Imagines et fasciculi
Mitte imagines cum nuntio: quae modelli eas accipiant, formae acceptae et limites earum.
POST https://api.shannon-ai.com/v1/chat/completions
Imago intra nuntium user it, ut una pars content eius. Exemplum fasciculum localem legit et eum ut data URL mittit.
import base64
from openai import OpenAI
client = OpenAI(api_key="YOUR_API_KEY", base_url="https://api.shannon-ai.com/v1")
with open("photo.jpg", "rb") as f:
image = base64.b64encode(f.read()).decode()
response = client.chat.completions.create(
model="shannon-3",
messages=[{
"role": "user",
"content": [
{"type": "text", "text": "What is in this picture?"},
{"type": "image_url", "image_url": {"url": "data:image/jpeg;base64," + image}},
],
}],
)
print(response.choices[0].message.content) import fs from "node:fs";
import OpenAI from "openai";
const client = new OpenAI({ apiKey: "YOUR_API_KEY", baseURL: "https://api.shannon-ai.com/v1" });
const image = fs.readFileSync("photo.jpg").toString("base64");
const response = await client.chat.completions.create({
model: "shannon-3",
messages: [{
role: "user",
content: [
{ type: "text", text: "What is in this picture?" },
{ type: "image_url", image_url: { url: "data:image/jpeg;base64," + image } },
],
}],
});
console.log(response.choices[0].message.content); # Linux: base64 -w0 photo.jpg macOS: base64 -i photo.jpg
IMAGE=$(base64 -w0 photo.jpg)
curl https://api.shannon-ai.com/v1/chat/completions \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d @- <<EOF
{
"model": "shannon-3",
"messages": [{
"role": "user",
"content": [
{"type": "text", "text": "What is in this picture?"},
{"type": "image_url", "image_url": {"url": "data:image/jpeg;base64,${IMAGE}"}}
]
}]
}
EOF {
"id": "chatcmpl-8d1f3a5c7e9b4d2f6a8c0e2b4d6f8a1c",
"object": "chat.completion",
"created": 1791590400,
"model": "shannon-3",
"choices": [
{
"index": 0,
"message": {
"role": "assistant",
"content": "A grey cat asleep on a windowsill, with a potted fern beside it.",
"reasoning_content": null
},
"finish_reason": "stop"
}
],
"usage": {
"prompt_tokens": 286,
"completion_tokens": 19,
"total_tokens": 305
}
} Quae modelli imagines accipiant
| Modelli | Legit |
|---|---|
shannon-3, shannon-3-pro, shannon-3.1, shannon-3.1-pro | Imagines, et documenta: PDF, Word, PowerPoint, Excel et fasciculi textus simplicis. |
shannon-1.6-lite, shannon-1.6-pro | Imagines. |
shannon-2-lite, shannon-2-pro | Imagines, in petitionibus quae etiam tools vel response_format mittunt. |
Kimi-K3-3BIT-REAP, MiniMax-M3-3BIT-REAP, Kimi-K2.6-W4A16-AUTOROUND-REAP, inkling-W4A16-AUTOROUND-REAP, MiMo-V2.5-W8A16 | Imagines. |
DeepSeek-V4-Pro-0813-3BIT-REAP, GLM-5.2-3BIT-REAP, Nemotron3Ultra-3BIT-REAP, DeepSeek-V4-Flash-0731-W4A16-AUTOROUND-REAP, Laguna-S-2.1-W4A16-AUTOROUND-REAP, MiMo-V2.5-Pro-W8A16, Hy3-W8A16 | Textus. Petitio cum imagine statu 400 respondetur. |
shannon-coder-1 | Textus. |
GET /v1/models input imaginis per id ut capabilities.vision nuntiat. Modella et pretia
- Modelli Shannon fasciculos ultimi nuntii user legunt. Pone imaginem in nuntio qui de ea quaerit.
- Familia Shannon 3 etiam paucas imagines et documenta nuntiorum user priorum in conspectu tenet cum inline missa erant, et maximum numerum imaginum per petitionem legit, a prima numeratum.
- Modelli open-weight hosted imagines omnium nuntiorum conversationis legunt.
Formae acceptae
Fasciculus duobus modis mittitur: intra petitionem ut base64, aut ut inscriptio quam API capit. Omnis fasciculus cum petitione it; API nullum endpoint upload habet.
| Endpoint | In petitione (base64) | Per inscriptionem |
|---|---|---|
/v1/chat/completions | {"type": "image_url", "image_url": {"url": "data:image/jpeg;base64,…"}} | {"type": "image_url", "image_url": {"url": "https://…"}} |
/v1/responses | {"type": "input_image", "image_url": "data:image/jpeg;base64,…"} | {"type": "input_image", "image_url": "https://…"} |
/v1/messages | {"type": "image", "source": {"type": "base64", "media_type": "image/jpeg", "data": "…"}} | {"type": "image", "source": {"type": "url", "url": "https://…"}} |
Idem nuntius user in qualibet forma:
{
"role": "user",
"content": [
{"type": "text", "text": "What is in this picture?"},
{
"type": "image_url",
"image_url": {
"url": "data:image/jpeg;base64,/9j/4AAQSkZJRgABAQAAAQABAAD…"
}
}
]
} {
"role": "user",
"content": [
{"type": "input_text", "text": "What is in this picture?"},
{
"type": "input_image",
"image_url": "data:image/jpeg;base64,/9j/4AAQSkZJRgABAQAAAQABAAD…"
}
]
} {
"role": "user",
"content": [
{"type": "text", "text": "What is in this picture?"},
{
"type": "image",
"source": {
"type": "base64",
"media_type": "image/jpeg",
"data": "/9j/4AAQSkZJRgABAQAAAQABAAD…"
}
}
]
} - Data URL formam
data:<media type>;base64,<data>habet. Pars;base64necessaria est. - In
/v1/chat/completionset/v1/responses,image_urlpotest esse ipse string aut objectum{"url": "…"}. - Typus fasciculi ex data URL vel ex
media_typevenit. Sine eo, imago utimage/pnglegitur. - Fasciculi inline ad magnitudinem corporis petitionis computantur, quod ad 32 MiB esse potest.
- Propter compatibilitatem accepta:
image_url.detail.
Limites fasciculorum remotorum
Cum inscriptionem mittis, API fasciculum capit antequam modellum currit, intra hos limites:
| Limes | Regula |
|---|---|
| Magnitudo | Ad 8 MiB per fasciculum. |
| Tempus | 20 secundae ad respondendum. |
| Redirectiones | Ad summum 5. |
| Inscriptio | http:// vel https://, sine nomine user aut password in inscriptione, in host cum inscriptione publica. |
| Responsio hosti | Status in range 200 et corpus quod vacuum non est. Typus fasciculi ex Content-Type legitur. |
| Petitur ut | User-Agent: ShannonBot/1.0 (+https://shannon-ai.com) |
Quomodo imagines in tokens computentur
In modellis open-weight hosted imago unum token pro quolibet patch 28 × 28 pixelorum computat: latitudo per 28 divisa, ad summum rotundata, multiplicata per altitudinem per 28 divisam, ad summum rotundatam. Eventus pars est usage.prompt_tokens et ut input computatur.
- 1024 × 1024
- 1,369 tokens
- 1920 × 1080
- 2,691 tokens
- 512 × 512
- 361 tokens
- Imago remota primum capitur, itaque magnitudo eius vera computatur.
- Imago cuius magnitudo legi non potest 1,024 tokens computat.
- Endpoints computationis eadem regula pro data URL utuntur. Inscriptionem remotam non capiunt et eam ut 1,024 tokens computant. Computatio tokenum
- Pro modello Shannon, quantum petitio cum imaginibus constiterit ex
usagein responsione lege.
Documenta et alii fasciculi
Familia Shannon 3 (shannon-3, shannon-3-pro, shannon-3.1, shannon-3.1-pro) etiam documenta legit. Textus documenti extrahitur et modello cum nuntio tuo datur.
| Documentum | Typus medii |
|---|---|
application/pdf | |
| Word | application/vnd.openxmlformats-officedocument.wordprocessingml.document |
| PowerPoint | application/vnd.openxmlformats-officedocument.presentationml.presentation |
| Excel | application/vnd.openxmlformats-officedocument.spreadsheetml.sheet |
Documentum est pars nuntii user, sicut imago:
| Endpoint | In petitione (base64) | Per inscriptionem |
|---|---|---|
/v1/chat/completions, /v1/messages | {"type": "document", "source": {"type": "base64", "media_type": "application/pdf", "data": "…"}} | {"type": "document", "source": {"type": "url", "url": "https://…"}} |
/v1/responses | {"type": "input_file", "file_data": "data:application/pdf;base64,…"} | {"type": "input_file", "file_url": "https://…"} |
{
"model": "shannon-3",
"messages": [
{
"role": "user",
"content": [
{
"type": "document",
"source": {
"type": "base64",
"media_type": "application/pdf",
"data": "JVBERi0xLjcKJeLjz9MK…"
}
},
{"type": "text", "text": "Summarise this report in five points."}
]
}
]
} {
"model": "shannon-3",
"input": [
{
"role": "user",
"content": [
{
"type": "input_file",
"file_data": "data:application/pdf;base64,JVBERi0xLjcKJeLjz9MK…"
},
{
"type": "input_text",
"text": "Summarise this report in five points."
}
]
}
]
} {
"model": "shannon-3",
"messages": [
{
"role": "user",
"content": [
{
"type": "document",
"source": {
"type": "base64",
"media_type": "application/pdf",
"data": "JVBERi0xLjcKJeLjz9MK…"
}
},
{"type": "text", "text": "Summarise this report in five points."}
]
}
]
} - Da verum typum medii fasciculi. Sine eo, documentum ut
application/pdflegitur. - Fasciculus textus simplicis, ut CSV, ut textus legitur et eodem modo adnectitur.
- Cum documentum legi non potest, aut fasciculus alterius typi est, modellum de hoc certior fit et in responsione dicere potest. Status tamen est
200. - In omni alio modello pars documenti ab eo quod modellum legit omittitur, et petitio ex reliquo respondetur.
- Documentum per inscriptionem missum sub limitibus pro fasciculis remotis supra capitur.
Errores
| Status | Genus | Nuntius | Quando |
|---|---|---|---|
400 | invalid_request_error | <id> does not accept image input | Imago ad modellum open-weight hosted missa est quod solum textum accipit. Nihil de saldo tuo trahitur. |
400 | invalid_request_error | audio and video input are not supported by any hosted model | Pars audio vel video ad modellum open-weight hosted missa est. |
413 | invalid_request_error | Failed to buffer the request body: … | Corpus petitionis, cum fasciculis inline, maius est quam 32 MiB. Error fert code: "request_too_large". |
Modellum Shannon cum statu 200 respondet quicumque fasciculi petitio fert: pars quam non legit omittitur. Tractatio errorum