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: 128,000 tokens.
Max completion tokens on that row: 128,000.
Input / output on that row: $0.35 / $0.56 per 1M tokens.
Architecture fields: text+image->text · Mistral.
Hugging Face id on that row: mistralai/Mistral-Small-3.1-24B-Instruct-2503.
Mistral Small 3.1 24B Instruct is an upgraded variant of Mistral Small 3 (2501), featuring 24 billion parameters with advanced multimodal capabilities.
When you want the 2025-03-17 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-3.1-24B-Instruct-2503. 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 | 48,022,792,280 |
model-00001-of-00010.safetensors | 4,883,550,696 |
model-00002-of-00010.safetensors | 4,781,593,336 |
model-00003-of-00010.safetensors | 4,886,472,224 |
model-00004-of-00010.safetensors | 4,781,593,376 |
model-00005-of-00010.safetensors | 4,781,593,368 |
model-00006-of-00010.safetensors | 4,886,472,248 |
model-00007-of-00010.safetensors | 4,781,593,376 |
model-00008-of-00010.safetensors | 4,781,593,368 |
model-00009-of-00010.safetensors | 4,886,472,248 |
model-00010-of-00010.safetensors | 4,571,866,320 |
tokenizer.json | 17,078,037 |
tekken.json | 14,801,330 |
tokenizer_config.json | 198,120 |
model.safetensors.index.json | 57,907 |
special_tokens_map.json | 21,449 |
README.md | 19,022 |
chat_template.json | 2,772 |
.gitattributes | 1,618 |
SYSTEM_PROMPT.txt | 1,494 |
config.json | 1,177 |
params.json | 807 |
preprocessor_config.json | 634 |
processor_config.json | 189 |
generation_config.json | 116 |
All 25 files the tree API returned are listed: every one of the 11 safetensor shards plus 14 other files. Files tab: https://huggingface.co/mistralai/Mistral-Small-3.1-24B-Instruct-2503/tree/main.
OpenRouter slug mistralai/mistral-small-3.1-24b-instruct 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: $0.35 in / $0.56 out per 1M tokens. Context 128,000 in / 128,000 out.
No separate internal-reasoning price on that row.
| Claim | Source | As of |
|---|---|---|
| OpenRouter id mistralai/mistral-small-3.1-24b-instruct; context 128000; created 1742238937; $0.35 / $0.56 per 1M | OpenRouter /api/v1/models | 2026-08-19 |
| OpenRouter id mistralai/mistral-small-3.1-24b-instruct, context 128,000 | OpenRouter /api/v1/models | 2026-08-19 |
| HF downloads 264,646 | Hugging Face API mistralai/Mistral-Small-3.1-24B-Instruct-2503 | 2026-08-19 |
| HF safetensors.total: 24,011,361,280 stored tensors; HF API usedStorage 96,115,639,662 bytes; created 2025-03-11T17:04:58.000Z; HF tensors BF16 | Hugging Face API mistralai/Mistral-Small-3.1-24B-Instruct-2503 | 2026-08-19 |
| 11 safetensor shards; shard bytes 96,045,592,840; tree files 25 | Hugging Face tree API mistralai/Mistral-Small-3.1-24B-Instruct-2503 | 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 Saba.
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-3.1-24b-instruct.