# Qwen3.8 Max

Model tracker · checked 2026-10-14 · https://dbggr.dev/models/qwen3-8-max/

Qwen3.8 Max is an everyday open-weight model from Alibaba, released 3 August 2026. At Alibaba it costs $2.00 per million input tokens and $6.00 per million output tokens, with a 1M-token context window. 6 providers serve it; the cheapest is DeepInfra at $1.65 input and $4.95 output.

- Made by: Alibaba Group (Qwen, Alibaba Cloud)
- Released: 2026-08-03
- Status: Generally available
- Tier: Everyday
- Weights: Open
- Context window: 1,000,000 tokens
- Input: text
- API id: qwen3.8-max
- Docs: https://www.alibabacloud.com/help/en/model-studio/models

## Qwen3.8 Max price at 6 providers

US dollars per million tokens. Blended is 3 input tokens for every output token, one number to compare on. The cheapest blended price is highlighted.

| Provider | Input | Output | Cached input | Blended | Batch | Checked |
|---|---|---|---|---|---|---|
| DeepInfra | $1.65 | $4.95 | $0.206 | $2.48 | – | [2026-10-14](https://deepinfra.com/pricing) |
| Alibaba | $2.00 | $6.00 | $0.20 | $3.00 | – | [2026-10-14](https://www.alibabacloud.com/help/en/model-studio/model-pricing) |
| Fireworks AI | $2.00 | $6.00 | $0.25 | $3.00 | 50% off | [2026-10-14](https://docs.fireworks.ai/serverless/pricing) |
| Modal Labs | $2.00 | $6.00 | $0.25 | $3.00 | – | [2026-10-14](https://modal.com/library/qwen/qwen3-8-max) |
| Novita AI | $2.00 | $6.00 | $0.25 | $3.00 | – | [2026-10-14](https://novita.ai/pricing) |
| Together AI | $2.00 | $6.00 | $0.25 | $3.00 | – | [2026-10-14](https://www.together.ai/pricing) |

- Alibaba: International (Singapore) deployment, up to 1M input tokens. Cache hits billed at 10% of input, explicit cache creation at 125%. A 50% batch discount is listed only for the China (Beijing) region.
- Fireworks AI: Priority tier: $3.00 in / $0.375 cached / $9.00 out.
- Modal Labs: Modal Shared Endpoint, billed per token from us-west; plan credits can't be used for Shared Endpoint usage. 262K native context, up to 1.01M.

## Qwen3.8 Max benchmarks

| Benchmark | Score | What it measures | Reported by |
|---|---|---|---|
| LMArena text score | 1482 | Elo-style score from people voting between answers | [Independent](https://arena.ai/leaderboard/text) |

Scores reported by a model's maker aren't independently checked.

## Models like Qwen3.8 Max

| Model | Input | Output | Context | Weights |
|---|---|---|---|---|
| Qwen3.8 Max | $2.00 | $6.00 | 1M | Open |
| [Mistral Medium 3.5](https://dbggr.dev/models/mistral-medium-3-5/) | $1.50 | $7.50 | 256K | Open |
| [Grok 4.7](https://dbggr.dev/models/grok-4-7/) | $2.00 | $6.00 | 500K | Closed |
| [Claude Sonnet 5.5](https://dbggr.dev/models/claude-sonnet-5-5/) | $2.00 | $10.00 | 1M | Closed |
| [GPT-6.1 Sol](https://dbggr.dev/models/gpt-6-1-sol/) | $2.00 | $10.00 | 1.1M | Closed |
| [GLM-5.3](https://dbggr.dev/models/glm-5-3/) | $1.40 | $4.40 | 1M | Open |

## FAQ

### How much does Qwen3.8 Max cost?

Qwen3.8 Max costs $2.00 per million input tokens and $6.00 per million output tokens at Alibaba, and $0.20 per million cached input tokens. Prices are list prices in US dollars, last checked 14 October 2026.

### What is Qwen3.8 Max's context window?

Qwen3.8 Max takes up to 1,000,000 tokens in one request.

### Is Qwen3.8 Max open weight?

Yes. Alibaba publishes the weights, so you can run Qwen3.8 Max yourself or at any host that serves it.

### Where can I use Qwen3.8 Max?

Qwen3.8 Max is available from DeepInfra, Alibaba, Fireworks AI, Modal Labs, Novita AI and Together AI. At Alibaba, call it as `qwen3.8-max`.