Qwen3.8 Max vs Qwen3.7 Max API pricing
Updated
Qwen3.8 Max: USD 1.65 input, USD 4.951 output per 1M tokens (DeepInfra). Qwen3.7 Max: USD 1.25 input, USD 3.75 output per 1M tokens (Novita AI). At 3 input tokens per output token, Qwen3.8 Max costs 32% more than Qwen3.7 Max (USD 2.475 vs USD 1.875 per 1M).
How do Qwen3.8 Max and Qwen3.7 Max differ on price?
- Cheapest input price: Qwen3.7 Max USD 1.25 against USD 1.65 per 1M tokens, so Qwen3.8 Max costs 1.32× as much (32% more).
- Cheapest output price: Qwen3.7 Max USD 3.75 against USD 4.951 per 1M tokens, so Qwen3.8 Max costs 1.32× as much (32% more).
- Among the 201 indexed models, Qwen3.8 Max ranks 157th cheapest and Qwen3.7 Max 152nd on the 3:1 blend.
- No input:output mix changes the answer: Qwen3.7 Max is cheaper at every mix before cache discounts.
- Both list cached-input discounts: Qwen3.8 Max at 6 standard prices of 7, from USD 0.20 (DigitalOcean, 90% below that provider's input price); Qwen3.7 Max at 5 standard prices of 5, from USD 0.25 (Novita AI, 80% below that provider's input price).
- Both state a context window of up to 1,000,000 tokens.
- Qwen3.8 Max has 7 providers with a standard price, 2 more than Qwen3.7 Max; 4 providers sell both (Novita AI, DeepInfra, Alibaba Cloud and GMI Cloud).
- On one account, Novita AI charges USD 3 for Qwen3.8 Max (1.21× its cheapest price) and USD 1.875 for Qwen3.7 Max (its cheapest price) at 3:1, the lowest combined price among the providers that sell both.
- Shopping around matters more for Qwen3.7 Max: its dearest standard price is 2× its cheapest, against 1.21× for Qwen3.8 Max.
- Qwen's own API charges USD 3 for Qwen3.8 Max at 3:1, 21% above the cheapest provider (DeepInfra).
- Qwen's own API charges USD 3.75 for Qwen3.7 Max at 3:1, 100% above the cheapest provider (Novita AI).
- For the one-developer coding agent preset, the gap is USD 1,785 a year in Qwen3.7 Max's favour (Qwen3.8 Max USD 1,206 a month, Qwen3.7 Max USD 1,058).
Qwen3.8 Max and Qwen3.7 Max 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 | Qwen3.8 Max | Qwen3.7 Max |
|---|---|---|
| Model page | Qwen3.8 Max Qwen · 7 providers | Qwen3.7 Max Qwen · 5 providers |
| Cheapest standard price, blended 3:1 | USD 2.475 USD 1.65 in / USD 4.951 out at DeepInfra DeepInfra page checked 2026-11-14 | USD 1.875 lower USD 1.25 in / USD 3.75 out at Novita AI Novita AI page checked 2026-11-14 |
| Cheapest input | USD 1.65 DeepInfra source | USD 1.25 lower Novita AI source |
| Cheapest cached input | USD 0.20 lower DigitalOcean source | USD 0.25 Novita AI source |
| Cheapest output | USD 4.951 DeepInfra source | USD 3.75 lower Novita AI source |
| Maker's own API | USD 2 / USD 6 Alibaba Cloud source | USD 2.50 / USD 7.50 Alibaba Cloud source |
| Median standard price | USD 2 / USD 6 input / output, 7 prices | USD 2.50 / USD 7.50 input / output, 5 prices |
| Context window | 1,000,000 tokens, largest stated; from 256,000 at some providers | 1,000,000 tokens, largest stated; from 256,000 at some providers |
| Providers with a standard price | 7 | 5 |
- 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 Qwen3.8 Max and Qwen3.7 Max 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 | Qwen3.8 Max | Qwen3.7 Max | Difference |
|---|---|---|---|
| Support chatbot 2,000 requests a day, 1,500 input tokens (60% cached), 300 output | USD 159.64 DeepInfra | USD 126.00 Novita AI | USD 33.64 Qwen3.7 Max lower |
| RAG over documents 1,000 requests a day, 8,000 input tokens (30% cached), 500 output | USD 366.30 DeepInfra | USD 284.25 Novita AI | USD 82.05 Qwen3.7 Max lower |
| Coding agent (one developer) 1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning | USD 1,206 DeepInfra | USD 1,058 Novita AI | USD 148.77 Qwen3.7 Max lower |
Qwen3.7 Max is cheaper on all three workloads. The widest gap is on RAG over documents: the dearer model costs 29% more than the cheaper one.
Does the cheaper model change with your input:output ratio?
Qwen3.7 Max is cheaper at every mix of input and output tokens, before cache discounts: its cheapest input price and its cheapest output price are both at or below Qwen3.8 Max's, so the input:output ratio never changes the answer.
| Input : output tokens | Qwen3.8 Max | Qwen3.7 Max |
|---|---|---|
| 1 : 3 (long answers) | USD 4.126 DeepInfra | USD 3.125 lower Novita AI |
| 1 : 1 | USD 3.30 DeepInfra | USD 2.50 lower Novita AI |
| 3 : 1 (the site’s blend) | USD 2.475 DeepInfra | USD 1.875 lower Novita AI |
| 10 : 1 (retrieval, long prompts) | USD 1.95 DeepInfra | USD 1.477 lower Novita AI |
| 30 : 1 (agents, big contexts) | USD 1.756 DeepInfra | USD 1.331 lower Novita AI |
USD per 1M tokens at the cheapest standard provider for each mix, before cache discounts. Thinking tokens bill as output.
What do Qwen3.8 Max and Qwen3.7 Max cost per character in other languages?
Not measured: the real cost by language dataset covers only tokenizers we could measure from published files, and Qwen3.8 Max and Qwen3.7 Max are not among them. Count tokens on your own text with the counters below.
Check it on your own traffic
- Qwen3.8 Max API pricing: all 7 providers and other tiers.
- Qwen3.7 Max API pricing: all 5 providers and other tiers.
- Cost calculator with Qwen3.8 Max and Qwen3.7 Max preloaded
- Qwen token counter
- Prompt caching calculator
More comparisons: Qwen3.8 Max vs Kimi K3 · DeepSeek V4 Pro vs Qwen3.8 Max · Qwen3.8 Max (0902) vs Qwen3.8 Max · Qwen3.8 Max vs Qwen3.8 Flash · Qwen3.7 Max vs Qwen3.7 Plus · every Qwen3.8 Max comparison · every Qwen3.7 Max comparison · all 662 price comparisons
Questions
Is Qwen3.8 Max cheaper than Qwen3.7 Max?
No. On a blend of 3 input tokens to 1 output token, Qwen3.7 Max costs USD 1.875 per 1M tokens and Qwen3.8 Max USD 2.475, at each model's cheapest standard price. For input alone, Qwen3.7 Max is cheaper (USD 1.25 against USD 1.65 per 1M); for output alone, Qwen3.7 Max is (USD 3.75 against USD 4.951). This compares price only, not quality.
What do Qwen3.8 Max and Qwen3.7 Max cost per 1M tokens?
Qwen3.8 Max: from USD 1.65 input and USD 4.951 output at DeepInfra; Alibaba Cloud's own API charges USD 2 / USD 6; median of 7 standard prices USD 2 / USD 6. Qwen3.7 Max: from USD 1.25 input and USD 3.75 output at Novita AI; Alibaba Cloud's own API charges USD 2.50 / USD 7.50; median of 5 standard prices USD 2.50 / USD 7.50. Each price is read from the provider's own pricing page; the source is linked in the table.
Which providers sell both Qwen3.8 Max and Qwen3.7 Max?
4 providers have a standard price for both: Novita AI (USD 3 and USD 1.875 at 3:1), DeepInfra (USD 2.475 and USD 3.75 at 3:1), Alibaba Cloud (USD 3 and USD 3.75 at 3:1), GMI Cloud (USD 3 and USD 3.75 at 3:1). The first is the lowest combined price. Buying each model from its own cheapest provider costs USD 2.475 and USD 1.875.
Which is cheaper for a coding agent or a chatbot, Qwen3.8 Max or Qwen3.7 Max?
For a coding agent (1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning): USD 1,206 a month on Qwen3.8 Max (DeepInfra) against USD 1,058 on Qwen3.7 Max (Novita AI), a difference of USD 148.77. For a support chatbot (2,000 requests a day, 1,500 input tokens (60% cached), 300 output): USD 159.64 a month on Qwen3.8 Max (DeepInfra) against USD 126.00 on Qwen3.7 Max (Novita AI), a difference of USD 33.64. 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 Qwen3.8 Max and Qwen3.7 Max change?
Qwen3.7 Max is cheaper at every mix of input and output tokens, before cache discounts: its cheapest input price and its cheapest output price are both at or below Qwen3.8 Max's, so the input:output ratio never changes the answer.
Do Qwen3.8 Max and Qwen3.7 Max have cached input pricing?
Qwen3.8 Max from USD 0.20 per 1M cached input tokens (DigitalOcean; 6 of 7 standard prices list a discount). Qwen3.7 Max from USD 0.25 per 1M cached input tokens (Novita AI; 5 of 5 standard prices list a discount). Cached tokens are billed at the input price where no cache price is published.
Which has the larger context window, Qwen3.8 Max or Qwen3.7 Max?
Both go up to 1,000,000 tokens on the providers that state it.