Qwen3 235B A22B Instruct 2507 API pricing
Alibaba · Budget price tier · Apache 2.0 · released 2025-07. Prices in USD per 1 million tokens. Data snapshot: 2026-11-12.
A support ticket workload of 100K requests a month costs $61.00 on Qwen3 235B A22B Instruct 2507; the next cheaper model in the Budget price tier for this workload, Qwen3.6 35B A3B, does it for $60.00. The price we quote for Qwen3 235B A22B Instruct 2507 has changed 6 times since 2026-08-15, most recently on 2026-11-04 when the quoted host changed (+46.1%); it is now the 98th cheapest of 160 models in the Budget price tier. Buying from DeepInfra rather than at the price we quote lowers the token price by about 32%, for a quantized fp8 build. It is rated a stable release but does not meet all four criteria of the FinOps Friendly badge.
- Input: $0.14 per 1M tokens
- Output: $0.80 per 1M tokens
- Batch API (in/out): Not published
- Prompt-cache read: $0.05 per 1M tokens
- Context window: 262K tokens
- Arena ELO: 1419 as of 2026-11-08
Available on
AWS Bedrock regions: ap-northeast-1, eu-central-1, us-east-2, us-west-2
Market position
On blended price ($0.602 per 1M tokens at 30% input, 70% output) it is cheaper than 39% of models in the Budget price tier: 98th cheapest of 160. Across every price tier it is cheaper than 68% of priced text models in the catalogue: 98th cheapest of 303. Its Arena ELO of 1419 ranks 80th of the 160 models that carry one, tied with one other, above 50% of them. With an Arena score of 1419, Qwen3 235B A22B Instruct 2507 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. It is 1 point under the Standard bar (Arena 1420+), within the benchmark's 20-point noise. 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 235B A22B Instruct 2507 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 235B parameters. Listed capabilities: Text, Agents. Filling its 262K context window once costs $0.0367 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 4 different hosts. 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.
Cheapest host: DeepInfra at $0.09 input / $0.55 output per 1M tokens, 32% below the price we quote on the blended price (30% input, 70% output). It serves a quantized fp8 build, which is not the same product as the full-precision model. A support ticket workload at 100K requests a month costs $41.00 there against $61.00 at the price we quote, a difference of $20.00 a month. The dearest, Parasail, charges 1.5x the cheapest.
| Host | Input $/1M | Output $/1M | Precision |
|---|---|---|---|
| DeepInfra | $0.09 | $0.55 | fp8 |
| Nebius | $0.20 | $0.60 | fp8 |
| Venice | $0.15 | $0.75 | fp8 |
| Parasail (price we quote) | $0.14 | $0.80 | 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 | $53 – $61 |
| Knowledge Q&A | 2,000 / 800 | $79 – $92 |
| Meeting Summary | 10,000 / 1,200 | $227 – $236 |
| Marketing Content | 2,500 / 1,800 | $175 – $179 |
| Coding Task | 3,000 / 2,000 | $189 – $202 |
| Invoice Processing | 1,500 / 600 | $65 – $69 |
| Call Summary | 2,000 / 700 | $82 – $84 |
| Agent Workflow | 6,000 / 3,000 | $286 – $324 |
Price history
Qwen3 235B A22B Instruct 2507 has been in our daily price archive since tracking began on 2026-08-15, when it listed at $0.09 input / $0.55 output per 1M tokens. The price we quote has changed 6 times since then, 5 of them a change of quoted host rather than a repricing. The latest change, on 2026-11-04, was +46.1% on the blended price (30% input, 70% output), to $0.14 input / $0.80 output (quoted host changed, not a repricing). Net of all changes, the blended price is +46.1% against 2026-08-15.
| Date | Old price (in / out) | New price (in / out) | Blended change |
|---|---|---|---|
| 2026-11-04 | $0.09 / $0.55 | $0.14 / $0.80 | +46.1% (quoted host changed, not a repricing) |
| 2026-10-06 | $0.0875 / $0.35 | $0.09 / $0.55 | +51.9% (quoted host changed, not a repricing) |
| 2026-09-13 | $0.22 / $0.88 | $0.0875 / $0.35 | -60.2% (quoted host changed, not a repricing) |
| 2026-09-09 | $0.09 / $0.55 | $0.22 / $0.88 | +65.5% (quoted host changed, not a repricing) |
| 2026-09-05 | $0.0875 / $0.35 | $0.09 / $0.55 | +51.9% (quoted host changed, not a repricing) |
1 earlier change is not listed.
Alternatives to Qwen3 235B A22B Instruct 2507
None of the 4 comparable models below costs less than Qwen3 235B A22B Instruct 2507 on the blended price.
- Next cheaper model in the Budget price tier: Qwen3 VL 8B Instruct (Alibaba) at $0.60 blended, under 1% less.
- Next more expensive: Mi:dm K 3.0 Pro (kt) at $0.62 blended, 3% more.
The nearest models in the Budget price tier on Arena ELO, each with its blended price and score difference against Qwen3 235B A22B Instruct 2507.
- Qwen3 VL 235B A22B Instruct (Alibaba): $0.21 in / $1.90 out per 1M, Arena ELO 1420 (131% more expensive, 1 ELO point higher)
- DeepSeek V3.1 (DeepSeek): $0.25 in / $0.95 out per 1M, Arena ELO 1420 (23% more expensive, 1 ELO point higher)
- DeepSeek V3.1 Terminus (DeepSeek): $0.27 in / $1.00 out per 1M, Arena ELO 1417 (30% more expensive, 2 ELO points lower)
- Qwen3 Next 80B A3B Instruct (Alibaba): $0.09 in / $1.10 out per 1M, Arena ELO 1417 (32% more expensive, 2 ELO points lower)
- Cheapest within 15 Arena points: Gemma 4 26B A4B (Google), 84% cheaper, 15 ELO points higher, out of 34 models in that band.
- Highest Arena ELO within 20% of this price: Qwen3 235B A22B Instruct 2507 itself has the highest score of the 8 models priced within 20% of it.
Other models from Alibaba
The 8 nearest to Qwen3 235B A22B Instruct 2507 in price, of 39 other Alibaba models in the catalogue. Prices per 1M tokens, input then output.
- 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
- Qwen3 VL 8B Instruct: $0.25 / $0.75
- Qwen-Plus: $0.26 / $0.78
- Qwen3.6 35B A3B: $0.10 / $0.90
- Qwen3 Coder Flash: $0.195 / $0.975
- Qwen3.5-35B-A3B: $0.14 / $1.00
All 40 Alibaba models and prices
Common questions about Qwen3 235B A22B Instruct 2507 pricing
- How much does Qwen3 235B A22B Instruct 2507 cost?
- Qwen3 235B A22B Instruct 2507 costs $0.14 per 1M input tokens and $0.80 per 1M output tokens at Parasail, the host whose rate we quote. Parasail 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 235B A22B Instruct 2507?
- Cheapest host: DeepInfra at $0.09 input / $0.55 output per 1M tokens, 32% below the price we quote on the blended price (30% input, 70% output). It serves a quantized fp8 build, which is not the same product as the full-precision model. A support ticket workload at 100K requests a month costs $41.00 there against $61.00 at the price we quote, a difference of $20.00 a month. The dearest, Parasail, charges 1.5x the cheapest. Host rates as listed on 2026-11-12.
- Does Qwen3 235B A22B Instruct 2507 offer batch or cached pricing?
- Yes, for prompt caching only. Cache reads cost $0.05 per 1M tokens, as listed on 2026-11-12. No batch pricing is published.
- What would Qwen3 235B A22B Instruct 2507 cost per month?
- With the Support Ticket profile (1,500 input and 500 output tokens per request), 100,000 requests a month cost about $61 on Qwen3 235B A22B Instruct 2507 at the list price quoted on 2026-11-12.
- Can Qwen3 235B A22B Instruct 2507 be self-hosted?
- Yes. Qwen3 235B A22B Instruct 2507 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 235B A22B Instruct 2507 changed?
- Qwen3 235B A22B Instruct 2507 has been in our daily price archive since tracking began on 2026-08-15, when it listed at $0.09 input / $0.55 output per 1M tokens. The price we quote has changed 6 times since then, 5 of them a change of quoted host rather than a repricing. The latest change, on 2026-11-04, was +46.1% on the blended price (30% input, 70% output), to $0.14 input / $0.80 output (quoted host changed, not a repricing). Net of all changes, the blended price is +46.1% against 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