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: 32,768 tokens.
Max completion tokens on that row: 16,384.
Input / output on that row: $0.05 / $0.08 per 1M tokens.
Architecture fields: text->text · Mistral.
Hugging Face id on that row: mistralai/Mistral-Small-24B-Instruct-2501.
Mistral Small 3 is a 24B-parameter language model optimized for low-latency performance across common AI tasks.
When you want the 2025-01-30 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: mistralai/Mistral-Small-24B-Instruct-2501. 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 |
|---|---|
consolidated.safetensors | 47,144,846,024 |
model-00001-of-00010.safetensors | 4,781,571,736 |
model-00002-of-00010.safetensors | 4,781,592,784 |
model-00003-of-00010.safetensors | 4,781,592,800 |
model-00004-of-00010.safetensors | 4,886,471,600 |
model-00005-of-00010.safetensors | 4,781,592,824 |
model-00006-of-00010.safetensors | 4,781,592,816 |
model-00007-of-00010.safetensors | 4,886,471,600 |
model-00008-of-00010.safetensors | 4,781,592,824 |
model-00009-of-00010.safetensors | 4,781,592,816 |
model-00010-of-00010.safetensors | 3,900,777,072 |
tokenizer.json | 17,078,037 |
tekken.json | 14,801,223 |
tokenizer_config.json | 199,695 |
model.safetensors.index.json | 29,894 |
special_tokens_map.json | 21,311 |
README.md | 14,757 |
.gitattributes | 1,618 |
SYSTEM_PROMPT.txt | 997 |
config.json | 623 |
params.json | 270 |
generation_config.json | 160 |
All 22 files the tree API returned are listed: every one of the 11 safetensor shards plus 11 other files. Files tab: https://huggingface.co/mistralai/Mistral-Small-24B-Instruct-2501/tree/main.
OpenRouter slug mistralai/mistral-small-24b-instruct-2501 on the 2026-08-19 catalog.
First party: https://docs.mistral.ai/getting-started/models/.
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: $0.05 in / $0.08 out per 1M tokens. Context 32,768 in / 16,384 out.
No separate internal-reasoning price on that row.
| Claim | Source | As of |
|---|---|---|
| OpenRouter id mistralai/mistral-small-24b-instruct-2501; context 32768; created 1738255409; $0.05 / $0.08 per 1M | OpenRouter /api/v1/models | 2026-08-19 |
| OpenRouter id mistralai/mistral-small-24b-instruct-2501, context 32,768 | OpenRouter /api/v1/models | 2026-08-19 |
| HF downloads 61,825 | Hugging Face API mistralai/Mistral-Small-24B-Instruct-2501 | 2026-08-19 |
| HF safetensors.total: 23,572,403,200 stored tensors; HF API usedStorage 94,321,574,156 bytes; created 2025-01-28T13:30:13.000Z; HF tensors BF16 | Hugging Face API mistralai/Mistral-Small-24B-Instruct-2501 | 2026-08-19 |
| 11 safetensor shards; shard bytes 94,289,694,896; tree files 22 | Hugging Face tree API mistralai/Mistral-Small-24B-Instruct-2501 | 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 Mistral's model family with Mistral Large 2407.
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 mistralai/mistral-small-24b-instruct-2501.