# Qwen3 235B API

Qwen3 235B is Alibaba's open-weight Qwen3 mixture-of-experts model (2507 release) with 235B total and 22B active parameters, served on Seedrise with a 256K-token context window and up to 8K output tokens; list price $0.23 in / $0.91 out per 1M tokens, provider list as at 1 November 2026.

- Provider: Alibaba
- Model ID: qwen3-235b
- Type: Chat
- Region: AU (can be pinned to Sydney or Melbourne on request)
- Context window: not listed
- Max output: not listed
- Modalities: not listed
- Endpoints: OpenAI Chat Completions https://api.seedrise.ai/v1
- Prices checked: 1 November 2026

## Provider list price

Provider list price as at 1 November 2026, per 1M tokens. AUD at a reference rate of 1 USD = 1.53 AUD; invoices use the rate on the day.

| Token type | USD | AUD |
|---|---:|---:|
| Input | 0.23 | 0.35 |
| Output | 0.91 | 1.39 |
| Cached input | Rates on request | Rates on request |

Your Seedrise rate is quoted per account against this list price. Request a rate card: https://seedrise.ai/contact?model=qwen3-235b

Pinning to an Australian region carries the provider's regional premium on top of the list price shown.

Marked AU: can be pinned to Sydney or Melbourne on request. Text input and output only, with an 8K-token output limit on the Australian-region deployment.

## Strengths

- Can be pinned to Sydney or Melbourne on request
- Open weights under the Apache 2.0 licence
- Instruction following, reasoning, coding and tool use improved in the 2507 release, per Qwen
- Broad long-tail knowledge across many languages

## Typical use cases

- Australian workloads that need a Qwen model with in-region inference
- Text and code generation under data residency requirements
- Classification and extraction pipelines kept in Australia
- Teams that want an open-weight model they could also self-host later

## Quickstart

A first request with curl. Replace sk-... with your Seedrise key.

```bash
curl https://api.seedrise.ai/v1/chat/completions \
  -H "Authorization: Bearer sk-..." \
  -H "Content-Type: application/json" \
  -d '{"model":"qwen3-235b","messages":[{"role":"user","content":"Hello"}]}'
```

OpenAI SDK, Python:

```python
from openai import OpenAI

client = OpenAI(base_url="https://api.seedrise.ai/v1", api_key="sk-...")

r = client.chat.completions.create(
    model="qwen3-235b",
    messages=[{"role": "user", "content": "Summarise this contract in three bullets."}],
)
print(r.choices[0].message.content)
```

## Where it runs

AU: Can be pinned to Sydney or Melbourne on request. Pinning is set per key, not per request.

## Related models

- [Qwen3.8 Max](https://seedrise.ai/models/qwen3.8-max): US$2.00 input · US$6.00 output per 1M tokens, SG
- [Qwen3.7 Plus](https://seedrise.ai/models/qwen3.7-plus): US$0.40 input · US$1.60 output per 1M tokens, SG
- [Qwen3.8 Flash](https://seedrise.ai/models/qwen3.8-flash): US$0.15 input · US$0.47 output per 1M tokens, SG
- [DeepSeek V4.1 Flash](https://seedrise.ai/models/deepseek-flash): US$0.30 input · US$1.20 output per 1M tokens, Global
- [Mistral Small 4](https://seedrise.ai/models/mistral-small-4): US$0.15 input · US$0.60 output per 1M tokens, Global
- [Claude Haiku 5.5](https://seedrise.ai/models/claude-haiku-5-5): US$0.10 input · US$0.50 output per 1M tokens, AU

## FAQ

### What is the model ID for Qwen3 235B?

Use qwen3-235b as the model field, with no vendor prefix, on the OpenAI-compatible endpoint at https://api.seedrise.ai/v1. GET /v1/models returns the IDs your key can call.

### How does the Seedrise rate for Qwen3 235B compare to the list price?

Alibaba's list price as at 1 November 2026 is US$0.23 per 1M input tokens and US$0.91 per 1M output tokens. Seedrise quotes rates per account against the provider's published list price for the same routing. Volume and committed tiers sit below list. Australian-region routing carries the provider's regional premium.

### What is the context window and max output of Qwen3 235B?

Context window and maximum output for Qwen3 235B are not listed on our rate card yet; ask us for the current limits.

### Can Qwen3 235B run in Australia?

Yes. Qwen3 235B can be pinned to Sydney or Melbourne on request. Pinning is set per key, not per request, and carries the provider's regional premium.

### Is Qwen3 235B the same as Qwen3.8?

No. Qwen3 235B is the open-weight Qwen3 generation (2507 release), served from Australian regions. Qwen3.8 Max and Qwen3.8 Flash are newer Alibaba models that run from Singapore.

### What are the limits of Qwen3 235B on Seedrise?

A 256K-token context window and up to 8K output tokens, with text input and output only.

Model names are trademarks of their respective providers.

Source: https://seedrise.ai/models/qwen3-235b