Qwen3.8 Max 0902
Qwen3.8 Max 0902 is an updated snapshot of Qwen3.8 Max from Alibaba's Qwen team. It is a 2.4-trillion-parameter mixture-of-experts model that accepts text, image, and video input and returns text, with a 1M-token context window and reasoning enabled by default.
This snapshot is post-trained for coding and agentic work, including multi-step software projects, multi-tool orchestration, and long-horizon task execution. It also targets chart reasoning, document parsing, and multimodal understanding over long documents and extended video. Tool calling, structured outputs, and configurable reasoning effort are supported.
- Organization
- Alibaba
- Family
- qwen
- Providers
- 6
- Context
- 1,000,000
- Output limit
- 131,072
- Knowledge
- —
- Release
- 2026-09-02
- Updated
- 2026-09-02
- Weights
- Closed
- Input
- text, image, video, pdf
- Output
- text
- Capabilities
- Tools, Reasoning, Temperature
Providers
Compare every cataloged offer for this model, including its provider, route, token limits, price, and capabilities.
| Provider | Model ID | Context | Output | Input / output · 1M | Reasoning | Tools | Structured | Details |
|---|---|---|---|---|---|---|---|---|
| Eden AI | qwen/qwen3.8-max-0902 | 1,000,000 | 131,072 | $2.00 / $6.00 | Yes | Yes | Yes | View |
| Kilo Gateway | qwen/qwen3.8-max-0902 | 1,000,000 | 131,072 | $2.00 / $6.00 | Yes | Yes | Yes | View |
| NanoGPT | qwen/qwen3.8-max-0902 | 991,808 | 131,072 | $2.00 / $6.00 | Yes | Yes | Yes | View |
| Ofox | bailian/qwen3.8-max-0902 | 1,000,000 | 131,072 | $2.00 / $6.00 | Yes | Yes | — | View |
| Ofox | qwen/qwen3.8-max-0902 | 1,000,000 | 131,072 | $1.71 / $5.14 | Yes | Yes | — | View |
| Alibabavia OpenRouter | qwen/qwen3.8-max-0902 unknown | 1,000,000 | 131,072 | $2.00 / $6.00 | Yes | Yes | Yes | View |
| Vercel AI Gateway | alibaba/qwen3.8-max-0902 | 991,000 | 128,000 | $2.00 / $6.00 | Yes | Yes | — | View |
Prices and limits apply to each offer. A dash means the value is not provided. OpenRouter offers show the hosting provider and routing channel separately.
Pricing
Compare token rates and cache charges across available routes and hosting configurations.
Lowest listed input and output prices across the offers above; they may belong to different providers. These are base rates, before conditional pricing, discounts or additional fees.
qwen/qwen3.8-max-0902Observed - Input
- $2.00
- Output
- $6.00
- Cache read
- $0.25
- Cache write
- $2.50
Hosting prices through OpenRouter All endpoints and cache rates
| Endpoint | Input / 1M | Output / 1M | Cache read / 1M | Cache write / 1M |
|---|---|---|---|---|
| Alibabaalibaba | $2.00 | $6.00 | $0.25 | $2.50 |
Each row is a hosting configuration. Open an offer in Providers for its full pricing conditions and additional fees. Endpoint observations may differ from the routing catalog's base price.
Performance
Review reported latency and output-throughput percentiles from the latest observed rolling window.
Time to first token · milliseconds
All latency percentiles 1 endpoints
| Endpoint | P50 | P75 | P90 | P99 |
|---|---|---|---|---|
| Alibabaalibaba | 4,140.5 ms | 7,018.25 ms | 11,542.8 ms | 49,607.83 ms |
Output throughput · tokens per second
All throughput percentiles 1 endpoints
| Endpoint | P50 | P75 | P90 | P99 |
|---|---|---|---|---|
| Alibabaalibaba | 34 t/s | 41 t/s | 47 t/s | 58 t/s |
Percentiles describe the observed request distribution. These are snapshots of a rolling window, not a historical time series.
Uptime
Compare successful request rates across the latest 5-minute, 30-minute, and 24-hour observations.
Reported by OpenRouter at the time of collection; rate-limited requests are excluded. A dash means no measurement was reported. This is not a live availability check.
Benchmarks
Review attributed evaluation results on each source's original scale.
qwen/qwen3.8-max-0902Observed Sources: Artificial Analysis and Design Arena, via OpenRouter. Scores retain their original scales and are not OpenAI Suite ratings.
Detailed evaluations
| Evaluation | Configuration | Source | Results | Details |
|---|---|---|---|---|
| Composite indices | Qwen3.8 Max (0902)qwen/qwen3.8-max-20260902 | Artificial Analysis | Intelligence 45.4 · Coding 76.2 · Agentic 56 | Details |
Sources: Artificial Analysis, Design Arena and OpenRouter. Evaluation configurations and scales differ; results are not interchangeable. Updated Oct 4, 2026.
Apps & session costs
Compare observed median session costs for applications using this model, grouped by conversation length.
| Application | Model route | Turns | Median cost / session | Details |
|---|---|---|---|---|
| Hermes Agent | qwen/qwen3.8-max-20260902 | 50+ turns | $3.334543 | Details |
| Claude Code | qwen/qwen3.8-max-20260902 | 50+ turns | $6.066278 | Details |
| Hermes Agent | qwen/qwen3.8-max-20260902 | 10–49 turns | $0.466432 | Details |
| Hermes Agent | qwen/qwen3.8-max-20260902 | 1 turn | $0.003517 | Details |
| Claude Code | qwen/qwen3.8-max-20260902 | 10–49 turns | $1.070254 | Details |
| Claude Code | qwen/qwen3.8-max-20260902 | 2–9 turns | $0.135476 | Details |
| Hermes Agent | qwen/qwen3.8-max-20260902 | 2–9 turns | $0.063501 | Details |
Source: OpenRouter, as of Oct 2, 2026. Published under CC BY 4.0. These are observed costs per session, not token prices or a forecast for your workload. Apps are compared separately.
Activity
Daily prompt and completion tokens reported for this model's routes in OpenRouter's top 50. Missing days have no published value.
35,677,808,866 tokens
38,503,040,408 tokens
70,379,635,917 tokens
62,584,798,180 tokens
68,375,093,409 tokens
81,231,424,490 tokens
63,710,750,329 tokens
37,687,003,568 tokens
47,041,645,762 tokens
41,590,160,868 tokens
53,192,607,163 tokens
53,556,546,361 tokens
88,309,969,500 tokens
65,294,508,696 tokens
37,682,735,307 tokens
61,349,292,337 tokens
46,677,448,668 tokens
Daily observations · 17 days
| Date (UTC) | Reported tokens | Reported routes |
|---|---|---|
| Oct 3, 2026 | 46,677,448,668 | 1 |
| Sep 22, 2026 | 61,349,292,337 | 1 |
| Sep 20, 2026 | 37,682,735,307 | 1 |
| Sep 19, 2026 | 65,294,508,696 | 1 |
| Sep 18, 2026 | 88,309,969,500 | 1 |
| Sep 17, 2026 | 53,556,546,361 | 1 |
| Sep 16, 2026 | 53,192,607,163 | 1 |
| Sep 15, 2026 | 41,590,160,868 | 1 |
| Sep 14, 2026 | 47,041,645,762 | 1 |
| Sep 13, 2026 | 37,687,003,568 | 1 |
| Sep 12, 2026 | 63,710,750,329 | 1 |
| Sep 10, 2026 | 81,231,424,490 | 1 |
| Sep 9, 2026 | 68,375,093,409 | 1 |
| Sep 8, 2026 | 62,584,798,180 | 1 |
| Sep 7, 2026 | 70,379,635,917 | 1 |
| Sep 6, 2026 | 38,503,040,408 | 1 |
| Sep 5, 2026 | 35,677,808,866 | 1 |
Source: OpenRouter (openrouter.ai/rankings), as of Oct 4, 2026. CC BY 4.0. Totals include only individually published routes. Tokenizers differ by provider; the aggregated “other” category is never assigned to a model.
Technical details & API
Explore specifications, supported parameters, reasoning controls, and API identifiers for each OpenRouter route.
qwen/qwen3.8-max-0902Observed - Context
- 1,000,000
- Maximum output
- 131,072
- Tokenizer
- Qwen
- Input
- text, image, video
- Output
- text
- Moderation
- No
- Added to OpenRouter
- 2026-09-03
https://openrouter.ai/api/v1qwen/qwen3.8-max-0902qwen/qwen3.8-max-20260902Reasoning
- Required
- Yes
- Enabled by default
- Yes
- Default effort
- xhigh
- Supported efforts
- xhigh, high, medium, low, minimal
Supported parameters
frequency_penaltyinclude_reasoninglogprobsmax_tokenspresence_penaltyreasoningreasoning_effortresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p
Frequently asked questions
Answers based on the model metadata and serving offers currently in the catalog.
How much does Qwen3.8 Max 0902 cost?
Listed rates start at $1.71 per million input tokens and $5.14 per million output tokens. Prices vary by provider and configuration; see Pricing for details.
Which providers offer Qwen3.8 Max 0902?
There are 7 cataloged offers across 6 providers. Compare model IDs, prices and limits in Providers.
What is the context window?
The cataloged model context is 1,000,000 tokens. Each serving endpoint may apply a different limit.
Does it support tools and structured output?
Tool calling: Yes. Structured output: Not reported. Support can vary by endpoint.
Catalog history · 2 recorded revisions
Metadata observations since this model was first cataloged. These are not model release versions.
- ·
d80589c75d21 - ·
2ae995e64bef