DeepSWE
No official DeepSWE mini-swe-agent row for this identity on the public board we fetched.
Context window on the 2026-08-19 OpenRouter row: 131,072 tokens.
Max completion tokens on that row: 32,768.
Input / output on that row: $0.40 / $4.00 per 1M tokens.
Architecture fields: text+image->text · Qwen3.
Hugging Face id on that row: Qwen/Qwen3-VL-235B-A22B-Thinking.
Qwen3-VL-235B-A22B Thinking is a multimodal model that unifies strong text generation with visual understanding across images and video.
When you want the 2025-09-23 catalog SKU, not a later rename.
No independent board lists this exact SKU as of 2026-08-19.
Closest benchmarked sibling: Qwen3.8 Max, 57% ±3% Pass@1 at xhigh on the DeepSWE official board. That is a score for the sibling, not for this SKU.
Boards checked: DeepSWE official (2026-08-13), Artificial Analysis Intelligence Index, vals.ai hero index. Every card that does carry a row is on the coding leaderboard.
No official DeepSWE mini-swe-agent row for this identity on the public board we fetched.
No Intelligence Index integer fetched for this identity. Chip omitted.
We did not open a vals.ai card for this identity. Chip omitted.
Plus is $25/mo with $25 weekly hosted usage. The Mac app stays free with your own keys. Get Plus is not Download for Mac.
Official weights id on the 2026-08-19 OpenRouter row: Qwen/Qwen3-VL-235B-A22B-Thinking. Community GGUF is a quant, not a second Continuum card.
This is the model repo, not Download for Mac. Downloads and likes from the Hugging Face API on 2026-08-19.
usedStorage and the sum of .safetensors sizes can differ (LFS pointers, non-shard files, duplicate copies). Cited separately. Source: recursive tree API, 2026-08-19.
| Path | Bytes |
|---|---|
model-00001-of-00096.safetensors | 2,541,132,904 |
model-00002-of-00096.safetensors | 4,975,511,472 |
model-00003-of-00096.safetensors | 4,975,511,472 |
model-00004-of-00096.safetensors | 4,975,511,472 |
model-00005-of-00096.safetensors | 4,975,511,472 |
model-00006-of-00096.safetensors | 4,975,511,472 |
model-00007-of-00096.safetensors | 4,975,511,472 |
model-00008-of-00096.safetensors | 4,975,511,472 |
model-00009-of-00096.safetensors | 4,975,511,472 |
model-00010-of-00096.safetensors | 4,975,511,472 |
model-00011-of-00096.safetensors | 4,975,511,456 |
model-00012-of-00096.safetensors | 4,975,511,480 |
model-00013-of-00096.safetensors | 4,975,511,480 |
model-00014-of-00096.safetensors | 4,975,511,480 |
model-00015-of-00096.safetensors | 4,975,511,480 |
model-00016-of-00096.safetensors | 4,975,511,480 |
model-00017-of-00096.safetensors | 4,975,511,480 |
model-00018-of-00096.safetensors | 4,975,511,480 |
model-00019-of-00096.safetensors | 4,975,511,480 |
model-00020-of-00096.safetensors | 4,975,511,480 |
model-00021-of-00096.safetensors | 4,975,511,480 |
model-00022-of-00096.safetensors | 4,975,511,480 |
model-00023-of-00096.safetensors | 4,975,511,480 |
model-00024-of-00096.safetensors | 4,975,511,480 |
model-00025-of-00096.safetensors | 4,975,511,480 |
model-00026-of-00096.safetensors | 4,975,511,480 |
model-00027-of-00096.safetensors | 4,975,511,480 |
model-00028-of-00096.safetensors | 4,975,511,480 |
model-00029-of-00096.safetensors | 4,975,511,480 |
model-00030-of-00096.safetensors | 4,975,511,480 |
model-00031-of-00096.safetensors | 4,975,511,480 |
model-00032-of-00096.safetensors | 4,975,511,480 |
model-00033-of-00096.safetensors | 4,975,511,480 |
model-00034-of-00096.safetensors | 4,975,511,480 |
model-00035-of-00096.safetensors | 4,975,511,480 |
model-00036-of-00096.safetensors | 4,975,511,480 |
model-00037-of-00096.safetensors | 4,975,511,480 |
model-00038-of-00096.safetensors | 4,975,511,480 |
model-00039-of-00096.safetensors | 4,975,511,480 |
model-00040-of-00096.safetensors | 4,975,511,480 |
model-00041-of-00096.safetensors | 4,975,511,480 |
model-00042-of-00096.safetensors | 4,975,511,480 |
model-00043-of-00096.safetensors | 4,975,511,480 |
model-00044-of-00096.safetensors | 4,975,511,480 |
model-00045-of-00096.safetensors | 4,975,511,480 |
model-00046-of-00096.safetensors | 4,975,511,480 |
model-00047-of-00096.safetensors | 4,975,511,480 |
model-00048-of-00096.safetensors | 4,975,511,480 |
model-00049-of-00096.safetensors | 4,975,511,480 |
model-00050-of-00096.safetensors | 4,975,511,480 |
model-00051-of-00096.safetensors | 4,975,511,480 |
model-00052-of-00096.safetensors | 4,975,511,480 |
model-00053-of-00096.safetensors | 4,975,511,480 |
model-00054-of-00096.safetensors | 4,975,511,480 |
model-00055-of-00096.safetensors | 4,975,511,480 |
model-00056-of-00096.safetensors | 4,975,511,480 |
model-00057-of-00096.safetensors | 4,975,511,480 |
model-00058-of-00096.safetensors | 4,975,511,480 |
model-00059-of-00096.safetensors | 4,975,511,480 |
model-00060-of-00096.safetensors | 4,975,511,480 |
model-00061-of-00096.safetensors | 4,975,511,480 |
model-00062-of-00096.safetensors | 4,975,511,480 |
model-00063-of-00096.safetensors | 4,975,511,480 |
model-00064-of-00096.safetensors | 4,975,511,480 |
tokenizer.json | 7,032,403 |
vocab.json | 2,776,833 |
merges.txt | 1,671,839 |
model.safetensors.index.json | 130,278 |
tokenizer_config.json | 10,781 |
README.md | 6,697 |
chat_template.json | 5,410 |
config.json | 1,663 |
.gitattributes | 1,519 |
preprocessor_config.json | 390 |
video_preprocessor_config.json | 385 |
generation_config.json | 270 |
Showing the first 64 of 96 safetensor shards, plus 12 other files. The snapshot was capped at 64 shards when the tree API was read on 2026-08-19, so the remaining 32 are on the Files tab, not on this page. Totals above are the full tree API sum, not this slice. Byte sizes are Hub tree API size fields, never invented.
OpenRouter slug qwen/qwen3-vl-235b-a22b-thinking on the 2026-08-19 catalog.
First party: https://qwen.ai/.
Not on the Continuum host list fetched 2026-08-19.
We list first-party and OpenRouter, plus Continuum only when the live public allowlist named the id. This is not a 15-host routing table.
OpenRouter 2026-08-19: $0.40 in / $4.00 out per 1M tokens. Context 131,072 in / 32,768 out.
No separate internal-reasoning price on that row.
| Claim | Source | As of |
|---|---|---|
| OpenRouter id qwen/qwen3-vl-235b-a22b-thinking; context 131072; created 1758668690; $0.40 / $4.00 per 1M | OpenRouter /api/v1/models | 2026-08-19 |
| OpenRouter id qwen/qwen3-vl-235b-a22b-thinking, context 131,072 | OpenRouter /api/v1/models | 2026-08-19 |
| HF downloads 11,490 | Hugging Face API Qwen/Qwen3-VL-235B-A22B-Thinking | 2026-08-19 |
| HF safetensors.total: 235,670,022,896 stored tensors; HF API usedStorage 471,340,223,736 bytes; created 2025-09-22T03:54:48.000Z; HF tensors BF16 | Hugging Face API Qwen/Qwen3-VL-235B-A22B-Thinking | 2026-08-19 |
| 96 safetensor shards; shard bytes 471,340,223,736; tree files 108 | Hugging Face tree API Qwen/Qwen3-VL-235B-A22B-Thinking | 2026-08-19 |
No other card in this cluster shares a published DeepSWE official row we can put next to this one. We will not compare on vendor-blog numbers.
Continue through Qwen's model family with Qwen3 VL 235B A22B Instruct.
Lab posts pick a harness, an effort, a split, and sometimes a private eval set. DeepSWE publishes the official mini-swe-agent row with cost, tokens, and steps. Scale SWE-bench Pro only counts when the public shared-harness board has a row we can fetch. A higher lab number is usually a different test, not a better one.
No Continuum hosted id is verified for this model, so this page does not invent a curl target. Use the first-party API or the OpenRouter slug qwen/qwen3-vl-235b-a22b-thinking.