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: 131,072.
Input / output on that row: $0.14 / $0.57 per 1M tokens.
Architecture fields: text->text · Other.
Hugging Face id on that row: tencent/Hunyuan-A13B-Instruct.
Hunyuan-A13B is a 13B active parameter Mixture-of-Experts (MoE) language model developed by Tencent, with a total parameter count of 80B and support for reasoning via Chain-of-Thought.
When you want the 2025-07-08 catalog SKU, not a later rename.
No independent board lists this exact SKU as of 2026-08-19.
No other card from this lab carries an independent board row either, so there is no sibling worth pointing at.
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: tencent/Hunyuan-A13B-Instruct. 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-00033.safetensors | 4,985,270,248 |
model-00002-of-00033.safetensors | 4,992,312,432 |
model-00003-of-00033.safetensors | 4,992,312,432 |
model-00004-of-00033.safetensors | 4,992,312,432 |
model-00005-of-00033.safetensors | 4,992,312,432 |
model-00006-of-00033.safetensors | 4,992,312,432 |
model-00007-of-00033.safetensors | 4,992,312,432 |
model-00008-of-00033.safetensors | 4,992,312,432 |
model-00009-of-00033.safetensors | 4,992,312,432 |
model-00010-of-00033.safetensors | 4,992,312,432 |
model-00011-of-00033.safetensors | 4,992,312,600 |
model-00012-of-00033.safetensors | 4,992,312,632 |
model-00013-of-00033.safetensors | 4,992,312,632 |
model-00014-of-00033.safetensors | 4,992,312,632 |
model-00015-of-00033.safetensors | 4,992,312,632 |
model-00016-of-00033.safetensors | 4,992,312,632 |
model-00017-of-00033.safetensors | 4,992,312,632 |
model-00018-of-00033.safetensors | 4,992,312,632 |
model-00019-of-00033.safetensors | 4,992,312,632 |
model-00020-of-00033.safetensors | 4,992,312,632 |
model-00021-of-00033.safetensors | 4,992,312,632 |
model-00022-of-00033.safetensors | 4,992,312,632 |
model-00023-of-00033.safetensors | 4,992,312,632 |
model-00024-of-00033.safetensors | 4,992,312,632 |
model-00025-of-00033.safetensors | 4,992,312,632 |
model-00026-of-00033.safetensors | 4,992,312,632 |
model-00027-of-00033.safetensors | 4,992,312,632 |
model-00028-of-00033.safetensors | 4,992,312,632 |
model-00029-of-00033.safetensors | 4,992,312,632 |
model-00030-of-00033.safetensors | 4,992,312,632 |
model-00031-of-00033.safetensors | 4,992,312,632 |
model-00032-of-00033.safetensors | 4,992,312,632 |
model-00033-of-00033.safetensors | 1,056,994,712 |
tokenizer.json | 16,388,221 |
model.safetensors.index.json | 585,367 |
modeling_hunyuan.py | 78,852 |
hunyuan.py | 37,574 |
README.md | 17,674 |
README_CN.md | 17,628 |
LICENSE | 15,524 |
Notice.txt | 15,354 |
configuration_hunyuan.py | 15,013 |
config.json | 3,376 |
.gitattributes | 1,570 |
tokenizer_config.json | 1,023 |
generation_config.json | 205 |
All 46 files the tree API returned are listed: every one of the 33 safetensor shards plus 13 other files. Files tab: https://huggingface.co/tencent/Hunyuan-A13B-Instruct/tree/main.
OpenRouter slug tencent/hunyuan-a13b-instruct on the 2026-08-19 catalog.
First party: https://hunyuan.tencent.com/.
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: $0.14 in / $0.57 out per 1M tokens. Context 131,072 in / 131,072 out.
No separate internal-reasoning price on that row.
| Claim | Source | As of |
|---|---|---|
| OpenRouter id tencent/hunyuan-a13b-instruct; context 131072; created 1751987664; $0.14 / $0.57 per 1M | OpenRouter /api/v1/models | 2026-08-19 |
| OpenRouter id tencent/hunyuan-a13b-instruct, context 131,072 | OpenRouter /api/v1/models | 2026-08-19 |
| HF downloads 44,345 | Hugging Face API tencent/Hunyuan-A13B-Instruct | 2026-08-19 |
| HF safetensors.total: 80,393,183,232 stored tensors; HF API usedStorage 482,436,254,851 bytes; created 2025-06-25T12:39:52.000Z; HF tensors F32 + BF16 | Hugging Face API tencent/Hunyuan-A13B-Instruct | 2026-08-19 |
| 33 safetensor shards; shard bytes 160,803,954,720; tree files 46 | Hugging Face tree API tencent/Hunyuan-A13B-Instruct | 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 Tencent's model family with Hy3.
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 tencent/hunyuan-a13b-instruct.