benchmark on your own prompts before committing — price is only one axis.
How are these prices kept current?
Prices are pulled directly from OpenRouter’s public models API once every 24 hours via a Convex cron job, then normalized to per-1M-token figures. Last refresh: May 28, 2026.