Qwen·qwen/qwen3-vl-235b-a22b-instruct
Qwen3 VL 235B A22B Instruct is ModelCap current-board rank #70 with Index 58.9 (Measured), from the ModelCap Index as of 22 Sept 2026, 02:49 UTC.
Qwen3 VL 235B A22B Instruct listed OpenRouter input price is $0.21 per 1M tokens and listed output price is $1.90 per 1M tokens, from OpenRouter listed prices as of 22 Sept 2026, 02:49 UTC.
Qwen3 VL 235B A22B Instruct has a published context limit of 262K tokens in the ModelCap catalogue as of 22 Sept 2026, 02:49 UTC.
Qwen3 VL 235B A22B Instruct has 5 published OpenRouter serving endpoints, from OpenRouter as of 22 Sept 2026, 02:49 UTC.
Qwen3 VL 235B A22B Instruct weight access is open weights, from ModelCap classification of published repository metadata as of 22 Sept 2026, 02:49 UTC.
Snapshot facts · download the public dataset · methodology
Provider economics and telemetry published by the Hugging Face Router. These are operational signals, not benchmark results.
Structured rows reported in this exact model repository at the pinned revision below. They are the publisher talking about itself: never measured evidence, never a score input on their own. They remain quarantined until dataset revision, harness, configuration and identity pass ModelCap’s independent admission review.
BES normalizes admitted public benchmark evidence for measured Index rows. Its legacy score and observables prior do not define the public language rank.
These adoption and deployment observations remain context only. They do not change this model's ModelCap Index score or rank.
The bounded 0–100 capability score blends each source’s competitive placement with its published achievement, then combines capability families. Evidence breadth adds a modest uncertainty adjustment; price and popularity are not part of benchmark-led rank.
Missing: artifactReproducibility.base-lineage, evaluationProvenance.evaluation-dataset-revisions.
A metadata completeness and deployability index—not a safety certification, quality grade, or production-readiness claim.
Market Gravity uses OpenRouter’s full-catalogue popularity order. Sparse Vercel top-ten observations appear only when published and do not affect the score.
OpenRouter weekly popularity across the full model catalogue.
Independent providers versus the model's open or closed cohort, weighted by uptime.
Hugging Face 30-day downloads for open models; neutral for closed models.
Time since first public availability, on a six-month half-life.
Open weights. Downloadable weights are published under an OSI or free-culture license in the current repository metadata. This describes weight availability, not whether the full training stack qualifies as Open Source AI.
Models within 3 places of #70 on the ModelCap Index.
Index score within 3 points of, or above, this model's, with a lower listed blended price (3:1 input:output).
The same publisher's other current models with a public Index position.
Qwen3 VL 235B A22B Instruct holds ModelCap Index position #70 of 248 ranked language models as of 22 September 2026, with an Index score of 58.9 (interval 53.7–64.1); evidence: measured. The Index combines public benchmark boards with published uncertainty; the methodology page explains the weighting.
Qwen3 VL 235B A22B Instruct is listed at $0.21 per 1M input tokens and $1.90 per 1M output tokens as of 22 September 2026; the lowest output price among 5 providers is $0.88 on DeepInfra. Prices come from the OpenRouter catalogue and re-observe on every refresh. For 1,000 requests using 2,000 input and 500 output tokens each, the listed rates imply $1.37 total (2M input + 0.5M output). This excludes caching, batch discounts, prompt-length tiers, tool charges and retries; verify the chosen endpoint's rate and limits before budgeting.
Qwen3 VL 235B A22B Instruct has a published context window of 262K tokens (262,144) and a maximum output of 33K tokens. Individual providers can serve less than the published maximum; the providers table lists each endpoint's own limit.
Open weights (apache-2.0). Downloadable weights are published under an OSI or free-culture license in the current repository metadata. This describes weight availability, not whether the full training stack qualifies as Open Source AI. The repository is Qwen/Qwen3-VL-235B-A22B-Instruct on Hugging Face.
5 providers serve Qwen3 VL 235B A22B Instruct through OpenRouter as of 22 September 2026: DeepInfra, Venice, Parasail, Alibaba and Novita. Each provider's price, context limit, quantization and measured uptime are in the providers table above.
Qwen3 VL 235B A22B Instruct has published results on 3 public boards tracked by ModelCap as of 22 September 2026: Arena coding 1465 (#120 of 397), AA τ²-Bench Telecom 35.1% (#247 of 436) and AA Humanity's Last Exam 6.6% (#356 of 615). Each board page ranks every tracked model on that benchmark; the ModelCap Index combines them with published uncertainty.
Qwen3 VL 235B A22B Instruct ranks #70 (Index 58.9) and Claude Haiku 4.5 ranks #71 (Index 58.7) on the ModelCap Index as of 22 September 2026. The head-to-head page lines up their benchmarks, listed prices, context windows and provider counts side by side.
Qwen3 VL 235B A22B Instruct first appeared in the catalogue on 23 Sept 2025, with a published knowledge cutoff of 2025-03-31. It is the current version in its family. Rank and price movements since then are recorded on the site's changes feed.