Alibaba Qwen: Qwen3.8 Max

2.4-trillion-parameter MoE flagship for coding, professional work, multimodal understanding, and long-horizon agentic workflows

Source-linked qwen Closed weights Released 2026-08-03

API record Report

InputT

OutputT

Input price$2/M

Output price$6/M

Context1M

Max output131.072K

Providers29

Inference availability

Providers

Provider-specific identifiers, limits, and listed prices per million tokens. Every row links back to the provider's own documentation.

Report a price

Providers offering Qwen3.8 Max
Provider	Provider model ID	Context	Max output	Input	Output	Cache read	Capabilities	Docs
Kenari	`qwen3-8-max`	1M	131.072K	—	—	—	ReasoningTools	Docs ↗
SCNet Token Plan	`Qwen3.8-Max`	1M	131.072K	—	—	—	ReasoningTools	Docs ↗
Alibaba Token Plan	`qwen3.8-max`	1M	131.072K	—	—	—	ReasoningToolsJSON	Docs ↗
Alibaba Token Plan (China)	`qwen3.8-max`	1M	131.072K	—	—	—	ReasoningToolsJSON	Docs ↗
Vancine	`qwen3.8-max`	1M	131.072K	$1.6	$4.8	$0.2	ReasoningTools	Docs ↗
Deep Infra	`Qwen/Qwen3.8-Max`	256K	131.072K	$1.65	$4.951	$0.206	ToolsJSON	Docs ↗
AIHubMix	`qwen3.8-max`	991K	128K	$1.69	$5.07	$0.169	ReasoningToolsJSON	Docs ↗
Ofox	`qwen/qwen3.8-max`	1M	131.072K	$1.71	$5.14	$0.17	ReasoningTools	Docs ↗
Alibaba (China)	`qwen3.8-max`	1M	131.072K	$1.777	$5.332	$0.222	ReasoningToolsJSON	Docs ↗
SCX.ai	`Qwen3.8-Max`	1M	131.072K	$1.815	$5.446	$0.17	ReasoningToolsJSON	Docs ↗
CrossModel	`qwen/qwen3.8-max`	1M	131.072K	$1.88	$5.63	$0.23	ReasoningToolsJSON	Docs ↗
EmpirioLabs AI	`qwen3-8-max`	1M	131.072K	$2	$6	$2	ReasoningToolsJSON	Docs ↗
Kilo Gateway	`qwen/qwen3.8-max`	1M	131.072K	$2	$6	$0.25	ReasoningToolsJSON	Docs ↗
OpenRouter	`qwen/qwen3.8-max`	1M	131.072K	$2	$6	$0.25	ReasoningToolsJSON	Docs ↗
Fireworks AI	`accounts/fireworks/models/qwen3p8-max`	262.144K	131.072K	$2	$6	$0.25	ReasoningTools	Docs ↗
ClinePass	`cline-pass/qwen3.8-max`	1M	131.072K	$2	$6	$0.25	ReasoningToolsJSON	Docs ↗
OrcaRouter	`qwen/qwen3.8-max`	1M	131.072K	$2	$6	$0.25	ReasoningTools	Docs ↗
Abacus	`qwen3.8-max`	1M	131.072K	$2	$6	—	ReasoningTools	Docs ↗
Cloudflare AI Gateway	`alibaba/qwen3.8-max`	1M	131.072K	$2	$6	$0.25	ReasoningTools	Docs ↗
DevPass (LLM Gateway)	`qwen3.8-max`	1M	1M	$2	$6	$0.25	ReasoningTools	Docs ↗
Alibaba	`qwen3.8-max`	1M	131.072K	$2	$6	$0.25	ReasoningToolsJSON	Docs ↗
Vercel AI Gateway	`alibaba/qwen3.8-max`	1M	128K	$2	$6	$0.25	ReasoningTools	Docs ↗
Ofox	`bailian/qwen3.8-max`	1M	131.072K	$2	$6	$0.25	ReasoningTools	Docs ↗
Merge Gateway	`qwen/qwen3.8-max`	1M	131.072K	$2	$6	$0.25	ReasoningToolsJSON	Docs ↗
Eden AI	`qwen/qwen3.8-max`	1M	131.072K	$2	$6	$0.25	ReasoningToolsJSON	Docs ↗
Requesty	`qwen3.8-max`	1.04858M	131.072K	$2	$6	$0.25	ReasoningToolsJSON	Docs ↗
LLM Gateway	`alibaba/qwen3.8-max`	1M	131.072K	$2	$6	$0.25	ReasoningTools	Docs ↗
NanoGPT	`qwen3.8-max`	991K	65.536K	$2	$6	$0.25	ToolsJSON	Docs ↗
302.AI	`qwen3.8-max`	1M	131.072K	$2.16	$6.36	—	ReasoningTools	Docs ↗

Capability badges appear only where the provider catalog explicitly lists support. A blank cell means the source is silent, not that the feature is absent.

Listed rates

Price across providers

Input price per million tokens as published by each provider. Bars are drawn from listed rates only — no traffic weighting, since the catalog observes no requests.

Lowest input $1.6/M

Across 25 priced providers

Median input $2/M

Midpoint of listed rates

Highest input $2.16/M

1.4× the lowest listed rate

Output range $4.8 – $6.36

Per million output tokens

Vancine $1.6/MLowest

Deep Infra $1.65/M

AIHubMix $1.69/M

Ofox $1.71/M

Alibaba (China) $1.777/M

SCX.ai $1.815/M

CrossModel $1.88/M

EmpirioLabs AI $2/M

Kilo Gateway $2/M

OpenRouter $2/M

Fireworks AI $2/M

ClinePass $2/M

OrcaRouter $2/M

Abacus $2/M

Cloudflare AI Gateway $2/M

DevPass (LLM Gateway) $2/M

Alibaba $2/M

Vercel AI Gateway $2/M

Ofox $2/M

Merge Gateway $2/M

Eden AI $2/M

Requesty $2/M

LLM Gateway $2/M

NanoGPT $2/M

302.AI $2.16/M

Cost calculator

Estimate a workload

Provider Input tokens 1,000,000 Output tokens 250,000 Cached input 0%

$0.00

Excludes taxes, non-token charges, and tiered discounts.

Context limits also differ by provider, from 256K to 1.04858M tokens. Compare the provider table above before choosing on price alone.

Specification

Capabilities

Recorded from the source catalog and provider listings.

× Reasoning No

✓ Tool calling Yes

✓ Structured output Yes

✓ Attachments Yes

✓ Vision input Yes

× Open weights No

Creator: Alibaba Qwen
Model family: qwen
Knowledge cutoff: Not documented
License: Not documented
Release date: 2026-08-03
Model ID: alibaba/qwen3.8-max

Published evaluations

Benchmarks

Every result stays attached to its source, version, metric and harness. Scores from different versions are never merged, and the profile below plots each benchmark against its own population rather than on a shared scale.

Benchmark registry

No published benchmark results

ModelBench does not infer quality from price, context size, or model name. When a source publishes a comparable result, it appears here with its version and link.

Read the methodology

Catalog activity

Change log

Field-level changes detected between successful source imports.

Full change log

Aug 04, 2026Price Completion4.951 → 6.0

Aug 04, 2026Price Prompt1.65 → 2.0

Aug 03, 2026Price Completion6.0 → 4.951

Aug 03, 2026Price Prompt2.0 → 1.65

Provenance

Sources & verification

Every figure on this page traces back to one of these records.

Methodology

Last verified: Sep 11, 2026
Status: Source-linked
Confidence: Medium
Catalog source: Models.dev

Public API

Use this record

Fetch the complete source-linked model record. No key, no account, no rate-limited tier.

API documentation

Endpoint

GET https://model.kyssta.lol/api/v1/models/alibaba/qwen3.8-max

curl

curl "https://model.kyssta.lol/api/v1/models/alibaba/qwen3.8-max"

Common questions

Frequently asked questions

Answered directly from the stored record — nothing here is generated beyond the catalog's own fields.

What is Qwen3.8 Max?

2.4-trillion-parameter MoE flagship for coding, professional work, multimodal understanding, and long-horizon agentic workflows. It is published by Alibaba Qwen and catalogued here from Models.dev.

How much does Qwen3.8 Max cost?

Listed input pricing starts at $1.6 per million tokens from Vancine, rising to $2.16 across 25 listed providers.

What is the context length of Qwen3.8 Max?

Qwen3.8 Max accepts up to 1M tokens of context and returns up to 131.072K output tokens.

Does Qwen3.8 Max support tool calling and structured output?

Provider catalogs list support for tool calling, structured output, and image input.

Which providers serve Qwen3.8 Max?

28 providers list this model: Kenari, SCNet Token Plan, Alibaba Token Plan, Alibaba Token Plan (China), Vancine, Deep Infra and 22 more.

Are the weights for Qwen3.8 Max open?

No. This model is served through hosted APIs only.

When was Qwen3.8 Max released?

The catalog records a release date of 2026-08-03, last verified Sep 11, 2026.