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: 8,192.
Input / output on that row: $0.12 / $0.46 per 1M tokens.
Architecture fields: text->text · Qwen3 · qwen3.
Hugging Face id on that row: Qwen/Qwen3-8B.
Qwen3-8B is a dense 8.2B parameter causal language model from the Qwen3 series, designed for both reasoning-heavy tasks and efficient dialogue.
When you want the 2025-04-28 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/Qwen3-8B. 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-00005.safetensors | 3,996,250,744 |
model-00002-of-00005.safetensors | 3,993,160,032 |
model-00003-of-00005.safetensors | 3,959,604,768 |
model-00004-of-00005.safetensors | 3,187,841,392 |
model-00005-of-00005.safetensors | 1,244,659,840 |
tokenizer.json | 11,422,654 |
vocab.json | 2,776,833 |
merges.txt | 1,671,853 |
model.safetensors.index.json | 32,878 |
README.md | 16,660 |
LICENSE | 11,343 |
tokenizer_config.json | 9,732 |
.gitattributes | 1,570 |
config.json | 728 |
generation_config.json | 239 |
All 15 files the tree API returned are listed: every one of the 5 safetensor shards plus 10 other files. Files tab: https://huggingface.co/Qwen/Qwen3-8B/tree/main.
OpenRouter slug qwen/qwen3-8b 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: $0.12 in / $0.46 out per 1M tokens. Context 131,072 in / 8,192 out.
No separate internal-reasoning price on that row.
| Claim | Source | As of |
|---|---|---|
| OpenRouter id qwen/qwen3-8b; context 131072; created 1745876632; $0.12 / $0.46 per 1M | OpenRouter /api/v1/models | 2026-08-19 |
| OpenRouter id qwen/qwen3-8b, context 131,072 | OpenRouter /api/v1/models | 2026-08-19 |
| HF downloads 15,796,910 | Hugging Face API Qwen/Qwen3-8B | 2026-08-19 |
| HF safetensors.total: 8,190,735,360 stored tensors; HF API usedStorage 45,450,222,438 bytes; created 2025-04-27T03:42:21.000Z; HF tensors BF16 | Hugging Face API Qwen/Qwen3-8B | 2026-08-19 |
| 5 safetensor shards; shard bytes 16,381,516,776; tree files 15 | Hugging Face tree API Qwen/Qwen3-8B | 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 Qwen3.8 27B.
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/qwen3-8b.