DeepSeek R1 0528 vs Qwen3.5 122B A10B API pricing
Updated
DeepSeek R1 0528: USD 0.385 input, USD 1.625 output per 1M tokens (Featherless). Qwen3.5 122B A10B: USD 0.26 input, USD 2.08 output per 1M tokens (SiliconFlow). At 3 input tokens per output token, Qwen3.5 122B A10B costs 2.9% more than DeepSeek R1 0528 (USD 0.715 vs USD 0.695 per 1M).
How do DeepSeek R1 0528 and Qwen3.5 122B A10B differ on price?
- Cheapest input price: Qwen3.5 122B A10B USD 0.26 against USD 0.385 per 1M tokens, so DeepSeek R1 0528 costs 1.48× as much (48% more).
- Cheapest output price: DeepSeek R1 0528 USD 1.625 against USD 2.08 per 1M tokens, so Qwen3.5 122B A10B costs 1.28× as much (28% more).
- Among the 201 indexed models, DeepSeek R1 0528 ranks 110th cheapest and Qwen3.5 122B A10B 112th on the 3:1 blend.
- The cheaper model changes at 3.6 input tokens per output token.
- Only DeepSeek R1 0528 lists a cached-input discount: DeepSeek R1 0528 at 3 standard prices of 5, from USD 0.23 (GMI Cloud, 60% below that provider's input price). Qwen3.5 122B A10B's cached tokens bill at the input price.
- Qwen3.5 122B A10B states up to 262,144 tokens of context, 1.6× the 163,840 of DeepSeek R1 0528.
- DeepSeek R1 0528 has 5 providers with a standard price, 1 more than Qwen3.5 122B A10B; 2 providers sell both (GMI Cloud and Novita AI).
- On one account, GMI Cloud charges USD 1 for DeepSeek R1 0528 (1.44× its cheapest price) and USD 1.10 for Qwen3.5 122B A10B (1.54× its cheapest price) at 3:1, the lowest combined price among the providers that sell both.
- Shopping around matters more for DeepSeek R1 0528: its dearest standard price is 3.4× its cheapest, against 1.54× for Qwen3.5 122B A10B.
- Qwen's own API charges USD 1.10 for Qwen3.5 122B A10B at 3:1, 54% above the cheapest provider (SiliconFlow).
- DeepSeek R1 0528 has a batch price at 1 provider, from USD 1.181 at 3:1 (Google Vertex AI); Qwen3.5 122B A10B has no batch price on file.
- For the one-developer coding agent preset, the gap is USD 680.40 a year in Qwen3.5 122B A10B's favour (DeepSeek R1 0528 USD 711.90 a month, Qwen3.5 122B A10B USD 655.20).
- Per character of input, the gap depends on the language: DeepSeek R1 0528 costs 2× as much as Qwen3.5 122B A10B on Hindi text but 1.4× as much as Qwen3.5 122B A10B on Code, because the two tokenizers split those languages differently.
DeepSeek R1 0528 and Qwen3.5 122B A10B prices side by side
USD per 1M tokens, standard tier. "Cheapest" is the lowest price at 3 input tokens to 1 output token; each line can come from a different provider.
| Price | DeepSeek R1 0528 | Qwen3.5 122B A10B |
|---|---|---|
| Model page | DeepSeek R1 0528 DeepSeek · 5 providers | Qwen3.5 122B A10B Qwen · 4 providers |
| Cheapest standard price, blended 3:1 | USD 0.695 lower USD 0.385 in / USD 1.625 out at Featherless Featherless page checked 2026-11-15 | USD 0.715 USD 0.26 in / USD 2.08 out at SiliconFlow SiliconFlow page checked 2026-11-14 |
| Cheapest input | USD 0.385 Featherless source | USD 0.26 lower SiliconFlow source |
| Cheapest cached input | USD 0.23 GMI Cloud source | No standard price lists a cache price; cached tokens bill at the input price. |
| Cheapest output | USD 1.625 lower Featherless source | USD 2.08 SiliconFlow source |
| Maker's own API | DeepSeek publishes no paid standard price on its own API that we found. | USD 0.40 / USD 3.20 Alibaba Cloud source |
| Median standard price | USD 0.57 / USD 2.29 input / output, 5 prices | USD 0.40 / USD 3.20 input / output, 4 prices |
| Context window | 163,840 tokens, largest stated; from 131,072 at some providers | 262,144 tokens, largest stated |
| Providers with a standard price | 5 | 4 |
- Lower marks the lower price on a line; tie, equal prices. Other tiers and free rows are on the model pages.
Report a wrong price or number (email to info@broadnet.ai, with this page's link filled in).
What do DeepSeek R1 0528 and Qwen3.5 122B A10B cost for a real workload?
30 days at each model's cheapest standard price for the workload (presets of the cost calculator; cached input at the cached price where listed).
| Workload | DeepSeek R1 0528 | Qwen3.5 122B A10B | Difference |
|---|---|---|---|
| Support chatbot 2,000 requests a day, 1,500 input tokens (60% cached), 300 output | USD 63.90 Featherless | USD 60.84 SiliconFlow | USD 3.06 Qwen3.5 122B A10B lower |
| RAG over documents 1,000 requests a day, 8,000 input tokens (30% cached), 500 output | USD 116.78 Featherless | USD 93.60 SiliconFlow | USD 23.17 Qwen3.5 122B A10B lower |
| Coding agent (one developer) 1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning | USD 711.90 GMI Cloud | USD 655.20 SiliconFlow | USD 56.70 Qwen3.5 122B A10B lower |
Qwen3.5 122B A10B is cheaper on all three workloads. The widest gap is on RAG over documents: the dearer model costs 25% more than the cheaper one.
Does the cheaper model change with your input:output ratio?
The cheaper model changes with the mix: below 3.6 input tokens per output token, DeepSeek R1 0528 is cheaper; above 3.6, Qwen3.5 122B A10B is cheaper. At the site's 3:1 blend, DeepSeek R1 0528 is cheaper. More input per output token, as with retrieval or agents that resend long contexts, favours the lower input price; long answers favour the lower output price.
| Input : output tokens | DeepSeek R1 0528 | Qwen3.5 122B A10B |
|---|---|---|
| 1 : 3 (long answers) | USD 1.315 lower Featherless | USD 1.625 SiliconFlow |
| 1 : 1 | USD 1.005 lower Featherless | USD 1.17 SiliconFlow |
| 3 : 1 (the site’s blend) | USD 0.695 lower Featherless | USD 0.715 SiliconFlow |
| 10 : 1 (retrieval, long prompts) | USD 0.4977 Featherless | USD 0.4255 lower SiliconFlow |
| 30 : 1 (agents, big contexts) | USD 0.425 Featherless | USD 0.3187 lower SiliconFlow |
USD per 1M tokens at the cheapest standard provider for each mix, before cache discounts. Thinking tokens bill as output.
What do DeepSeek R1 0528 and Qwen3.5 122B A10B cost per character in other languages?
Cost to send 1M characters at each model's cheapest non-promotional standard input price, with the DeepSeek V4.1 Flash tokenizer for DeepSeek R1 0528 and the Qwen3.8 27B tokenizer for Qwen3.5 122B A10B:
| Content | DeepSeek R1 0528 | Qwen3.5 122B A10B |
|---|---|---|
| English | USD 0.082 Featherless | USD 0.058 lower SiliconFlow |
| Arabic MSA | USD 0.145 Featherless | USD 0.081 lower SiliconFlow |
| Egyptian Arabic | USD 0.149 Featherless | USD 0.085 lower SiliconFlow |
| Hindi | USD 0.222 Featherless | USD 0.110 lower SiliconFlow |
| Chinese | USD 0.226 Featherless | USD 0.150 lower SiliconFlow |
| Spanish | USD 0.099 Featherless | USD 0.060 lower SiliconFlow |
| Code | USD 0.102 Featherless | USD 0.072 lower SiliconFlow |
From the real cost by language dataset (measured tokens per character on FLORES-200 and other texts). Your own text will differ.
Check it on your own traffic
- DeepSeek R1 0528 API pricing: all 5 providers and other tiers.
- Qwen3.5 122B A10B API pricing: all 4 providers and other tiers.
- Cost calculator with DeepSeek R1 0528 and Qwen3.5 122B A10B preloaded
- DeepSeek token counter
- Qwen token counter
- Prompt caching calculator
More comparisons: DeepSeek R1 0528 vs DeepSeek R1 · Qwen3.5 397B A17B vs Qwen3.5 122B A10B · Qwen3.5 122B A10B vs Qwen3.5 35B A3B · every DeepSeek R1 0528 comparison · every Qwen3.5 122B A10B comparison · all 662 price comparisons
Questions
Is DeepSeek R1 0528 cheaper than Qwen3.5 122B A10B?
Yes. On a blend of 3 input tokens to 1 output token, DeepSeek R1 0528 costs USD 0.695 per 1M tokens and Qwen3.5 122B A10B USD 0.715, at each model's cheapest standard price. For input alone, Qwen3.5 122B A10B is cheaper (USD 0.26 against USD 0.385 per 1M); for output alone, DeepSeek R1 0528 is (USD 1.625 against USD 2.08). This compares price only, not quality.
What do DeepSeek R1 0528 and Qwen3.5 122B A10B cost per 1M tokens?
DeepSeek R1 0528: from USD 0.385 input and USD 1.625 output at Featherless; median of 5 standard prices USD 0.57 / USD 2.29. Qwen3.5 122B A10B: from USD 0.26 input and USD 2.08 output at SiliconFlow; Alibaba Cloud's own API charges USD 0.40 / USD 3.20; median of 4 standard prices USD 0.40 / USD 3.20. Each price is read from the provider's own pricing page; the source is linked in the table.
Which providers sell both DeepSeek R1 0528 and Qwen3.5 122B A10B?
2 providers have a standard price for both: GMI Cloud (USD 1 and USD 1.10 at 3:1), Novita AI (USD 1.15 and USD 1.10 at 3:1). The first is the lowest combined price. Buying each model from its own cheapest provider costs USD 0.695 and USD 0.715.
Which is cheaper for a coding agent or a chatbot, DeepSeek R1 0528 or Qwen3.5 122B A10B?
For a coding agent (1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning): USD 711.90 a month on DeepSeek R1 0528 (GMI Cloud) against USD 655.20 on Qwen3.5 122B A10B (SiliconFlow), a difference of USD 56.70. For a support chatbot (2,000 requests a day, 1,500 input tokens (60% cached), 300 output): USD 63.90 a month on DeepSeek R1 0528 (Featherless) against USD 60.84 on Qwen3.5 122B A10B (SiliconFlow), a difference of USD 3.06. Each uses the cheapest standard price for that workload, cached input included. Try your own numbers.
At what input:output ratio does the cheaper of DeepSeek R1 0528 and Qwen3.5 122B A10B change?
The cheaper model changes with the mix: below 3.6 input tokens per output token, DeepSeek R1 0528 is cheaper; above 3.6, Qwen3.5 122B A10B is cheaper. At the site's 3:1 blend, DeepSeek R1 0528 is cheaper. More input per output token, as with retrieval or agents that resend long contexts, favours the lower input price; long answers favour the lower output price.
Do DeepSeek R1 0528 and Qwen3.5 122B A10B have cached input pricing?
DeepSeek R1 0528 from USD 0.23 per 1M cached input tokens (GMI Cloud; 3 of 5 standard prices list a discount). Qwen3.5 122B A10B: no standard price lists a cached-input discount. Cached tokens are billed at the input price where no cache price is published.
Which has the larger context window, DeepSeek R1 0528 or Qwen3.5 122B A10B?
Qwen3.5 122B A10B: up to 262,144 tokens, against 163,840 for DeepSeek R1 0528, as stated on providers' pricing pages. Some providers offer less than the maximum; check the model pages before you pick the cheapest row for long prompts.
Read as MarkdownAsk ChatGPTAsk ClaudeAsk Perplexity
Sources