Qwen3.5 35B A3B vs GLM 4.5 Air API pricing
Updated
Qwen3.5 35B A3B: USD 0.14 input, USD 1 output per 1M tokens (DeepInfra). GLM 4.5 Air: USD 0.13 input, USD 0.85 output per 1M tokens (Novita AI). At 3 input tokens per output token, Qwen3.5 35B A3B costs 15% more than GLM 4.5 Air (USD 0.355 vs USD 0.31 per 1M).
How do Qwen3.5 35B A3B and GLM 4.5 Air differ on price?
- Cheapest input price: GLM 4.5 Air USD 0.13 against USD 0.14 per 1M tokens, so Qwen3.5 35B A3B costs 1.08× as much (8% more).
- Cheapest output price: GLM 4.5 Air USD 0.85 against USD 1 per 1M tokens, so Qwen3.5 35B A3B costs 1.18× as much (18% more).
- Among the 201 indexed models, Qwen3.5 35B A3B ranks 76th cheapest and GLM 4.5 Air 72nd on the 3:1 blend.
- No input:output mix changes the answer: GLM 4.5 Air 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); GLM 4.5 Air at 2 standard prices of 4, from USD 0.025 (Novita AI, 81% below that provider's input price).
- Qwen3.5 35B A3B states up to 262,144 tokens of context, 2× the 131,076 of GLM 4.5 Air.
- Qwen3.5 35B A3B has 7 providers with a standard price, 3 more than GLM 4.5 Air; 3 providers sell both (SiliconFlow, Novita AI and GMI Cloud).
- On one account, SiliconFlow charges USD 0.63 for Qwen3.5 35B A3B (1.77× its cheapest price) and USD 0.32 for GLM 4.5 Air (1.03× its cheapest price) at 3:1, 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 1.37× for GLM 4.5 Air.
- Qwen's own API charges USD 0.6875 for Qwen3.5 35B A3B at 3:1, 94% above the cheapest provider (DeepInfra).
- Z.ai's own API charges USD 0.425 for GLM 4.5 Air at 3:1, 37% above the cheapest provider (Novita AI).
- For the one-developer coding agent preset, the gap is USD 653.40 a year in GLM 4.5 Air's favour (Qwen3.5 35B A3B USD 204.30 a month, GLM 4.5 Air USD 149.85).
Qwen3.5 35B A3B and GLM 4.5 Air 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 | GLM 4.5 Air |
|---|---|---|
| Model page | Qwen3.5 35B A3B Qwen · 7 providers | GLM 4.5 Air Z.ai · 4 providers |
| Cheapest standard price, blended 3:1 | USD 0.355 USD 0.14 in / USD 1 out at DeepInfra DeepInfra page checked 2026-11-14 | USD 0.31 lower USD 0.13 in / USD 0.85 out at Novita AI Novita AI page checked 2026-11-14 |
| Cheapest input | USD 0.14 DeepInfra source | USD 0.13 lower Novita AI source |
| Cheapest cached input | USD 0.05 DeepInfra source | USD 0.025 lower Novita AI source |
| Cheapest output | USD 1 DeepInfra source | USD 0.85 lower Novita AI source |
| Maker's own API | USD 0.25 / USD 2 Alibaba Cloud source | USD 0.20 / USD 1.10 Z.ai source |
| Median standard price | USD 0.24 / USD 1.80 input / output, 7 prices | USD 0.17 / USD 0.98 input / output, 4 prices |
| Context window | 262,144 tokens, largest stated; from 256,000 at some providers | 131,076 tokens, largest stated; from 131,072 at some providers |
| Providers with a standard price | 7 | 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 Qwen3.5 35B A3B and GLM 4.5 Air 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 | GLM 4.5 Air | Difference |
|---|---|---|---|
| Support chatbot 2,000 requests a day, 1,500 input tokens (60% cached), 300 output | USD 25.74 DeepInfra | USD 21.33 Novita AI | USD 4.41 GLM 4.5 Air lower |
| RAG over documents 1,000 requests a day, 8,000 input tokens (30% cached), 500 output | USD 42.12 DeepInfra | USD 36.39 Novita AI | USD 5.73 GLM 4.5 Air 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 149.85 Novita AI | USD 54.45 GLM 4.5 Air lower |
GLM 4.5 Air is cheaper on all three workloads. The widest gap is on Coding agent (one developer): the dearer model costs 36% more than the cheaper one.
Does the cheaper model change with your input:output ratio?
GLM 4.5 Air 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 Qwen3.5 35B A3B's, so the input:output ratio never changes the answer.
| Input : output tokens | Qwen3.5 35B A3B | GLM 4.5 Air |
|---|---|---|
| 1 : 3 (long answers) | USD 0.785 DeepInfra | USD 0.67 lower Novita AI |
| 1 : 1 | USD 0.57 DeepInfra | USD 0.49 lower Novita AI |
| 3 : 1 (the site’s blend) | USD 0.355 DeepInfra | USD 0.31 lower Novita AI |
| 10 : 1 (retrieval, long prompts) | USD 0.2182 DeepInfra | USD 0.1955 lower Novita AI |
| 30 : 1 (agents, big contexts) | USD 0.1677 DeepInfra | USD 0.1532 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 Qwen3.5 35B A3B and GLM 4.5 Air cost per character in other languages?
Not measured: the real cost by language dataset covers only tokenizers we could measure from published files, and GLM 4.5 Air 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.
- GLM 4.5 Air API pricing: all 4 providers and other tiers.
- Cost calculator with Qwen3.5 35B A3B and GLM 4.5 Air preloaded
- Qwen token counter
- GLM 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 GLM 4.5 Air · GLM 4.5 Air vs GLM-4.5-FP8 · every Qwen3.5 35B A3B comparison · every GLM 4.5 Air comparison · all 662 price comparisons
Questions
Is Qwen3.5 35B A3B cheaper than GLM 4.5 Air?
No. On a blend of 3 input tokens to 1 output token, GLM 4.5 Air costs USD 0.31 per 1M tokens and Qwen3.5 35B A3B USD 0.355, at each model's cheapest standard price. For input alone, GLM 4.5 Air is cheaper (USD 0.13 against USD 0.14 per 1M); for output alone, GLM 4.5 Air is (USD 0.85 against USD 1). This compares price only, not quality.
What do Qwen3.5 35B A3B and GLM 4.5 Air 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. GLM 4.5 Air: from USD 0.13 input and USD 0.85 output at Novita AI; Z.ai's own API charges USD 0.20 / USD 1.10; median of 4 standard prices USD 0.17 / USD 0.98. 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 GLM 4.5 Air?
3 providers have a standard price for both: SiliconFlow (USD 0.63 and USD 0.32 at 3:1), Novita AI (USD 0.6875 and USD 0.31 at 3:1), GMI Cloud (USD 0.6875 and USD 0.425 at 3:1). The first is the lowest combined price. Buying each model from its own cheapest provider costs USD 0.355 and USD 0.31.
Which is cheaper for a coding agent or a chatbot, Qwen3.5 35B A3B or GLM 4.5 Air?
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 149.85 on GLM 4.5 Air (Novita AI), a difference of USD 54.45. 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 21.33 on GLM 4.5 Air (Novita AI), a difference of USD 4.41. 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 GLM 4.5 Air change?
GLM 4.5 Air 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 Qwen3.5 35B A3B's, so the input:output ratio never changes the answer.
Do Qwen3.5 35B A3B and GLM 4.5 Air 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). GLM 4.5 Air from USD 0.025 per 1M cached input tokens (Novita AI; 2 of 4 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 GLM 4.5 Air?
Qwen3.5 35B A3B: up to 262,144 tokens, against 131,076 for GLM 4.5 Air, 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.