impulse

Qwen3.8 Max

Open weights

Qwen3.8 Max 0902 is an updated snapshot of Qwen3.8 Max from Alibaba's Qwen team.

API id qwen3.8-maxReleased 3 Sep 2026 (Sep 2026)
Input / 1M
$2.00
at Alibaba DashScope
Output / 1M
$6.00
at Alibaba DashScope
Context window
992K
tokens
Max output
131K
tokens per reply
Hosts
11
14 listings
Released
Sep 2026
3 Sep 2026

Pricing

List prices at Alibaba DashScope, in US dollars per million tokens.

TierInput / 1MOutput / 1M
Standard$2.00$6.00
Cached input
88% off input
$0.25

What it costs a month

At Alibaba DashScope list prices, 30 days.

  • Chat assistant5,000 requests a day, 2K in / 0.5K out, cached$893
  • RAG over documents2,000 requests a day, 8K in / 0.6K out, cached$756
  • Coding agent1,000 requests a day, 40K in / 2K out, cached$1,290
  • Overnight batch20,000 requests a day, 4K in / 0.4K out$6,240
Use your own numbers

Where to run it

11 hosts serve Qwen3.8 Max. The comparison is on blended price, 3 parts input to 1 part output.

HostIn / out per 1M
qwen3.8-max
$2.00 / $6.00
qwen3.8-max
$2.00 / $6.00
Qwen CloudLab API
qwen3.8-max
$2.00 / $6.00
DeepInfraInference
Qwen3.8-Max
$1.65 / $4.95
−17% vs headline
SCX.aiCloud
Qwen3.8-Max
$1.65 / $4.99
−17% vs headline
AIHubMixGateway
qwen3.8-max
$1.69 / $5.07
−15% vs headline
qwen3-8-max
$2.00 / $6.00
qwen3.8-max
$2.00 / $6.00
GMI CloudInference
Qwen3.8-Max
$2.00 / $6.00
Novita AIInference
qwen3.8-max
$2.00 / $6.00
Fireworks AIInference
qwen3p8-max
$2.00 / $6.00
Show 3 more listings: regions, snapshots and variants
EmpirioLabs AI
0902
qwen3-8-max-0902
$2.00 / $6.00
GMI Cloud
0902
Qwen3.8-Max-0902
$1.65 / $4.95
−17% vs headline
Fireworks AI
Alias
qwen3p8-max
$2.00 / $6.00

Capabilities

Core

  • Streaming
  • Function calling
  • JSON mode
  • Structured outputs

Multimodal

  • Vision
  • Image input
  • Audio
  • Image generation
  • Video

Advanced

  • Reasoning
  • Tool calling
  • MCP
  • Prompt caching
  • Batch API
  • Embeddings
Takes in
TextImages
Produces
Text
Features
Prompt caching
Open weights
License: Apache-2.0
Runtimes: Ollama, SGLang, llama.cpp, vLLM

Cheaper alternatives

Current models that cost less and keep most of what this one can do: tools, vision, reasoning, structured output, caching and enough context.

Same model, cheaper host

  • DeepInfra
    Qwen3.8-Max
    $1.65 / $4.95
    17% less
  • GMI Cloud
    Qwen3.8-Max-0902
    $1.65 / $4.95
    17% less
  • SCX.ai
    Qwen3.8-Max
    $1.65 / $4.99
    17% less
  • AIHubMix
    qwen3.8-max
    $1.69 / $5.07
    15% less

Smaller Alibaba Qwen models

No cheaper Alibaba Qwen model keeps its key capabilities.

Other frontier labs

  • GPT-6.1 Terra
    OpenAI · on OpenAI
    $1.00 / $5.00
    Has every key capability
    33% less
  • Gemini 3.8 Flash
    Google · on Google AI Studio
    $0.75 / $3.75
    Has every key capability
    50% less
  • Grok Build 0.1
    xAI · on xAI
    $1.00 / $2.00
    Has every key capability
    58% less
  • Claude Haiku 5.5
    Anthropic · on Anthropic
    $0.10 / $0.50
    Has every key capability
    93% less

Open-weight picks

  • Qwen4 Max
    Alibaba Qwen · on Together AI
    $1.43 / $4.28
    Has every key capability
    29% less
  • Inkling
    Independent · on DeepInfra
    $0.95 / $4.05
    Has every key capability
    43% less
  • Kimi K2.7 Code
    Moonshot AI · on CLF AI Gateway
    $0.38 / $1.60
    Has every key capability
    77% less
  • DeepSeek Flash
    DeepSeek · on DeepSeek
    $0.30 / $1.20
    Has every key capability
    83% less

Model line

Newer and older versions, at each lab's own price.

  1. Nov 2026Qwen4 MaxLatest$1.50 / $4.50
  2. Sep 2026Qwen3.8 MaxThis page$2.00 / $6.00
  3. UndatedQwen 3.8 Max$2.23 / $6.68
  4. May 2026Qwen3.7 Max$2.50 / $7.50
  5. May 2026Qwen 3.7 Max$2.07 / $6.21
  6. Jan 2026Qwen3 MaxNot listed

Call it

Using Alibaba DashScope's API.

Python
from litellm import completion

response = completion(
    model="dashscope/qwen3.8-max",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Quick answers

How much does Qwen3.8 Max cost?

On Alibaba DashScope, Qwen3.8 Max costs $2.00 per million input tokens and $6.00 per million output tokens. Cached input costs $0.25 per million tokens. The cheapest host is DeepInfra, at $1.65 per million input tokens and $4.95 per million output tokens.

Which APIs offer Qwen3.8 Max?

Qwen3.8 Max runs on 11 APIs: Alibaba DashScope, Qianwen AI Platform, Qwen Cloud, DeepInfra, SCX.ai, AIHubMix, EmpirioLabs AI, OpenCode Go, GMI Cloud and 2 more.

What is Qwen3.8 Max's context window?

992K tokens, with up to 131K tokens in one reply.

Is Qwen3.8 Max being retired?

No retirement date is scheduled for it on any API we track.

Is there a newer version of Qwen3.8 Max?

Yes. Qwen4 Max is the newest model in this line, released on 16 Nov 2026.

What are cheaper alternatives to Qwen3.8 Max?

Models that cost less and keep most of what it can do: GPT-6.1 Terra on OpenAI (33% less), Gemini 3.8 Flash on Google AI Studio (50% less) and Qwen4 Max on Together AI (29% less). Qwen3.8 Max itself costs 17% less on DeepInfra. Savings are on a mix of 3 input tokens to 1 output token.

When was Qwen3.8 Max released?

Alibaba Qwen released it on 3 Sep 2026.

What is Qwen3.8 Max's API model id?

Use qwen3.8-max with Alibaba DashScope. Other hosts use their own ids: Qwen3.8-Max on DeepInfra, Qwen3.8-Max on SCX.ai, qwen3-8-max on EmpirioLabs AI, Qwen3.8-Max on GMI Cloud.

Sources

Raw catalog entry for qwen3.8-max on Alibaba DashScope
{
  "cache_read_input_token_cost": 2.5e-7,
  "input_cost_per_token": 0.000002,
  "litellm_provider": "dashscope",
  "max_input_tokens": 991808,
  "max_output_tokens": 131072,
  "mode": "chat",
  "output_cost_per_token": 0.000006,
  "source": "https://www.alibabacloud.com/help/en/model-studio/models",
  "supports_function_calling": true,
  "supports_prompt_caching": true,
  "supports_reasoning": true,
  "supports_response_schema": true,
  "supports_tool_choice": true,
  "supports_vision": true
}