Qwen3.5 35B A3B vs Step 3.7 Flash API pricing
Updated
Qwen3.5 35B A3B: USD 0.14 input, USD 1 output per 1M tokens (DeepInfra). Step 3.7 Flash: USD 0.20 input, USD 1.15 output per 1M tokens (Featherless and 2 others). At 3 input tokens per output token, Step 3.7 Flash costs 23% more than Qwen3.5 35B A3B (USD 0.4375 vs USD 0.355 per 1M).
How do Qwen3.5 35B A3B and Step 3.7 Flash differ on price?
- Cheapest input price: Qwen3.5 35B A3B USD 0.14 against USD 0.20 per 1M tokens, so Step 3.7 Flash costs 1.43× as much (43% more).
- Cheapest output price: Qwen3.5 35B A3B USD 1 against USD 1.15 per 1M tokens, so Step 3.7 Flash costs 1.15× as much (15% more).
- Among the 201 indexed models, Qwen3.5 35B A3B ranks 76th cheapest and Step 3.7 Flash 88th on the 3:1 blend.
- No input:output mix changes the answer: Qwen3.5 35B A3B is cheaper at every mix before cache discounts.
- Both list cached-input discounts: Qwen3.5 35B A3B at 4 standard prices of 7, from USD 0.05 (DeepInfra, 64% below that provider's input price); Step 3.7 Flash at 3 standard prices of 3, from USD 0.04 (Featherless, 80% below that provider's input price).
- Both state a context window of up to 262,144 tokens.
- Qwen3.5 35B A3B has 7 providers with a standard price, 4 more than Step 3.7 Flash; 2 providers sell both (GMI Cloud and Novita AI).
- On one account, GMI Cloud charges USD 0.6875 for Qwen3.5 35B A3B (1.94× its cheapest price) and USD 0.4375 for Step 3.7 Flash (its cheapest price) at 3:1, tied with 1 other provider for the lowest combined price among the providers that sell both.
- Shopping around matters more for Qwen3.5 35B A3B: its dearest standard price is 1.94× its cheapest, against 1× for Step 3.7 Flash.
- Qwen's own API charges USD 0.6875 for Qwen3.5 35B A3B at 3:1, 94% above the cheapest provider (DeepInfra).
- For the one-developer coding agent preset, the gap is USD 172.80 a year in Qwen3.5 35B A3B's favour (Qwen3.5 35B A3B USD 204.30 a month, Step 3.7 Flash USD 218.70).
Qwen3.5 35B A3B and Step 3.7 Flash 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 | Qwen3.5 35B A3B | Step 3.7 Flash |
|---|---|---|
| Model page | Qwen3.5 35B A3B Qwen · 7 providers | Step 3.7 Flash StepFun · 3 providers |
| Cheapest standard price, blended 3:1 | USD 0.355 lower USD 0.14 in / USD 1 out at DeepInfra DeepInfra page checked 2026-11-14 | USD 0.4375 USD 0.20 in / USD 1.15 out at Featherless and 2 others Featherless page checked 2026-11-15 |
| Cheapest input | USD 0.14 lower DeepInfra source | USD 0.20 Featherless source |
| Cheapest cached input | USD 0.05 DeepInfra source | USD 0.04 lower Featherless source |
| Cheapest output | USD 1 lower DeepInfra source | USD 1.15 Featherless source |
| Maker's own API | USD 0.25 / USD 2 Alibaba Cloud source | StepFun publishes no paid standard price on its own API that we found. |
| Median standard price | USD 0.24 / USD 1.80 input / output, 7 prices | USD 0.20 / USD 1.15 input / output, 3 prices |
| Context window | 262,144 tokens, largest stated; from 256,000 at some providers | 262,144 tokens, largest stated; from 256,000 at some providers |
| Providers with a standard price | 7 | 3 |
- 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 Qwen3.5 35B A3B and Step 3.7 Flash 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 | Qwen3.5 35B A3B | Step 3.7 Flash | Difference |
|---|---|---|---|
| Support chatbot 2,000 requests a day, 1,500 input tokens (60% cached), 300 output | USD 25.74 DeepInfra | USD 30.06 Featherless | USD 4.32 Qwen3.5 35B A3B lower |
| RAG over documents 1,000 requests a day, 8,000 input tokens (30% cached), 500 output | USD 42.12 DeepInfra | USD 53.73 Featherless | USD 11.61 Qwen3.5 35B A3B lower |
| Coding agent (one developer) 1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning | USD 204.30 DeepInfra | USD 218.70 Featherless | USD 14.40 Qwen3.5 35B A3B lower |
Qwen3.5 35B A3B is cheaper on all three workloads. The widest gap is on RAG over documents: the dearer model costs 28% more than the cheaper one.
Does the cheaper model change with your input:output ratio?
Qwen3.5 35B A3B 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 Step 3.7 Flash's, so the input:output ratio never changes the answer.
| Input : output tokens | Qwen3.5 35B A3B | Step 3.7 Flash |
|---|---|---|
| 1 : 3 (long answers) | USD 0.785 lower DeepInfra | USD 0.9125 Featherless |
| 1 : 1 | USD 0.57 lower DeepInfra | USD 0.675 Featherless |
| 3 : 1 (the site’s blend) | USD 0.355 lower DeepInfra | USD 0.4375 Featherless |
| 10 : 1 (retrieval, long prompts) | USD 0.2182 lower DeepInfra | USD 0.2864 Featherless |
| 30 : 1 (agents, big contexts) | USD 0.1677 lower DeepInfra | USD 0.2306 Featherless |
USD per 1M tokens at the cheapest standard provider for each mix, before cache discounts. Thinking tokens bill as output.
What do Qwen3.5 35B A3B and Step 3.7 Flash cost per character in other languages?
Not measured: the real cost by language dataset covers only tokenizers we could measure from published files, and Step 3.7 Flash is not among them. Count tokens on your own text with the counters below.
Check it on your own traffic
- Qwen3.5 35B A3B API pricing: all 7 providers and other tiers.
- Step 3.7 Flash API pricing: all 3 providers and other tiers.
- Cost calculator with Qwen3.5 35B A3B and Step 3.7 Flash preloaded
- Qwen token counter
- Token counter
- Prompt caching calculator
More comparisons: DeepSeek V4.1 Flash vs Qwen3.5 35B A3B · Qwen3.6 35B A3B vs Qwen3.5 35B A3B · Qwen3.5 35B A3B vs Qwen3 30B A3B · Qwen3.5 35B A3B vs Qwen3.5 27B · Qwen3.5 122B A10B vs Qwen3.5 35B A3B · Qwen3.8 27B vs Step 3.7 Flash · Step 3.7 Flash vs Step-3.5-Flash · every Qwen3.5 35B A3B comparison · every Step 3.7 Flash comparison · all 662 price comparisons
Questions
Is Qwen3.5 35B A3B cheaper than Step 3.7 Flash?
Yes. On a blend of 3 input tokens to 1 output token, Qwen3.5 35B A3B costs USD 0.355 per 1M tokens and Step 3.7 Flash USD 0.4375, at each model's cheapest standard price. For input alone, Qwen3.5 35B A3B is cheaper (USD 0.14 against USD 0.20 per 1M); for output alone, Qwen3.5 35B A3B is (USD 1 against USD 1.15). This compares price only, not quality.
What do Qwen3.5 35B A3B and Step 3.7 Flash cost per 1M tokens?
Qwen3.5 35B A3B: from USD 0.14 input and USD 1 output at DeepInfra; Alibaba Cloud's own API charges USD 0.25 / USD 2; median of 7 standard prices USD 0.24 / USD 1.80. Step 3.7 Flash: from USD 0.20 input and USD 1.15 output at Featherless and 2 others; median of 3 standard prices USD 0.20 / USD 1.15. Each price is read from the provider's own pricing page; the source is linked in the table.
Which providers sell both Qwen3.5 35B A3B and Step 3.7 Flash?
2 providers have a standard price for both: GMI Cloud (USD 0.6875 and USD 0.4375 at 3:1), Novita AI (USD 0.6875 and USD 0.4375 at 3:1). The first 2 tie for the lowest combined price. Buying each model from its own cheapest provider costs USD 0.355 and USD 0.4375.
Which is cheaper for a coding agent or a chatbot, Qwen3.5 35B A3B or Step 3.7 Flash?
For a coding agent (1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning): USD 204.30 a month on Qwen3.5 35B A3B (DeepInfra) against USD 218.70 on Step 3.7 Flash (Featherless), a difference of USD 14.40. For a support chatbot (2,000 requests a day, 1,500 input tokens (60% cached), 300 output): USD 25.74 a month on Qwen3.5 35B A3B (DeepInfra) against USD 30.06 on Step 3.7 Flash (Featherless), a difference of USD 4.32. 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 Qwen3.5 35B A3B and Step 3.7 Flash change?
Qwen3.5 35B A3B 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 Step 3.7 Flash's, so the input:output ratio never changes the answer.
Do Qwen3.5 35B A3B and Step 3.7 Flash have cached input pricing?
Qwen3.5 35B A3B from USD 0.05 per 1M cached input tokens (DeepInfra; 4 of 7 standard prices list a discount). Step 3.7 Flash from USD 0.04 per 1M cached input tokens (Featherless; 3 of 3 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, Qwen3.5 35B A3B or Step 3.7 Flash?
Both go up to 262,144 tokens on the providers that state it.