Qwen3 30B A3B API pricing
Alibaba · Budget price tier · Apache 2.0 · released 2025-04. Prices in USD per 1 million tokens. Data snapshot: 2026-11-12.
A support ticket workload of 100K requests a month costs $43.00 on Qwen3 30B A3B; the next cheaper model in the Budget price tier for this workload, LFM2.5-24B-A2B, does it for $42.50. The price we quote for Qwen3 30B A3B has changed 4 times since 2026-08-15, most recently on 2026-10-01 when the quoted host changed (-4.2%); it is now the 78th cheapest of 160 models in the Budget price tier. Only one host, DeepInfra, sells it, so there is no second price to shop. It is rated a stable release but does not meet all four criteria of the FinOps Friendly badge.
- Input: $0.12 per 1M tokens
- Output: $0.50 per 1M tokens
- Batch API (in/out): Not published
- Prompt-cache read: Not published
- Context window: 41K tokens
- Arena ELO: 1317 as of 2026-11-08
Market position
On blended price ($0.386 per 1M tokens at 30% input, 70% output) it is cheaper than 52% of models in the Budget price tier: 78th cheapest of 160. Across every price tier it is cheaper than 75% of priced text models in the catalogue: 78th cheapest of 303. Its Arena ELO of 1317 ranks 135th of the 160 models that carry one, above 16% of them. With an Arena score of 1317, Qwen3 30B A3B sits below OptimNow's lowest working quality threshold, Standard (Arena 1420+), so the quality-bar method would not shortlist it for any of the 8 use cases the table prices. Each threshold is a distance below the best ranked model, which scores 1530 on Arena scores as of 8 Nov 2026.
Licence, size and capabilities
Qwen3 30B A3B is open source: its weights are published under Apache 2.0, an OSI-approved licence with no field-of-use limit, so it can be self-hosted as well as bought by the token. Its published size is 30B parameters. Listed capabilities: Text, Reasoning, Agents. Filling its 41K context window once costs $0.00492 in input tokens at list price.
Pricing by host
A host is a company that runs the model and sells it by the token: the model maker, a cloud platform like Amazon Bedrock, Azure or Vertex, or an independent host. One model, several hosts, and often several prices. This model is sold by 1 host. The price we quote elsewhere on this page is marked. We quote one host's rate so that models stay comparable; it is not a recommendation to buy there.
DeepInfra is the only host with a published rate, $0.12 input / $0.50 output per 1M tokens, which is the price we quote. It serves a quantized fp8 build, which is not the same product as the full-precision model.
| Host | Input $/1M | Output $/1M | Precision |
|---|---|---|---|
| DeepInfra (price we quote) | $0.12 | $0.50 | fp8 |
List prices as published on 2026-11-12, via OpenRouter. Negotiated rates, committed-use discounts and provisioned capacity are not shown.
Monthly cost at 100K requests, by business use case
From the after-discounts figure (prompt caching on the cached input share, batch API for async workloads, only where Alibaba publishes those rates), which assumes you implement both, to the list price. One figure means no discount is published.
| Use case | Tokens (in/out) | Monthly (after discounts – list) |
|---|---|---|
| Support Ticket | 1,500 / 500 | $43 |
| Knowledge Q&A | 2,000 / 800 | $64 |
| Meeting Summary | 10,000 / 1,200 | $180 |
| Marketing Content | 2,500 / 1,800 | $120 |
| Coding Task | 3,000 / 2,000 | $136 |
| Invoice Processing | 1,500 / 600 | $48 |
| Call Summary | 2,000 / 700 | $59 |
| Agent Workflow | 6,000 / 3,000 | $222 |
Price history
Qwen3 30B A3B has been in our daily price archive since tracking began on 2026-08-15, when it listed at $0.12 input / $0.50 output per 1M tokens. The price we quote has changed 4 times since then, 2 of them a change of quoted host rather than a repricing. The latest change, on 2026-10-01, was -4.2% on the blended price (30% input, 70% output), to $0.12 input / $0.50 output (quoted host changed, not a repricing). Net of all changes, the blended price is back where it started on 2026-08-15.
| Date | Old price (in / out) | New price (in / out) | Blended change |
|---|---|---|---|
| 2026-10-01 | $0.13 / $0.52 | $0.12 / $0.50 | -4.2% (quoted host changed, not a repricing) |
| 2026-09-30 | $0.12 / $0.50 | $0.13 / $0.52 | +4.4% (quoted host changed, not a repricing) |
| 2026-08-23 | $0.13 / $0.52 | $0.12 / $0.50 | -4.2% |
| 2026-08-16 | $0.12 / $0.50 | $0.13 / $0.52 | +4.4% |
Alternatives to Qwen3 30B A3B
3 of the 4 comparable models below cost less than Qwen3 30B A3B: Granite 4.2 8B undercuts it by 68%, and scores 1 Arena point higher.
- Next cheaper model in the Budget price tier: Claude Haiku 5.5 (Anthropic) at $0.38 blended, 2% less.
- Next more expensive: Qwen2.5 72B Instruct (Alibaba) at $0.388 blended, 1% more.
The nearest models in the Budget price tier on Arena ELO, each with its blended price and score difference against Qwen3 30B A3B.
- Granite 4.2 8B (ibm-granite): $0.06 in / $0.15 out per 1M, Arena ELO 1318 (68% cheaper, 1 ELO point higher)
- GPT-5 Nano (OpenAI): $0.05 in / $0.40 out per 1M, Arena ELO 1320 (24% cheaper, 3 ELO points higher)
- Nemotron 3.5 Lightning (Nvidia): $0.07 in / $0.20 out per 1M, Arena ELO 1329 (58% cheaper, 12 ELO points higher)
- GLM 4.5V (Zhipu): $0.60 in / $1.80 out per 1M, Arena ELO 1333 (273% more expensive, 16 ELO points higher)
- Cheapest within 15 Arena points: Granite 4.2 8B (ibm-granite), 68% cheaper, 1 ELO point higher, out of 5 models in that band.
- Highest Arena ELO within 20% of this price: Gemma 4 31B (Google), 12% cheaper, 126 ELO points higher, out of 10 models in that price band.
Other models from Alibaba
The 8 nearest to Qwen3 30B A3B in price, of 39 other Alibaba models in the catalogue. Prices per 1M tokens, input then output.
- Qwen3 32B: $0.08 / $0.28
- Qwen3 30B A3B Instruct 2507: $0.10 / $0.30
- Qwen3.8 Flash: $0.15 / $0.47
- Qwen3.8 Omni Flash: $0.15 / $0.47
- Qwen2.5 72B Instruct: $0.36 / $0.40
- Qwen3 Coder 30B A3B Instruct: $0.15 / $0.60
- Qwen3 VL 30B A3B Instruct: $0.15 / $0.60
- Qwen3 Coder Next: $0.12 / $0.80
All 40 Alibaba models and prices
Common questions about Qwen3 30B A3B pricing
- How much does Qwen3 30B A3B cost?
- Qwen3 30B A3B costs $0.12 per 1M input tokens and $0.50 per 1M output tokens at DeepInfra, the host whose rate we quote. DeepInfra serves a quantized fp8 build, which is not the same product as the full-precision model. Prices as listed on 2026-11-12.
- Which host is cheapest for Qwen3 30B A3B?
- DeepInfra is the only host with a published rate, $0.12 input / $0.50 output per 1M tokens, which is the price we quote. It serves a quantized fp8 build, which is not the same product as the full-precision model. Host rates as listed on 2026-11-12.
- Does Qwen3 30B A3B offer batch or cached pricing?
- No. Neither a batch rate nor a prompt-cache rate is published for Qwen3 30B A3B as of 2026-11-12.
- What would Qwen3 30B A3B cost per month?
- With the Support Ticket profile (1,500 input and 500 output tokens per request), 100,000 requests a month cost about $43 on Qwen3 30B A3B at the list price quoted on 2026-11-12.
- Can Qwen3 30B A3B be self-hosted?
- Yes. Qwen3 30B A3B is open source: its weights are published under Apache 2.0, an OSI-approved licence with no field-of-use limit, so it can be self-hosted as well as bought by the token.
- Has the price of Qwen3 30B A3B changed?
- Qwen3 30B A3B has been in our daily price archive since tracking began on 2026-08-15, when it listed at $0.12 input / $0.50 output per 1M tokens. The price we quote has changed 4 times since then, 2 of them a change of quoted host rather than a repricing. The latest change, on 2026-10-01, was -4.2% on the blended price (30% input, 70% output), to $0.12 input / $0.50 output (quoted host changed, not a repricing). Net of all changes, the blended price is back where it started on 2026-08-15.
Its weights are published, which changes what you may run yourself: the cost gap between open weights and proprietary APIs.
These are list prices. Your real cost also depends on caching and batching, negotiated discounts, marketplace agreements, and the contracts you already have. OptimNow audits exactly that.
Build the business case · Get a FinOps review
LLM pricing · Models by maker · Cloud compute pricing · Compare models · Price barometer · FinOps guides · API and MCP server