Qwen3.8 Max
Qwen3.8 Max is a reasoning model from Qwen released on Jul 19, 2026. It reads text, images, files and video and writes text, with a 1M token context window and up to 131K tokens per reply.
Show moreShow less
It costs $2 per million input tokens and $6 per million output tokens. Cached input bills at $0.25, 88% less than fresh input.
It supports tool calling, structured JSON output and prompt caching.
30 providers serve it, including Deep Infra, Fireworks AI and Novita AI. The lowest input price is $1.54 per million tokens at DevPass (LLM Gateway).
On the Artificial Analysis Intelligence Index it scores 45.4, which places it in the top ten, at number 9, among the 43 models I track with independent scores.
- Modalities
- In / out price
- $2 / $6 per 1M
- Context
- 1M
- Max output
- 131K
- Released
- Jul 19, 2026
- Knowledge cutoff
- n/a
- Tool calling
- Structured output
- Reasoning
- Prompt caching
- Open weights
- Free to use
Qwen3.8 Max pricing
USD, as listed on Oct 15, 2026. Most bills are input heavy, so the cached input rate matters as much as the headline price.
| Input | $2 / 1M tokens | |
|---|---|---|
| Output | $6 / 1M tokens | |
| Cached input (read) | $0.25 / 1M tokens | 88% off input |
| Cache write | $2.50 / 1M tokens |
Qwen3.8 Max providers
30 providers serve it, including Deep Infra, Fireworks AI and Novita AI. The lowest input price is $1.54 per million tokens at DevPass (LLM Gateway). Each host sets its own price and limits, so the cheapest one is not always the one with the longest context.
| Provider | Input /M | Output /M | Cache read /M | Context | Max output |
|---|---|---|---|---|---|
| Alibaba First party | $2 | $6 | $0.25 | 1M | 131K |
| Deep Infra | $1.65 | $4.95 | $0.206 | 256K | 131K |
| Fireworks AI | $2 | $6 | $0.25 | 262K | 131K |
| Novita AI | $2 | $6 | $0.25 | 1M | 131K |
| Vercel AI Gateway | $2 | $6 | $0.25 | 262K | 128K |
| DevPass (LLM Gateway) | $1.54 | $4.63 | $0.198 | 1M | 1M |
| LLM Gateway | $1.54 | $4.63 | $0.198 | 1M | 131K |
| Vancine | $1.60 | $4.80 | $0.20 | 1M | 131K |
| AIHubMix | $1.69 | $5.07 | $0.169 | 991K | 128K |
| Alibaba (China) | $1.78 | $5.33 | $0.2222 | 1M | 131K |
| SCX.ai | $1.81 | $5.45 | $0.17 | 1M | 131K |
| CrossModel | $1.88 | $5.63 | $0.23 | 1M | 131K |
Showing 12 of 30 providers: the lab first, then the major clouds, then the cheapest resellers.
What Qwen3.8 Max costs per month
Pick a workload close to yours or type your own volumes.
Independent benchmarks
Measured by third parties, not reported by Qwen. Each links to its source and shows the date I checked it.
A composite of 10 independent evaluations (agents 30%, coding 20%, scientific reasoning 20%, general 30%), run by Artificial Analysis on each model, version 4.3.2.
Artificial Analysis, checked Oct 10, 2026
Human preference: people compare two anonymous answers and pick the better one. Ratings from the Text Arena overall board, style control on.
Arena (formerly LMArena), checked Oct 10, 2026
Agentic coding in a real terminal: can the model, driving an agent harness, finish multi step software and ops tasks. Resolution rate.
Terminal-Bench, checked Oct 10, 2026
Median output tokens per second measured by Artificial Analysis on the provider API, for the same model setting as its index score.
Artificial Analysis, checked Oct 10, 2026
Benchmarks Qwen reports (9)
- terminal-bench-2.1 (Terminal Bench 2.1, Claude Code harness, avg@10, 5-hour timeout, max_tokens 131,072)86.6%
- swe-bench-pro (SWE-bench Pro, Claude Code harness, temp 1.0, top_p 0.95, 256K context, on a refined benchmark ("Problematic tasks corrected and all baselines evaluated on the refined benchmark"))67.7%
- deepswe-v1.1 (DeepSWE 1.1, best of Claude Code and mini-SWE-agent harnesses, 256K context)56.6%
- gpqa-diamond (GPQA Diamond)92.6%
- hle-no-tools (HLE)43.6%
- hle-with-tools (HLE w/ tools)56.2%
- mrcr-v2 (MRCR v2 256K (8-needle))92.9%
- toolathlon-verified (Toolathlon Verified (Pass@1))72.5%
- ifbench (IFBench)82.8%
Labs pick their own settings and harnesses, so compare these only within one lab.
Supported request parameters
What you can set when you call Qwen3.8 Max through an OpenAI compatible API.
- Tools
tools - Structured outputs
structured_outputs - Reasoning
reasoning - Temperature
temperature
Alternatives to Qwen3.8 Max
Models that take the same inputs and call tools, closest in price, cheaper ones first.
- Index 48.1
Reads text, images, files, audio and video. Tool calling, structured output, reasoning. Served by 12 providers.
by metaSep 2, 20261.05M context$1.25/M input tokens$4.25/M output tokens12 providers
- 1.05M context
Reads text, images, files, audio and video. Tool calling, structured output, reasoning. Served by 14 providers.
by metaAug 5, 2026$1.25/M input tokens$4.25/M output tokens14 providers
- Index 40.9
Reads text, images, files, audio and video. Tool calling, structured output, reasoning. Served by 24 providers.
by googleSep 2, 20261.05M context$0.75/M input tokens$3.75/M output tokens24 providers
- 1.05M context
Reads text, images, files, audio and video. Tool calling, structured output, reasoning. Served by 25 providers.
by googleJul 9, 2026$0.75/M input tokens$3.75/M output tokens25 providers
- 1.05M context
Reads text, images, files, audio and video. Tool calling, structured output, reasoning. Served by 30 providers.
by googleFeb 5, 2025$1.25/M input tokens$10/M output tokens30 providers
- 1.05M context
Reads text, images, files and video. Tool calling, structured output, reasoning. Served by 14 providers.
by metaApr 8, 2026$1.25/M input tokens$4.25/M output tokens14 providers
More from Qwen
- 262K context
Reads text and images. Tool calling, reasoning.
by qwenOct 5, 2026$0.10/M input tokens$0.60/M output tokens
- 262K context
Reads text and images. Tool calling, reasoning.
by qwenOct 5, 2026$0.10/M input tokens$0.60/M output tokens
- 262K context
Reads text and images. Tool calling, reasoning.
by qwenOct 5, 2026$0.10/M input tokens$0.60/M output tokens
- 262K context
Reads text and images. Tool calling, reasoning.
by qwenOct 5, 2026$0.10/M input tokens$0.60/M output tokens
- 262K context
Reads text and images. Tool calling, reasoning.
by qwenOct 5, 2026$0.10/M input tokens$0.60/M output tokens
- 262K context
Reads text and images. Tool calling, reasoning.
by qwenOct 5, 2026$0.10/M input tokens$0.60/M output tokens
Qwen3.8 Max questions
How much does the Qwen3.8 Max API cost?
$2 per million input tokens and $6 per million output tokens, with cached input at $0.25. The estimator on this page turns that into a monthly bill for your own workload.
What is the context window of Qwen3.8 Max?
1,000,000 tokens of input, and it can write up to 131,072 tokens in one reply. As a rough guide, a million tokens is around 750,000 English words.
Which providers serve Qwen3.8 Max?
30 providers serve it, including Deep Infra, Fireworks AI and Novita AI. The lowest input price is $1.54 per million tokens at DevPass (LLM Gateway). Prices differ by host, so the Providers table on this page lists each one with its input and output price.
Does Qwen3.8 Max support tool calling?
Yes. It accepts tool definitions and can return JSON that matches a schema, which is what an agent needs to call your APIs.
Is Qwen3.8 Max open source?
No. Qwen serves it through an API only, so you cannot download the weights or host it yourself.
When was Qwen3.8 Max released?
Jul 19, 2026.
How good is Qwen3.8 Max compared with other models?
It scores 45.4 on the Artificial Analysis Intelligence Index and 1483 on the Arena text leaderboard. Benchmarks are a shortlist, not a verdict: test the top two or three candidates on your own tasks before you commit.
Catalog data from models.dev (MIT licensed), refreshed daily, last on Oct 15, 2026. Independent scores from my hand checked rankings, sources linked above. The summary is written from these facts.
Building on Qwen3.8 Max?
I test your real tasks on it and the two closest alternatives, then ship the agent on whichever wins on cost and accuracy.
Book Meeting