Qwen3 VL 235B A22B Instruct
Qwen3-VL-235B-A22B Instruct is an open-weight multimodal model that unifies strong text generation with visual understanding across images and video. $0.20 per million input tokens, $0.88 per million output tokens. 262,144 token context window, maximum output of 16,384 tokens. Higher uptime with 5 providers. Includes independent benchmarks from Artificial Analysis.
- Input / output price
- $0.20 / $0.88 per 1M
- Context
- 262K tokens
- Released
- Sep 23, 2025
Paste into Claude Code, Cursor, or Codex
Help me set up the Respan gateway: fetch and follow https:/
Providers
4 providers, cheapest first, OpenRouter last, priced per 1M tokens after gateway discounts.
| Provider | Input | Output |
|---|---|---|
Concentrate concentrate/qwen3-vl-235b-a22b | $0.20/M | $0.88/M |
DeepInfra deepinfra/qwen3-vl-235b-a22b-instruct | $0.20/M | $0.88/M |
Parasail parasail/qwen3-vl-235b-a22b-instruct | $0.21/M | $1.90/M |
OpenRouter openrouter/qwen3-vl-235b-a22b-instruct | $0.21/M | $1.90/M |
Is a provider down? OpenRouter status
Pricing
Averaged across 4 providers, in USD per 1M tokens after gateway discounts.
- Average input
- $0.20 per 1M
- Average output
- $1.39 per 1M
- Average cache read
- $0.11 per 1M
Cost by volume
Total cost from 0 to 1T tokens on the cheapest and most expensive provider.
Throughput and latency
30-day averages from requests through the Respan gateway. Under each figure, every model on the gateway by its average, this one in blue.
Output speed
Higher is better7.9tokens/sacross providers
Response latency
Lower is better3.6sacross providers
Benchmarks
17 published scores from 2 sources, each linked to where it was published.
Published scores
| Benchmark | Score | Source | Published |
|---|---|---|---|
| BFCL-v3huggingface.co | 67.7% | huggingface.co | Sep 23, 2025 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| SuperGPQAhuggingface.co | 60.4% | huggingface.co | Sep 23, 2025 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| AIME25huggingface.co | 74.7% | huggingface.co | Sep 23, 2025 |
| HMMT25huggingface.co | 57.4% | huggingface.co | Sep 23, 2025 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| MMLU-Reduxhuggingface.co | 92.2% | huggingface.co | Sep 23, 2025 |
| IFEvalhuggingface.co | 87.8% | huggingface.co | Sep 23, 2025 |
| MMLU-Prohuggingface.co | 81.8% | huggingface.co | Sep 23, 2025 |
| SimpleQAhuggingface.co | 51.9% | huggingface.co | Sep 23, 2025 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| MathVista (mini)huggingface.co | 84.9% | huggingface.co | Sep 23, 2025 |
| VideoMME (w/o sub)huggingface.co | 79.2% | huggingface.co | Sep 23, 2025 |
| MMMU (val)huggingface.co | 78.7% | huggingface.co | Sep 23, 2025 |
| MMMU_Prohuggingface.co | 68.1% | huggingface.co | Sep 23, 2025 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| Arena-Hard v2huggingface.co | 77.4% | huggingface.co | Sep 23, 2025 |
| LMArena EloLMArena | 1413 Elo · #113 of 191 | LMArena | Nov 19, 2026 |
| LMArena VisionLMArena | 1214 Elo · #65 of 91 | LMArena | Nov 19, 2026 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| ScreenSpot Prohuggingface.co | 62% | huggingface.co | Sep 23, 2025 |
| LCBV6 (25.02-25.05)huggingface.co | 54.3% | huggingface.co | Sep 23, 2025 |
Apps
Use Qwen3 VL 235B A22B Instruct in the tools you already run. Each guide points the app at the Respan gateway.
Setup guides for more apps are in the integration docs.
Qwen3 VL 235B A22B Instruct FAQ
Short answers, built from the data on this page.
Qwen3 VL 235B A22B Instruct is a model from Qwen, released on Sep 23, 2025. Qwen3-VL-235B-A22B Instruct is an open-weight multimodal model that unifies strong text generation with visual understanding across images and video. $0.20 per million input tokens, $0.88 per million output tokens. 262,144 token context window, maximum output of 16,384 tokens. Higher uptime with 5 providers. Includes independent benchmarks from Artificial Analysis.
On the Respan gateway, Qwen3 VL 235B A22B Instruct costs from $0.20 per 1M input tokens and $0.88 per 1M output tokens on Concentrate and DeepInfra, after gateway discounts. Averaged across its 4 providers, it costs $0.20 per 1M input tokens and $1.39 per 1M output tokens.
Qwen3 VL 235B A22B Instruct is available through 4 providers: Concentrate, DeepInfra, Parasail, and OpenRouter.
Qwen3 VL 235B A22B Instruct accepts up to 262K tokens of context on its largest provider route.
Point any OpenAI-compatible SDK at https://gateway.respan.ai/v1 with your Respan API key and set the model to "qwen3-vl-235b-a22b-instruct". To set it up with a coding agent, copy the agent setup prompt at the top of this page.
Qwen3 VL 235B A22B Instruct has 17 published benchmark scores, including BFCL-v3 67.7%, SuperGPQA 60.4%, and AIME25 74.7%. Each score links to where it was published; the data is collected by Respan.
Certified where it counts.
Built to meet the security and privacy standards that enterprise and healthcare teams require.
ISO 27001
The internationally recognized standard for information security management.
SOC 2
Secure, compliant management of your data across all of our systems.
GDPR
Operated under GDPR, the world's strictest standard for data privacy.
HIPAA
HIPAA compliant, with a BAA available for healthcare teams.