DeepSeek V3.1 vs Qwen3 Next 80B A3B Thinking API pricing
Updated
DeepSeek V3.1: USD 0.25 input, USD 0.95 output per 1M tokens (DeepInfra). Qwen3 Next 80B A3B Thinking: USD 0.15 input, USD 1.20 output per 1M tokens (Google Vertex AI). At 3 input tokens per output token, DeepSeek V3.1 costs 3% more than Qwen3 Next 80B A3B Thinking (USD 0.425 vs USD 0.4125 per 1M).
How do DeepSeek V3.1 and Qwen3 Next 80B A3B Thinking differ on price?
- Cheapest input price: Qwen3 Next 80B A3B Thinking USD 0.15 against USD 0.25 per 1M tokens, so DeepSeek V3.1 costs 1.67× as much (67% more).
- Cheapest output price: DeepSeek V3.1 USD 0.95 against USD 1.20 per 1M tokens, so Qwen3 Next 80B A3B Thinking costs 1.26× as much (26% more).
- Among the 201 indexed models, DeepSeek V3.1 ranks 87th cheapest and Qwen3 Next 80B A3B Thinking 85th on the 3:1 blend.
- The cheaper model changes at 2.5 input tokens per output token.
- Only DeepSeek V3.1 lists a cached-input discount: DeepSeek V3.1 at 3 standard prices of 7, from USD 0.06 (Google Vertex AI, 90% below that provider's input price). Qwen3 Next 80B A3B Thinking's cached tokens bill at the input price.
- Qwen3 Next 80B A3B Thinking states up to 262,144 tokens of context, 1.6× the 163,840 of DeepSeek V3.1.
- DeepSeek V3.1 has 7 providers with a standard price, 5 more than Qwen3 Next 80B A3B Thinking; 2 providers sell both (GMI Cloud and Google Vertex AI).
- On one account, GMI Cloud charges USD 0.4525 for DeepSeek V3.1 (1.06× its cheapest price) and USD 0.4875 for Qwen3 Next 80B A3B Thinking (1.18× its cheapest price) at 3:1, the lowest combined price among the providers that sell both.
- Shopping around matters more for DeepSeek V3.1: its dearest standard price is 5.1× its cheapest, against 1.18× for Qwen3 Next 80B A3B Thinking.
- DeepSeek V3.1 has a batch price at 1 provider, from USD 0.4375 at 3:1 (Google Vertex AI); Qwen3 Next 80B A3B Thinking has no batch price on file.
- For the one-developer coding agent preset, the gap is USD 313.20 a year in DeepSeek V3.1's favour (DeepSeek V3.1 USD 351.90 a month, Qwen3 Next 80B A3B Thinking USD 378.00).
- Per character of input, the gap depends on the language: DeepSeek V3.1 costs 1.69× as much as Qwen3 Next 80B A3B Thinking on Code text but 1.03× as much as Qwen3 Next 80B A3B Thinking on Hindi, because the two tokenizers split those languages differently.
DeepSeek V3.1 and Qwen3 Next 80B A3B Thinking 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 V3.1 | Qwen3 Next 80B A3B Thinking |
|---|---|---|
| Model page | DeepSeek V3.1 DeepSeek · 7 providers | Qwen3 Next 80B A3B Thinking Qwen · 2 providers |
| Cheapest standard price, blended 3:1 | USD 0.425 USD 0.25 in / USD 0.95 out at DeepInfra DeepInfra page checked 2026-11-14 | USD 0.4125 lower USD 0.15 in / USD 1.20 out at Google Vertex AI Google Vertex AI page checked 2026-11-14 |
| Cheapest input | USD 0.25 DeepInfra source | USD 0.15 lower Google Vertex AI source |
| Cheapest cached input | USD 0.06 Google Vertex AI source | No standard price lists a cache price; cached tokens bill at the input price. |
| Cheapest output | USD 0.95 lower DeepInfra source | USD 1.20 Google Vertex AI source |
| Maker's own API | DeepSeek publishes no paid standard price on its own API that we found. | Qwen publishes no paid standard price on its own API that we found. |
| Median standard price | USD 0.285 / USD 1 input / output, 7 prices | USD 0.15 / USD 1.35 input / output, 2 prices |
| Context window | 163,840 tokens, largest stated; from 131,072 at some providers | 262,144 tokens, largest stated |
| Providers with a standard price | 7 | 2 |
- 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 V3.1 and Qwen3 Next 80B A3B Thinking 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 V3.1 | Qwen3 Next 80B A3B Thinking | Difference |
|---|---|---|---|
| Support chatbot 2,000 requests a day, 1,500 input tokens (60% cached), 300 output | USD 33.12 DeepInfra | USD 35.10 Google Vertex AI | USD 1.98 DeepSeek V3.1 lower |
| RAG over documents 1,000 requests a day, 8,000 input tokens (30% cached), 500 output | USD 65.61 DeepInfra | USD 54.00 Google Vertex AI | USD 11.61 Qwen3 Next 80B A3B Thinking lower |
| Coding agent (one developer) 1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning | USD 351.90 DeepInfra | USD 378.00 Google Vertex AI | USD 26.10 DeepSeek V3.1 lower |
The cheaper model depends on the workload: DeepSeek V3.1 for Support chatbot, Qwen3 Next 80B A3B Thinking for RAG over documents, DeepSeek V3.1 for Coding agent (one developer). Cache-heavy work rewards a low cached-input price. The widest gap is on RAG over documents: the dearer model costs 22% more than the cheaper one.
Does the cheaper model change with your input:output ratio?
The cheaper model changes with the mix: below 2.5 input tokens per output token, DeepSeek V3.1 is cheaper; above 2.5, Qwen3 Next 80B A3B Thinking is cheaper. At the site's 3:1 blend, Qwen3 Next 80B A3B Thinking 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 V3.1 | Qwen3 Next 80B A3B Thinking |
|---|---|---|
| 1 : 3 (long answers) | USD 0.775 lower DeepInfra | USD 0.9375 Google Vertex AI |
| 1 : 1 | USD 0.60 lower DeepInfra | USD 0.675 Google Vertex AI |
| 3 : 1 (the site’s blend) | USD 0.425 DeepInfra | USD 0.4125 lower Google Vertex AI |
| 10 : 1 (retrieval, long prompts) | USD 0.3136 DeepInfra | USD 0.2455 lower Google Vertex AI |
| 30 : 1 (agents, big contexts) | USD 0.2726 DeepInfra | USD 0.1839 lower Google Vertex AI |
USD per 1M tokens at the cheapest standard provider for each mix, before cache discounts. Thinking tokens bill as output.
What do DeepSeek V3.1 and Qwen3 Next 80B A3B Thinking 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 V3.1 and the Qwen3 32B tokenizer for Qwen3 Next 80B A3B Thinking:
| Content | DeepSeek V3.1 | Qwen3 Next 80B A3B Thinking |
|---|---|---|
| English | USD 0.054 DeepInfra | USD 0.033 lower GMI Cloud |
| Arabic MSA | USD 0.094 DeepInfra | USD 0.058 lower GMI Cloud |
| Egyptian Arabic | USD 0.097 DeepInfra | USD 0.060 lower GMI Cloud |
| Hindi | USD 0.144 DeepInfra | USD 0.140 lower GMI Cloud |
| Chinese | USD 0.147 DeepInfra | USD 0.096 lower GMI Cloud |
| Spanish | USD 0.064 DeepInfra | USD 0.040 lower GMI Cloud |
| Code | USD 0.066 DeepInfra | USD 0.039 lower GMI Cloud |
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 V3.1 API pricing: all 7 providers and other tiers.
- Qwen3 Next 80B A3B Thinking API pricing: all 2 providers and other tiers.
- Cost calculator with DeepSeek V3.1 and Qwen3 Next 80B A3B Thinking preloaded
- DeepSeek token counter
- Qwen3 token counter
- Prompt caching calculator
More comparisons: DeepSeek V3.1 vs DeepSeek V3 · DeepSeek V3.2 vs DeepSeek V3.1 · Qwen3 Next 80B A3B Thinking vs Qwen3 Next 80B A3B · every DeepSeek V3.1 comparison · every Qwen3 Next 80B A3B Thinking comparison · all 662 price comparisons
Questions
Is DeepSeek V3.1 cheaper than Qwen3 Next 80B A3B Thinking?
No. On a blend of 3 input tokens to 1 output token, Qwen3 Next 80B A3B Thinking costs USD 0.4125 per 1M tokens and DeepSeek V3.1 USD 0.425, at each model's cheapest standard price. For input alone, Qwen3 Next 80B A3B Thinking is cheaper (USD 0.15 against USD 0.25 per 1M); for output alone, DeepSeek V3.1 is (USD 0.95 against USD 1.20). This compares price only, not quality.
What do DeepSeek V3.1 and Qwen3 Next 80B A3B Thinking cost per 1M tokens?
DeepSeek V3.1: from USD 0.25 input and USD 0.95 output at DeepInfra; median of 7 standard prices USD 0.285 / USD 1. Qwen3 Next 80B A3B Thinking: from USD 0.15 input and USD 1.20 output at Google Vertex AI; median of 2 standard prices USD 0.15 / USD 1.35. Each price is read from the provider's own pricing page; the source is linked in the table.
Which providers sell both DeepSeek V3.1 and Qwen3 Next 80B A3B Thinking?
2 providers have a standard price for both: GMI Cloud (USD 0.4525 and USD 0.4875 at 3:1), Google Vertex AI (USD 0.875 and USD 0.4125 at 3:1). The first is the lowest combined price. Buying each model from its own cheapest provider costs USD 0.425 and USD 0.4125.
Which is cheaper for a coding agent or a chatbot, DeepSeek V3.1 or Qwen3 Next 80B A3B Thinking?
For a coding agent (1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning): USD 351.90 a month on DeepSeek V3.1 (DeepInfra) against USD 378.00 on Qwen3 Next 80B A3B Thinking (Google Vertex AI), a difference of USD 26.10. For a support chatbot (2,000 requests a day, 1,500 input tokens (60% cached), 300 output): USD 33.12 a month on DeepSeek V3.1 (DeepInfra) against USD 35.10 on Qwen3 Next 80B A3B Thinking (Google Vertex AI), a difference of USD 1.98. 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 V3.1 and Qwen3 Next 80B A3B Thinking change?
The cheaper model changes with the mix: below 2.5 input tokens per output token, DeepSeek V3.1 is cheaper; above 2.5, Qwen3 Next 80B A3B Thinking is cheaper. At the site's 3:1 blend, Qwen3 Next 80B A3B Thinking 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 V3.1 and Qwen3 Next 80B A3B Thinking have cached input pricing?
DeepSeek V3.1 from USD 0.06 per 1M cached input tokens (Google Vertex AI; 3 of 7 standard prices list a discount). Qwen3 Next 80B A3B Thinking: 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 V3.1 or Qwen3 Next 80B A3B Thinking?
Qwen3 Next 80B A3B Thinking: up to 262,144 tokens, against 163,840 for DeepSeek V3.1, 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.