-
Notifications
You must be signed in to change notification settings - Fork 0
Expand file tree
/
Copy pathapi.html
More file actions
1068 lines (1008 loc) · 59.2 KB
/
Copy pathapi.html
File metadata and controls
1068 lines (1008 loc) · 59.2 KB
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
<!DOCTYPE html>
<html lang="en">
<head>
<meta charset="UTF-8">
<meta name="viewport" content="width=device-width, initial-scale=1.0">
<title>WEB6 API Reference</title>
<meta name="description" content="OASIS WEB6 complete API reference — every endpoint, request shape, and response type for the unified AI gateway.">
<link rel="icon" href="data:image/svg+xml,<svg xmlns='http://www.w3.org/2000/svg' viewBox='0 0 100 100'><circle cx='50' cy='50' r='44' fill='none' stroke='%23fdd835' stroke-width='6'/><circle cx='50' cy='50' r='10' fill='%23fdd835'/></svg>">
<link href="https://fonts.googleapis.com/css2?family=Orbitron:wght@400;600;700;900&family=Rajdhani:wght@300;400;500;600;700&family=Share+Tech+Mono&display=swap" rel="stylesheet">
<style>
:root{
--gold:#fdd835;--gold-glow:rgba(253,216,53,.18);
--cyan:#00e5ff;--green:#00e676;--red:#ff5252;--purple:#a78bfa;
--bg:#030714;--bg-card:#0a1535;--bg-card2:#071028;
--text:#d0e4ff;--dim:#a8bfd8;--heading:#ffffff;
}
*,*::before,*::after{box-sizing:border-box;margin:0;padding:0}
html{scroll-behavior:smooth}
body{background:var(--bg);color:var(--text);font-family:'Rajdhani',sans-serif;font-size:16px;line-height:1.6;overflow-x:hidden}
a{color:var(--dim);text-decoration:none;transition:color .2s}
a:hover{color:var(--gold)}
nav{position:fixed;top:0;left:0;right:0;z-index:100;padding:18px 40px;display:flex;align-items:center;justify-content:space-between;background:rgba(3,7,20,.9);backdrop-filter:blur(12px);border-bottom:1px solid rgba(253,216,53,.12)}
.nav-brand{font-family:'Orbitron',sans-serif;font-size:13px;font-weight:700;letter-spacing:.22em;color:#fff;text-decoration:none}
.nav-brand span{color:var(--gold)}
.nav-links{display:flex;gap:24px;list-style:none}
.nav-links a{font-family:'Share Tech Mono',monospace;font-size:11px;letter-spacing:.14em;color:var(--dim);text-transform:uppercase;transition:color .2s}
.nav-links a:hover{color:var(--gold)}
.nav-cta{font-family:'Share Tech Mono',monospace;font-size:11px;letter-spacing:.1em;color:var(--gold);border:1px solid rgba(253,216,53,.35);border-radius:999px;padding:8px 18px;transition:background .2s;white-space:nowrap}
.nav-cta:hover{background:rgba(253,216,53,.08)}
@media(max-width:900px){.nav-links{display:none}.nav-cta{display:none}}
.layout{display:grid;grid-template-columns:240px 1fr;gap:0;max-width:1280px;margin:0 auto;padding-top:72px;min-height:100vh}
/* Sidebar */
.sidebar{position:sticky;top:72px;height:calc(100vh - 72px);overflow-y:auto;padding:32px 20px;border-right:1px solid rgba(253,216,53,.08);background:rgba(3,7,20,.6)}
.sidebar-section{margin-bottom:28px}
.sidebar-section h3{font-family:'Share Tech Mono',monospace;font-size:10px;letter-spacing:.22em;color:var(--gold);text-transform:uppercase;margin-bottom:10px;padding-bottom:6px;border-bottom:1px solid rgba(253,216,53,.12)}
.sidebar-section a{display:block;font-size:13px;color:var(--dim);padding:4px 0 4px 10px;border-left:2px solid transparent;transition:color .2s,border-color .2s}
.sidebar-section a:hover,.sidebar-section a.active{color:var(--gold);border-left-color:var(--gold)}
@media(max-width:900px){
.layout{grid-template-columns:1fr}
.sidebar{display:none}
}
/* Content */
.content{padding:40px 48px 80px;max-width:900px}
@media(max-width:600px){.content{padding:24px 20px 60px}}
.kicker{font-family:'Share Tech Mono',monospace;font-size:11px;letter-spacing:.28em;color:var(--gold);margin-bottom:12px}
h1{font-family:'Orbitron',sans-serif;font-size:clamp(26px,4vw,44px);font-weight:900;color:#fff;margin-bottom:12px}
.intro{font-size:17px;color:var(--dim);max-width:660px;line-height:1.7;margin-bottom:48px}
.line{display:block;width:60px;height:2px;background:linear-gradient(90deg,transparent,var(--gold),transparent);margin:0 0 40px}
/* Section headers */
.api-group{margin-bottom:60px}
.api-group h2{font-family:'Orbitron',sans-serif;font-size:18px;font-weight:900;letter-spacing:.1em;color:#fff;margin-bottom:24px;padding-bottom:10px;border-bottom:1px solid rgba(253,216,53,.15)}
/* Endpoint card */
.ep{background:var(--bg-card);border:1px solid rgba(255,255,255,.07);border-radius:14px;margin-bottom:16px;overflow:hidden;transition:border-color .2s}
.ep:hover{border-color:rgba(253,216,53,.18)}
.ep-head{display:flex;align-items:center;gap:14px;padding:16px 20px;cursor:pointer;user-select:none}
.ep-head::-webkit-details-marker{display:none}
.method{font-family:'Share Tech Mono',monospace;font-size:11px;font-weight:700;letter-spacing:.1em;padding:4px 10px;border-radius:6px;flex-shrink:0}
.method.post{color:#000;background:var(--green)}
.method.get{color:#000;background:var(--cyan)}
.ep-path{font-family:'Share Tech Mono',monospace;font-size:14px;color:#e8f0ff;flex:1}
.ep-desc{font-size:14px;color:var(--dim);padding:0 20px 18px}
.ep-body{padding:0 20px 20px;border-top:1px solid rgba(255,255,255,.05);margin-top:0}
.field-table{width:100%;border-collapse:collapse;margin-top:14px}
.field-table th{font-family:'Share Tech Mono',monospace;font-size:10px;letter-spacing:.18em;color:var(--gold);background:rgba(253,216,53,.06);padding:8px 12px;text-align:left;border-bottom:1px solid rgba(253,216,53,.1)}
.field-table td{font-size:13px;color:var(--dim);padding:8px 12px;border-bottom:1px solid rgba(255,255,255,.04);vertical-align:top}
.field-table td:first-child{font-family:'Share Tech Mono',monospace;color:#e8f0ff}
.field-table td:nth-child(2){color:var(--purple);font-family:'Share Tech Mono',monospace;font-size:12px}
.field-table tr:last-child td{border-bottom:none}
.req-label{font-family:'Share Tech Mono',monospace;font-size:10px;color:var(--red);border:1px solid rgba(255,82,82,.3);border-radius:4px;padding:1px 6px;margin-left:6px}
.opt-label{font-family:'Share Tech Mono',monospace;font-size:10px;color:var(--dim);border:1px solid rgba(168,191,216,.2);border-radius:4px;padding:1px 6px;margin-left:6px}
.sub-head{font-family:'Share Tech Mono',monospace;font-size:11px;letter-spacing:.18em;color:var(--gold);text-transform:uppercase;margin:16px 0 8px}
pre{background:rgba(0,0,0,.4);border:1px solid rgba(255,255,255,.08);border-radius:8px;padding:14px 16px;overflow-x:auto;font-family:'Share Tech Mono',monospace;font-size:12px;color:#b0d4ff;line-height:1.6;margin-top:8px}
/* Auth badge */
.auth-note{display:inline-flex;align-items:center;gap:8px;background:rgba(253,216,53,.07);border:1px solid rgba(253,216,53,.2);border-radius:8px;padding:10px 16px;font-size:13px;color:var(--dim);margin-bottom:32px}
.auth-note strong{color:#fff}
/* Base URL bar */
.base-url{background:var(--bg-card2);border:1px solid rgba(0,229,255,.2);border-radius:10px;padding:14px 20px;font-family:'Share Tech Mono',monospace;font-size:13px;color:var(--cyan);margin-bottom:40px}
.base-url span{color:var(--dim);font-size:11px;display:block;margin-bottom:4px;letter-spacing:.12em}
</style>
</head>
<body>
<nav>
<a class="nav-brand" href="/"><span>WEB</span>6</a>
<ul class="nav-links">
<li><a href="/">HOME</a></li>
<li><a href="/#providers">PROVIDERS</a></li>
<li><a href="/#features">FEATURES</a></li>
<li><a href="/api.html" style="color:var(--gold)">API REFERENCE</a></li>
<li><a href="/sdk.html">SDK</a></li>
<li><a href="/pricing.html">PRICING</a></li>
</ul>
<a class="nav-cta" href="https://oportal.oasisomniverse.one" target="_blank" rel="noopener">GET API KEY</a>
</nav>
<div class="layout">
<!-- Sidebar TOC -->
<aside class="sidebar">
<div class="sidebar-section">
<h3>Getting Started</h3>
<a href="#overview">Overview</a>
<a href="#auth">Authentication</a>
<a href="#errors">Errors</a>
</div>
<div class="sidebar-section">
<h3>AI Core</h3>
<a href="#completions">Completions</a>
<a href="#embeddings">Embeddings</a>
<a href="#images">Images</a>
<a href="#video">Video</a>
<a href="#audio">Audio</a>
</div>
<div class="sidebar-section">
<h3>Search & Language</h3>
<a href="#search">Search</a>
<a href="#rerank">Rerank</a>
<a href="#moderation">Moderation</a>
<a href="#translation">Translation</a>
<a href="#classification">Classification</a>
<a href="#extraction">Extraction</a>
</div>
<div class="sidebar-section">
<h3>Advanced</h3>
<a href="#documents">Documents</a>
<a href="#code">Code Execution</a>
<a href="#batch">Batch</a>
<a href="#memory">Memory</a>
<a href="#guardrails">Guardrails</a>
<a href="#finetuning">Fine-Tuning</a>
<a href="#graphrag">GraphRAG</a>
<a href="#prompts">Prompts</a>
<a href="#fahrn">FAHRN</a>
</div>
<div class="sidebar-section">
<h3>Utilities</h3>
<a href="#models">Models</a>
<a href="#providers-ep">Providers</a>
<a href="#estimate">Cost Estimate</a>
<a href="#usage">Usage</a>
<a href="#health">Health</a>
</div>
<div class="sidebar-section">
<h3>OpenServ</h3>
<a href="#openserv-models">OpenServ Models</a>
</div>
<div class="sidebar-section">
<h3>Orchestrators</h3>
<a href="#orchestrate-crewai">CrewAI</a>
<a href="#orchestrate-autogen">AutoGen</a>
<a href="#orchestrate-langgraph">LangGraph</a>
</div>
<div class="sidebar-section">
<h3>MCP</h3>
<a href="#mcp-overview">Overview</a>
<a href="#mcp-tools">Tool Reference</a>
</div>
</aside>
<!-- Main content -->
<main class="content">
<div class="kicker">REFERENCE</div>
<h1>WEB6 API Reference</h1>
<p class="intro">One API, every AI. All 35+ endpoints of the OASIS WEB6 unified AI gateway — request shapes, field types, and response structures.</p>
<span class="line"></span>
<div id="overview" class="base-url">
<span>BASE URL</span>
https://api.web6.oasisomniverse.one
</div>
<div class="auth-note">
<strong>Authentication:</strong> All endpoints require <code>Authorization: Bearer <JWT></code> or <code>X-Api-Key: <key></code>. Get yours at <a href="https://oportal.oasisomniverse.one" target="_blank" rel="noopener" style="color:var(--gold)">OPORTAL</a>.
</div>
<!-- ── COMPLETIONS ─────────────────────────────────────────────────── -->
<div id="completions" class="api-group">
<h2>Completions</h2>
<details class="ep">
<summary class="ep-head">
<span class="method post">POST</span>
<span class="ep-path">/v1/complete</span>
</summary>
<div class="ep-desc">Routes a chat completion to the best-fit AI provider for your plan. Optionally enhances the request with FAHRN reasoning dispatch and Holonic BRAID graph injection.</div>
<div class="ep-body">
<div class="sub-head">Request body</div>
<table class="field-table">
<tr><th>Field</th><th>Type</th><th>Description</th></tr>
<tr><td>messages<span class="req-label">required</span></td><td>array</td><td>Array of <code>{"role":"user|assistant|system","content":"..."}</code> objects</td></tr>
<tr><td>provider</td><td>string</td><td>Target provider: <code>openai</code>, <code>anthropic</code>, <code>gemini</code>, <code>groq</code>, <code>mistral</code>, <code>cohere</code>, <code>xai</code>, <code>deepseek</code>, <code>ollama</code>, <code>awsbedrock</code>, <code>azureopenai</code>, <code>auto</code> (default)</td></tr>
<tr><td>model</td><td>string</td><td>Model ID e.g. <code>gpt-4o</code>, <code>claude-sonnet-5</code>. Default: <code>auto</code></td></tr>
<tr><td>avatarId</td><td>string (uuid)</td><td>OASIS avatar ID for karma-gated access and usage metering</td></tr>
<tr><td>useFAHRN</td><td>boolean</td><td>Run the last user message through the FAHRN reasoning network and inject the plan into context</td></tr>
<tr><td>useHolonicBraid</td><td>boolean</td><td>Inject the shared Holonic BRAID reasoning graph for the detected task type</td></tr>
<tr><td>injectAvatarContext</td><td>boolean</td><td>Prepend this avatar's identity/karma context to the system prompt</td></tr>
<tr><td>tools</td><td>array</td><td>Tool definitions (OpenAI-compatible function calling schema)</td></tr>
<tr><td>temperature</td><td>number</td><td>0–2. Default provider-specific</td></tr>
<tr><td>maxTokens</td><td>integer</td><td>Max completion tokens</td></tr>
<tr><td>routing</td><td>object</td><td>Advanced routing overrides e.g. <code>{"useOpenServ":true}</code></td></tr>
</table>
<div class="sub-head">Example</div>
<pre>{
"provider": "auto",
"model": "auto",
"messages": [
{"role": "system", "content": "You are a helpful OASIS guide."},
{"role": "user", "content": "What is holonic memory?"}
]
}</pre>
</div>
</details>
<details class="ep">
<summary class="ep-head">
<span class="method post">POST</span>
<span class="ep-path">/v1/complete/stream</span>
</summary>
<div class="ep-desc">Same as <code>/v1/complete</code> but returns a <code>text/event-stream</code> SSE response. Each <code>data:</code> line is a JSON completion chunk; the final chunk has <code>"done":true</code>.</div>
<div class="ep-body">
<div class="sub-head">Response format (SSE)</div>
<pre>data: {"content":"Once ","done":false}
data: {"content":"upon ","done":false}
data: {"content":"a time...","done":false}
data: {"content":"","done":true,"promptTokens":12,"completionTokens":47}</pre>
</div>
</details>
<details class="ep">
<summary class="ep-head">
<span class="method post">POST</span>
<span class="ep-path">/v1/complete/tool-result</span>
</summary>
<div class="ep-desc">Re-enters the completion pipeline with a message history that already contains <code>role:"tool"</code> result messages. Use this for agentic tool-calling loops.</div>
</details>
</div>
<!-- ── EMBEDDINGS ──────────────────────────────────────────────────── -->
<div id="embeddings" class="api-group">
<h2>Embeddings</h2>
<details class="ep">
<summary class="ep-head">
<span class="method post">POST</span>
<span class="ep-path">/v1/embeddings</span>
</summary>
<div class="ep-desc">Generates vector embeddings for one or more text strings.</div>
<div class="ep-body">
<table class="field-table">
<tr><th>Field</th><th>Type</th><th>Description</th></tr>
<tr><td>texts<span class="req-label">required</span></td><td>string[]</td><td>One or more strings to embed</td></tr>
<tr><td>provider</td><td>string</td><td>e.g. <code>openai</code>, <code>cohere</code>, <code>auto</code></td></tr>
<tr><td>model</td><td>string</td><td>e.g. <code>text-embedding-3-large</code></td></tr>
</table>
</div>
</details>
</div>
<!-- ── IMAGES ─────────────────────────────────────────────────────── -->
<div id="images" class="api-group">
<h2>Image Generation</h2>
<details class="ep">
<summary class="ep-head">
<span class="method post">POST</span>
<span class="ep-path">/v1/images/generate</span>
</summary>
<div class="ep-desc">Generates images from text prompts via DALL·E 3, Stable Diffusion, Midjourney and others.</div>
<div class="ep-body">
<table class="field-table">
<tr><th>Field</th><th>Type</th><th>Description</th></tr>
<tr><td>prompt<span class="req-label">required</span></td><td>string</td><td>Image description</td></tr>
<tr><td>provider</td><td>string</td><td>e.g. <code>openai</code>, <code>stability</code>, <code>auto</code></td></tr>
<tr><td>width</td><td>integer</td><td>Output width in pixels</td></tr>
<tr><td>height</td><td>integer</td><td>Output height in pixels</td></tr>
<tr><td>n</td><td>integer</td><td>Number of images (default 1)</td></tr>
</table>
</div>
</details>
</div>
<!-- ── VIDEO ──────────────────────────────────────────────────────── -->
<div id="video" class="api-group">
<h2>Video Generation</h2>
<details class="ep">
<summary class="ep-head">
<span class="method post">POST</span>
<span class="ep-path">/v1/video/generate</span>
</summary>
<div class="ep-desc">Generates video from text or image via RunwayML, Luma AI, Pika Labs, Kling AI, HailuoAI (MiniMax), Vidu, Wan Video. Long-running — supply <code>callbackUrl</code> for webhook notification.</div>
<div class="ep-body">
<table class="field-table">
<tr><th>Field</th><th>Type</th><th>Description</th></tr>
<tr><td>prompt<span class="req-label">required</span></td><td>string</td><td>Video description</td></tr>
<tr><td>provider</td><td>string</td><td>e.g. <code>runwayml</code>, <code>lumaai</code>, <code>auto</code></td></tr>
<tr><td>imageUrl</td><td>string</td><td>Seed image URL for image-to-video</td></tr>
<tr><td>duration</td><td>integer</td><td>Duration in seconds</td></tr>
<tr><td>aspectRatio</td><td>string</td><td>e.g. <code>16:9</code>, <code>9:16</code>, <code>1:1</code></td></tr>
<tr><td>callbackUrl</td><td>string</td><td>Webhook URL to receive completion POST when rendering finishes</td></tr>
</table>
</div>
</details>
</div>
<!-- ── AUDIO ──────────────────────────────────────────────────────── -->
<div id="audio" class="api-group">
<h2>Audio</h2>
<details class="ep">
<summary class="ep-head">
<span class="method post">POST</span>
<span class="ep-path">/v1/audio/speech</span>
</summary>
<div class="ep-desc">Synthesises speech from text (TTS). Returns audio bytes.</div>
<div class="ep-body">
<table class="field-table">
<tr><th>Field</th><th>Type</th><th>Description</th></tr>
<tr><td>text<span class="req-label">required</span></td><td>string</td><td>Text to synthesise</td></tr>
<tr><td>voice</td><td>string</td><td>Voice ID e.g. <code>alloy</code>, <code>nova</code>, <code>shimmer</code></td></tr>
<tr><td>provider</td><td>string</td><td>e.g. <code>openai</code>, <code>elevenlabs</code>, <code>auto</code></td></tr>
</table>
</div>
</details>
<details class="ep">
<summary class="ep-head">
<span class="method post">POST</span>
<span class="ep-path">/v1/audio/transcriptions</span>
</summary>
<div class="ep-desc">Transcribes audio to text (STT) via Whisper or compatible providers. Accepts multipart form with an audio file.</div>
<div class="ep-body">
<table class="field-table">
<tr><th>Field</th><th>Type</th><th>Description</th></tr>
<tr><td>file<span class="req-label">required</span></td><td>multipart file</td><td>Audio file (.mp3, .wav, .m4a, etc.)</td></tr>
<tr><td>language</td><td>string</td><td>ISO-639-1 code e.g. <code>en</code>, <code>fr</code></td></tr>
</table>
</div>
</details>
</div>
<!-- ── SEARCH ─────────────────────────────────────────────────────── -->
<div id="search" class="api-group">
<h2>Search</h2>
<details class="ep">
<summary class="ep-head">
<span class="method post">POST</span>
<span class="ep-path">/v1/search</span>
</summary>
<div class="ep-desc">Web search via Tavily, Serper, Exa, Perplexity and others.</div>
<div class="ep-body">
<table class="field-table">
<tr><th>Field</th><th>Type</th><th>Description</th></tr>
<tr><td>query<span class="req-label">required</span></td><td>string</td><td>Search query</td></tr>
<tr><td>provider</td><td>string</td><td>e.g. <code>tavily</code>, <code>serper</code>, <code>exa</code>, <code>auto</code></td></tr>
<tr><td>maxResults</td><td>integer</td><td>Max results to return (default 10)</td></tr>
</table>
</div>
</details>
</div>
<!-- ── RERANK ─────────────────────────────────────────────────────── -->
<div id="rerank" class="api-group">
<h2>Reranking</h2>
<details class="ep">
<summary class="ep-head">
<span class="method post">POST</span>
<span class="ep-path">/v1/rerank</span>
</summary>
<div class="ep-desc">Reranks a list of documents by relevance to a query via Cohere Rerank or compatible providers.</div>
<div class="ep-body">
<table class="field-table">
<tr><th>Field</th><th>Type</th><th>Description</th></tr>
<tr><td>query<span class="req-label">required</span></td><td>string</td><td>Query to rank against</td></tr>
<tr><td>documents<span class="req-label">required</span></td><td>string[]</td><td>Documents to rerank</td></tr>
<tr><td>topN</td><td>integer</td><td>Number of top results to return (default 5)</td></tr>
<tr><td>provider</td><td>string</td><td>e.g. <code>cohere</code>, <code>auto</code></td></tr>
</table>
</div>
</details>
</div>
<!-- ── MODERATION ─────────────────────────────────────────────────── -->
<div id="moderation" class="api-group">
<h2>Moderation</h2>
<details class="ep">
<summary class="ep-head">
<span class="method post">POST</span>
<span class="ep-path">/v1/moderation</span>
</summary>
<div class="ep-desc">Checks text for harmful, unsafe or policy-violating content.</div>
<div class="ep-body">
<table class="field-table">
<tr><th>Field</th><th>Type</th><th>Description</th></tr>
<tr><td>text<span class="req-label">required</span></td><td>string</td><td>Text to check</td></tr>
<tr><td>provider</td><td>string</td><td>e.g. <code>openai</code>, <code>llamaguard</code>, <code>auto</code></td></tr>
</table>
</div>
</details>
</div>
<!-- ── TRANSLATION ────────────────────────────────────────────────── -->
<div id="translation" class="api-group">
<h2>Translation</h2>
<details class="ep">
<summary class="ep-head">
<span class="method post">POST</span>
<span class="ep-path">/v1/translate</span>
</summary>
<div class="ep-desc">Translates text to a target language via DeepL, Google Translate, or LLM-backed providers.</div>
<div class="ep-body">
<table class="field-table">
<tr><th>Field</th><th>Type</th><th>Description</th></tr>
<tr><td>text<span class="req-label">required</span></td><td>string</td><td>Source text</td></tr>
<tr><td>targetLanguage<span class="req-label">required</span></td><td>string</td><td>ISO-639-1 e.g. <code>fr</code>, <code>de</code>, <code>ja</code></td></tr>
<tr><td>sourceLanguage</td><td>string</td><td>Auto-detected if omitted</td></tr>
<tr><td>provider</td><td>string</td><td>e.g. <code>deepl</code>, <code>googletranslate</code>, <code>auto</code></td></tr>
</table>
</div>
</details>
</div>
<!-- ── CLASSIFICATION ─────────────────────────────────────────────── -->
<div id="classification" class="api-group">
<h2>Classification</h2>
<details class="ep">
<summary class="ep-head">
<span class="method post">POST</span>
<span class="ep-path">/v1/classify</span>
</summary>
<div class="ep-desc">Zero-shot text classification against a user-supplied label set.</div>
<div class="ep-body">
<table class="field-table">
<tr><th>Field</th><th>Type</th><th>Description</th></tr>
<tr><td>text<span class="req-label">required</span></td><td>string</td><td>Text to classify</td></tr>
<tr><td>labels<span class="req-label">required</span></td><td>string[]</td><td>Candidate labels e.g. <code>["positive","negative","neutral"]</code></td></tr>
<tr><td>provider</td><td>string</td><td>e.g. <code>cohere</code>, <code>auto</code></td></tr>
</table>
</div>
</details>
</div>
<!-- ── EXTRACTION ─────────────────────────────────────────────────── -->
<div id="extraction" class="api-group">
<h2>Structured Extraction</h2>
<details class="ep">
<summary class="ep-head">
<span class="method post">POST</span>
<span class="ep-path">/v1/extract</span>
</summary>
<div class="ep-desc">Extracts structured data from unstructured text according to a JSON schema.</div>
<div class="ep-body">
<table class="field-table">
<tr><th>Field</th><th>Type</th><th>Description</th></tr>
<tr><td>text<span class="req-label">required</span></td><td>string</td><td>Source text</td></tr>
<tr><td>schema<span class="req-label">required</span></td><td>object</td><td>JSON schema describing the target structure</td></tr>
<tr><td>provider</td><td>string</td><td>e.g. <code>openai</code>, <code>auto</code></td></tr>
</table>
</div>
</details>
</div>
<!-- ── DOCUMENTS ─────────────────────────────────────────────────── -->
<div id="documents" class="api-group">
<h2>Document Processing</h2>
<details class="ep">
<summary class="ep-head">
<span class="method post">POST</span>
<span class="ep-path">/v1/documents/parse</span>
</summary>
<div class="ep-desc">Parses PDFs, Word docs, and other document formats into structured text. Accepts multipart form.</div>
<div class="ep-body">
<table class="field-table">
<tr><th>Field</th><th>Type</th><th>Description</th></tr>
<tr><td>file<span class="req-label">required</span></td><td>multipart file</td><td>Document file (.pdf, .docx, .txt, etc.)</td></tr>
<tr><td>provider</td><td>string</td><td>e.g. <code>llamaparse</code>, <code>auto</code></td></tr>
</table>
</div>
</details>
</div>
<!-- ── CODE ──────────────────────────────────────────────────────── -->
<div id="code" class="api-group">
<h2>Code Execution</h2>
<details class="ep">
<summary class="ep-head">
<span class="method post">POST</span>
<span class="ep-path">/v1/code/execute</span>
</summary>
<div class="ep-desc">Executes code in a sandboxed environment and returns output.</div>
<div class="ep-body">
<table class="field-table">
<tr><th>Field</th><th>Type</th><th>Description</th></tr>
<tr><td>code<span class="req-label">required</span></td><td>string</td><td>Code to execute</td></tr>
<tr><td>language</td><td>string</td><td><code>python</code>, <code>javascript</code>, <code>bash</code> (default: python)</td></tr>
<tr><td>provider</td><td>string</td><td>Execution sandbox provider</td></tr>
</table>
</div>
</details>
</div>
<!-- ── BATCH ──────────────────────────────────────────────────────── -->
<div id="batch" class="api-group">
<h2>Batch Processing</h2>
<details class="ep">
<summary class="ep-head">
<span class="method post">POST</span>
<span class="ep-path">/v1/batch/submit</span>
</summary>
<div class="ep-desc">Submits a batch of completion requests at up to 50% cost reduction via OpenAI Batch API or Anthropic Message Batches. Supply <code>callbackUrl</code> for webhook notification when complete.</div>
<div class="ep-body">
<table class="field-table">
<tr><th>Field</th><th>Type</th><th>Description</th></tr>
<tr><td>requests<span class="req-label">required</span></td><td>array</td><td>Array of completion request objects</td></tr>
<tr><td>provider</td><td>string</td><td>e.g. <code>openai</code>, <code>anthropic</code>, <code>auto</code></td></tr>
<tr><td>callbackUrl</td><td>string</td><td>Webhook URL for completion notification</td></tr>
</table>
</div>
</details>
<details class="ep">
<summary class="ep-head">
<span class="method get">GET</span>
<span class="ep-path">/v1/batch/{batchId}/status</span>
</summary>
<div class="ep-desc">Polls a previously submitted batch job for status and results.</div>
<div class="ep-body">
<table class="field-table">
<tr><th>Param</th><th>Type</th><th>Description</th></tr>
<tr><td>batchId</td><td>path string</td><td>Batch ID returned by <code>/v1/batch/submit</code></td></tr>
<tr><td>provider</td><td>query string</td><td>Provider that owns the batch job</td></tr>
</table>
</div>
</details>
</div>
<!-- ── MEMORY ─────────────────────────────────────────────────────── -->
<div id="memory" class="api-group">
<h2>Memory</h2>
<details class="ep">
<summary class="ep-head">
<span class="method post">POST</span>
<span class="ep-path">/v1/memory/store</span>
</summary>
<div class="ep-desc">Stores a memory fragment for later retrieval via Mem0, Zep, Qdrant, Weaviate, or built-in OASIS holonic memory.</div>
<div class="ep-body">
<table class="field-table">
<tr><th>Field</th><th>Type</th><th>Description</th></tr>
<tr><td>content<span class="req-label">required</span></td><td>string</td><td>Content to store</td></tr>
<tr><td>userId</td><td>string</td><td>User/avatar identifier</td></tr>
<tr><td>provider</td><td>string</td><td>e.g. <code>mem0</code>, <code>zep</code>, <code>auto</code></td></tr>
</table>
</div>
</details>
<details class="ep">
<summary class="ep-head">
<span class="method post">POST</span>
<span class="ep-path">/v1/memory/query</span>
</summary>
<div class="ep-desc">Semantic search over stored memories for a given user.</div>
<div class="ep-body">
<table class="field-table">
<tr><th>Field</th><th>Type</th><th>Description</th></tr>
<tr><td>query<span class="req-label">required</span></td><td>string</td><td>Query to search</td></tr>
<tr><td>userId</td><td>string</td><td>Scope to a specific user</td></tr>
<tr><td>provider</td><td>string</td><td>Memory provider</td></tr>
</table>
</div>
</details>
</div>
<!-- ── GUARDRAILS ─────────────────────────────────────────────────── -->
<div id="guardrails" class="api-group">
<h2>Guardrails</h2>
<details class="ep">
<summary class="ep-head">
<span class="method post">POST</span>
<span class="ep-path">/v1/guardrails/check</span>
</summary>
<div class="ep-desc">Checks text against safety and policy guardrails via NeMo Guardrails or compatible providers.</div>
<div class="ep-body">
<table class="field-table">
<tr><th>Field</th><th>Type</th><th>Description</th></tr>
<tr><td>text<span class="req-label">required</span></td><td>string</td><td>Input to check</td></tr>
<tr><td>provider</td><td>string</td><td>e.g. <code>nemo</code>, <code>auto</code></td></tr>
</table>
</div>
</details>
</div>
<!-- ── FINE-TUNING ────────────────────────────────────────────────── -->
<div id="finetuning" class="api-group">
<h2>Fine-Tuning</h2>
<details class="ep">
<summary class="ep-head">
<span class="method post">POST</span>
<span class="ep-path">/v1/fine-tuning/jobs</span>
</summary>
<div class="ep-desc">Creates a fine-tuning job. Supply <code>callbackUrl</code> to receive a webhook when training completes.</div>
<div class="ep-body">
<table class="field-table">
<tr><th>Field</th><th>Type</th><th>Description</th></tr>
<tr><td>baseModel<span class="req-label">required</span></td><td>string</td><td>Base model ID to fine-tune</td></tr>
<tr><td>trainingData<span class="req-label">required</span></td><td>array</td><td>Array of training examples</td></tr>
<tr><td>provider</td><td>string</td><td>e.g. <code>openai</code>, <code>togetherai</code>, <code>mistral</code></td></tr>
<tr><td>callbackUrl</td><td>string</td><td>Webhook URL for training completion</td></tr>
</table>
</div>
</details>
<details class="ep">
<summary class="ep-head">
<span class="method get">GET</span>
<span class="ep-path">/v1/fine-tuning/jobs/{jobId}</span>
</summary>
<div class="ep-desc">Gets the status of a fine-tuning job.</div>
</details>
</div>
<!-- ── GRAPHRAG ────────────────────────────────────────────────────── -->
<div id="graphrag" class="api-group">
<h2>GraphRAG</h2>
<details class="ep">
<summary class="ep-head">
<span class="method post">POST</span>
<span class="ep-path">/v1/graphrag/query</span>
</summary>
<div class="ep-desc">Graph-based retrieval-augmented generation — answers complex multi-hop questions using a knowledge graph.</div>
<div class="ep-body">
<table class="field-table">
<tr><th>Field</th><th>Type</th><th>Description</th></tr>
<tr><td>query<span class="req-label">required</span></td><td>string</td><td>Natural language query</td></tr>
<tr><td>provider</td><td>string</td><td>e.g. <code>thegraph</code>, <code>neo4j</code>, <code>auto</code></td></tr>
</table>
</div>
</details>
</div>
<!-- ── PROMPTS ────────────────────────────────────────────────────── -->
<div id="prompts" class="api-group">
<h2>Prompt Optimisation</h2>
<details class="ep">
<summary class="ep-head">
<span class="method post">POST</span>
<span class="ep-path">/v1/prompts/optimise</span>
</summary>
<div class="ep-desc">Automatically rewrites and improves a prompt using SkillOpt or LLM-based optimisation.</div>
<div class="ep-body">
<table class="field-table">
<tr><th>Field</th><th>Type</th><th>Description</th></tr>
<tr><td>prompt<span class="req-label">required</span></td><td>string</td><td>Original prompt</td></tr>
<tr><td>provider</td><td>string</td><td>Optimisation provider</td></tr>
</table>
</div>
</details>
</div>
<!-- ── FAHRN ──────────────────────────────────────────────────────── -->
<div id="fahrn" class="api-group">
<h2>FAHRN — Reasoning Network</h2>
<details class="ep">
<summary class="ep-head">
<span class="method post">POST</span>
<span class="ep-path">/v1/reasoning-network/dispatch</span>
</summary>
<div class="ep-desc">Dispatches a problem through the Fractal Adaptive Holonic Reasoning Network — classifies the task, scores agents, assembles the optimal sub-network, and returns a final answer with a Mermaid execution plan.</div>
<div class="ep-body">
<table class="field-table">
<tr><th>Field</th><th>Type</th><th>Description</th></tr>
<tr><td>problem<span class="req-label">required</span></td><td>string</td><td>The problem or question to solve</td></tr>
<tr><td>taskType</td><td>string</td><td>Task hint e.g. <code>general</code>, <code>code</code>, <code>research</code>, <code>creative</code></td></tr>
<tr><td>mode</td><td>string</td><td><code>Serial</code> (default), <code>Parallel</code>, <code>Hybrid</code></td></tr>
</table>
</div>
</details>
</div>
<!-- ── MODELS ─────────────────────────────────────────────────────── -->
<div id="models" class="api-group">
<h2>Model Catalogue</h2>
<details class="ep">
<summary class="ep-head">
<span class="method get">GET</span>
<span class="ep-path">/v1/models</span>
</summary>
<div class="ep-desc">Lists all 23+ models in the WEB6 catalogue with pricing, context window, and minimum plan requirement.</div>
<div class="ep-body">
<table class="field-table">
<tr><th>Param</th><th>Type</th><th>Description</th></tr>
<tr><td>plan</td><td>query string</td><td>Filter to models accessible on this plan: <code>Free</code>, <code>Bronze</code>, <code>Silver</code>, <code>Gold</code></td></tr>
</table>
<div class="sub-head">Example response</div>
<pre>{
"total": 23,
"models": [
{
"id": "gpt-4o",
"name": "GPT-4o",
"providerName": "OpenAI",
"minPlanLabel": "Bronze",
"inputPer1kUSD": 0.0025,
"outputPer1kUSD": 0.01,
"contextWindow": 128000,
"supportsVision": true,
"supportsFunctions": true
}
]
}</pre>
</div>
</details>
<details class="ep">
<summary class="ep-head">
<span class="method get">GET</span>
<span class="ep-path">/v1/models/{modelId}</span>
</summary>
<div class="ep-desc">Returns full detail for a single model.</div>
</details>
</div>
<!-- ── PROVIDERS ──────────────────────────────────────────────────── -->
<div id="providers-ep" class="api-group">
<h2>Provider Status</h2>
<details class="ep">
<summary class="ep-head">
<span class="method get">GET</span>
<span class="ep-path">/v1/providers</span>
</summary>
<div class="ep-desc">Returns all 20+ providers with their minimum plan requirement, supported endpoint types, and live status.</div>
</details>
</div>
<!-- ── ESTIMATE ───────────────────────────────────────────────────── -->
<div id="estimate" class="api-group">
<h2>Cost Estimate</h2>
<details class="ep">
<summary class="ep-head">
<span class="method post">POST</span>
<span class="ep-path">/v1/estimate</span>
</summary>
<div class="ep-desc">Previews the estimated USD cost of a call before executing it, based on token counts and the provider's current pricing.</div>
<div class="ep-body">
<table class="field-table">
<tr><th>Field</th><th>Type</th><th>Description</th></tr>
<tr><td>provider<span class="req-label">required</span></td><td>string</td><td>Provider ID e.g. <code>openai</code></td></tr>
<tr><td>model<span class="req-label">required</span></td><td>string</td><td>Model ID e.g. <code>gpt-4o</code></td></tr>
<tr><td>promptTokens<span class="req-label">required</span></td><td>integer</td><td>Expected prompt token count</td></tr>
<tr><td>completionTokens</td><td>integer</td><td>Expected completion token count (default 0)</td></tr>
</table>
<div class="sub-head">Response</div>
<pre>{ "estimatedUSD": 0.001250, "note": "Based on gpt-4o pricing at $0.0025/1K in + $0.01/1K out" }</pre>
</div>
</details>
</div>
<!-- ── USAGE ──────────────────────────────────────────────────────── -->
<div id="usage" class="api-group">
<h2>Usage</h2>
<details class="ep">
<summary class="ep-head">
<span class="method get">GET</span>
<span class="ep-path">/v1/usage</span>
</summary>
<div class="ep-desc">Returns this avatar's usage summary — daily calls used, effective call limit (plan × karma multiplier), monthly token spend, and remaining quota today.</div>
<div class="ep-body">
<table class="field-table">
<tr><th>Param</th><th>Type</th><th>Description</th></tr>
<tr><td>plan</td><td>query string</td><td>Subscription plan for limit calculation: <code>Free</code>, <code>Bronze</code>, <code>Silver</code>, <code>Gold</code>, <code>Enterprise</code></td></tr>
<tr><td>karma</td><td>query integer</td><td>Avatar karma score for multiplier calculation</td></tr>
</table>
<div class="sub-head">Response</div>
<pre>{
"dailyCallsUsed": 47,
"dailyCallLimit": 1500,
"remainingCallsToday": 1453,
"karmaMultiplier": 3.0,
"monthlySpendUSD": 0.042,
"dailyTokensUsed": 185000,
"periodMonth": "2026-08",
"periodDay": "2026-08-23"
}</pre>
</div>
</details>
</div>
<!-- ── HEALTH ────────────────────────────────────────────────────── -->
<div id="health" class="api-group">
<h2>Health</h2>
<details class="ep">
<summary class="ep-head">
<span class="method get">GET</span>
<span class="ep-path">/v1/health</span>
</summary>
<div class="ep-desc">Unauthenticated status check. Returns API version and UTC timestamp. Used by load balancers and uptime monitors.</div>
<div class="ep-body">
<div class="sub-head">Response</div>
<pre>{
"status": "ok",
"version": "2.0",
"timestamp": "2026-08-23T10:00:00.0000000Z"
}</pre>
</div>
</details>
</div>
<!-- ── OPENSERV ───────────────────────────────────────────────────── -->
<div id="openserv-models" class="api-group">
<h2>OpenServ</h2>
<details class="ep">
<summary class="ep-head">
<span class="method get">GET</span>
<span class="ep-path">/v1/openserv/models</span>
</summary>
<div class="ep-desc">Returns all WEB6 models in OpenServ-compatible format. Use this when connecting WEB6 as an OpenServ AI provider — OpenServ fetches this endpoint to populate its model selector.</div>
<div class="ep-body">
<div class="sub-head">Response</div>
<pre>[
{
"id": "oasis-web6/gpt-4o",
"name": "GPT-4o via WEB6",
"provider": "openai",
"contextWindow": 128000,
"capabilities": ["chat", "tools", "vision"]
},
...
]</pre>
</div>
</details>
</div>
<!-- ── ORCHESTRATORS ────────────────────────────────────────────────── -->
<div id="orchestrate-crewai" class="api-group">
<h2>Orchestrators</h2>
<p style="color:var(--dim);font-size:15px;margin-bottom:20px">Route multi-agent orchestration frameworks through WEB6. Each endpoint translates a framework-native payload into WEB6 completions and returns results in the originating framework's expected shape — no framework SDK required.</p>
<details class="ep">
<summary class="ep-head">
<span class="method post">POST</span>
<span class="ep-path">/v1/orchestrate/crewai</span>
</summary>
<div class="ep-desc">Dispatches a CrewAI-style crew definition. WEB6 maps each agent's role to the best provider for that capability tier and runs tasks in the specified process order.</div>
<div class="ep-body">
<table class="field-table">
<tr><th>Field</th><th>Type</th><th>Description</th></tr>
<tr><td>tasks<span class="req-label">required</span></td><td>array</td><td>Array of task objects with <code>id</code>, <code>agent</code>, <code>description</code>, <code>expected_output</code></td></tr>
<tr><td>process</td><td>string</td><td><code>sequential</code> (default) or <code>hierarchical</code></td></tr>
<tr><td>provider</td><td>string</td><td>Force all agents to a specific WEB6 provider (default: <code>auto</code>)</td></tr>
</table>
<div class="sub-head">Example</div>
<pre>{
"process": "sequential",
"tasks": [
{
"id": "research",
"agent": "Researcher",
"description": "Find the top 3 OASIS providers for video generation",
"expected_output": "A ranked list with reasons"
},
{
"id": "write",
"agent": "Writer",
"description": "Turn the research findings into a blog section",
"expected_output": "200-word blog paragraph"
}
]
}</pre>
</div>
</details>
<details id="orchestrate-autogen" class="ep">
<summary class="ep-head">
<span class="method post">POST</span>
<span class="ep-path">/v1/orchestrate/autogen</span>
</summary>
<div class="ep-desc">Accepts a Microsoft AutoGen conversation initiation payload. Routes the <code>initial_message</code> through WEB6 and returns a reply in AutoGen's expected assistant-message shape.</div>
<div class="ep-body">
<table class="field-table">
<tr><th>Field</th><th>Type</th><th>Description</th></tr>
<tr><td>initial_message<span class="req-label">required</span></td><td>string</td><td>The opening user message to start the AutoGen conversation</td></tr>
<tr><td>system_message</td><td>string</td><td>System/assistant persona to set for the WEB6 agent</td></tr>
<tr><td>provider</td><td>string</td><td>WEB6 provider to use (default: <code>auto</code>)</td></tr>
<tr><td>model</td><td>string</td><td>Model ID override (default: <code>auto</code>)</td></tr>
<tr><td>max_rounds</td><td>integer</td><td>Maximum conversation rounds (default: 10)</td></tr>
</table>
</div>
</details>
<details id="orchestrate-langgraph" class="ep">
<summary class="ep-head">
<span class="method post">POST</span>
<span class="ep-path">/v1/orchestrate/langgraph</span>
</summary>
<div class="ep-desc">Receives a LangGraph node invocation — the current graph state plus the node to execute. Runs the node's LLM step via WEB6 and returns the updated state for the next graph edge.</div>
<div class="ep-body">
<table class="field-table">
<tr><th>Field</th><th>Type</th><th>Description</th></tr>
<tr><td>node_name<span class="req-label">required</span></td><td>string</td><td>The LangGraph node identifier to execute</td></tr>
<tr><td>state</td><td>object</td><td>Current graph state (key-value pairs, passed through and augmented)</td></tr>
<tr><td>messages</td><td>array</td><td>Message history to pass to the LLM for this node</td></tr>
<tr><td>next_node</td><td>string</td><td>Next node to route to (returned in response for the graph executor)</td></tr>
<tr><td>provider</td><td>string</td><td>WEB6 provider (default: <code>auto</code>)</td></tr>
</table>
<div class="sub-head">Response</div>
<pre>{
"isError": false,
"result": {
"state": {
"research_output": "...",
"__node__": "research",
"__timestamp__": "2026-08-23T10:00:00Z"
},
"nextNode": "summarise"
}
}</pre>
</div>
</details>
</div>
<!-- ── MCP ───────────────────────────────────────────────────────────── -->
<div id="mcp-overview" class="api-group">
<h2>MCP — Model Context Protocol</h2>
<p style="color:var(--dim);font-size:15px;margin-bottom:20px">WEB6 exposes its full capability surface as an MCP server, making every tool callable directly from Claude Code, claude.ai connectors, OpenAI Responses API, and any other MCP-compatible client — with zero HTTP configuration required.</p>
<div class="base-url" style="margin-bottom:16px">
<span>MCP ENDPOINT</span>
https://api.web6.oasisomniverse.one/mcp
</div>
<div class="base-url" style="border-color:rgba(253,216,53,.2);margin-bottom:24px">
<span>DISCOVERY DOCUMENTS</span>
https://api.web6.oasisomniverse.one/.well-known/mcp.json<br>
https://api.web6.oasisomniverse.one/.well-known/agent.json
</div>
<p style="color:var(--dim);font-size:15px;margin-bottom:10px">Connect in Claude Code:</p>
<pre>claude mcp add oasis-web6 \
--transport http \
--url https://api.web6.oasisomniverse.one/mcp \
--header "Authorization: Bearer <your-jwt>"</pre>
<p style="color:var(--dim);font-size:15px;margin:16px 0 10px">Or in <code>~/.claude/claude_desktop_config.json</code>:</p>
<pre>{
"mcpServers": {
"oasis-web6": {
"transport": "http",
"url": "https://api.web6.oasisomniverse.one/mcp",
"headers": { "Authorization": "Bearer <your-jwt>" }
}
}
}</pre>
</div>
<div id="mcp-tools" class="api-group">
<h2>MCP Tool Reference</h2>
<p style="color:var(--dim);font-size:15px;margin-bottom:20px">All 35+ tools exposed by the MCP server. Each tool is callable from any MCP client — Claude Code, claude.ai, OpenAI, or your own agent.</p>
<table class="field-table" style="background:var(--bg-card);border:1px solid rgba(255,255,255,.07);border-radius:10px;overflow:hidden">
<tr><th>Tool name</th><th>What it does</th></tr>
<tr><td>web6_complete</td><td>Chat completion across 20+ providers (auto-routes)</td></tr>
<tr><td>web6_fahrn_solve</td><td>Full FAHRN pipeline — classify, dispatch, BRAID, EMA, telemetry in one call</td></tr>
<tr><td>web6_fahrn_dispatch</td><td>Direct FAHRN dispatch with explicit mode (Serial/Parallel/Decomposed)</td></tr>
<tr><td>web6_fahrn_register_agent</td><td>Register a new reasoning agent with FAHRN</td></tr>
<tr><td>web6_fahrn_get_agents</td><td>List all FAHRN agents with live composite scoring</td></tr>
<tr><td>web6_fahrn_seed_openserv_agents</td><td>Seed FAHRN with one agent per OpenServ SERV model</td></tr>
<tr><td>web6_fahrn_get_agent_skill</td><td>Get the evolved best_skill.md for an agent + task category</td></tr>
<tr><td>web6_fahrn_evolve_agent_skill</td><td>Run one SkillOpt epoch — evolve the agent's skill document</td></tr>
<tr><td>web6_generate_image</td><td>Image generation via StabilityAI or OpenAI DALL·E</td></tr>
<tr><td>web6_embed</td><td>Generate embeddings via OpenAI, Cohere, or HuggingFace</td></tr>
<tr><td>web6_braid_find_graph</td><td>Look up shared BRAID reasoning graph for a task type</td></tr>
<tr><td>web6_braid_save_graph</td><td>Store a Mermaid reasoning graph in the BRAID library</td></tr>
<tr><td>web6_braid_record_outcome</td><td>Feed solver outcome back into graph quality metadata</td></tr>
<tr><td>web6_memory_get_earth_holon</td><td>Get/create the planetary Earth holon (top of fractal hierarchy)</td></tr>
<tr><td>web6_memory_get_or_create_holon</td><td>Find or create a holon at any level in the fractal hierarchy</td></tr>
<tr><td>web6_memory_set_membrane_rule</td><td>Set consent-governed upward-propagation rule on a holon</td></tr>
<tr><td>web6_memory_record</td><td>Record a memory item at a holon</td></tr>
<tr><td>web6_memory_propagate</td><td>Propagate permitted memories up one hop to parent holon</td></tr>
<tr><td>web6_memory_propagate_up</td><td>Propagate up N hops (or to Earth root)</td></tr>
<tr><td>web6_memory_search</td><td>Semantic search over memory items in a holon</td></tr>
<tr><td>web6_memory_external_search</td><td>Search Mem0, Zep, Letta, LangMem, Graphiti, Qdrant, Weaviate external providers</td></tr>
<tr><td>web6_memory_external_add</td><td>Add a memory to an external provider (Mem0, Zep, etc.)</td></tr>
<tr><td>web6_memory_external_list_providers</td><td>List registered external memory providers</td></tr>
<tr><td>web6_orchestrator_register</td><td>Register an external agent/orchestrator endpoint</td></tr>
<tr><td>web6_orchestrator_list</td><td>List all registered orchestrator adapters</td></tr>
<tr><td>web6_orchestrator_invoke</td><td>Invoke a registered orchestrator (MCP/A2A/LangChain/AutoGen/CrewAI)</td></tr>
<tr><td>web6_orchestrate_crewai</td><td>Dispatch a CrewAI task list through WEB6 routing</td></tr>
<tr><td>web6_orchestrate_autogen</td><td>Route an AutoGen conversation initiation through WEB6</td></tr>
<tr><td>web6_orchestrate_langgraph</td><td>Execute a LangGraph node via WEB6, return updated state</td></tr>
<tr><td>web6_list_models</td><td>Browse the full model catalogue, filter by plan or capability</td></tr>
<tr><td>web6_get_model</td><td>Full detail for a single model by ID</td></tr>
<tr><td>web6_list_providers</td><td>All 20+ providers with tier, endpoints, and status</td></tr>
<tr><td>web6_estimate_cost</td><td>USD cost estimate before executing a call</td></tr>
<tr><td>web6_get_usage</td><td>Avatar's daily call count, limit, and monthly spend</td></tr>
<tr><td>web6_get_avatar_context</td><td>Rich avatar context block — karma, quests, world memberships</td></tr>
<tr><td>web6_list_openserv_models</td><td>List every model in the OpenServ SERV catalog</td></tr>
<tr><td>web6_ml_classify_task</td><td>In-process ML.NET task classification (zero latency)</td></tr>
<tr><td>web6_ml_sentiment</td><td>In-process ML.NET sentiment analysis (zero latency)</td></tr>
<tr><td>web6_health</td><td>API status, version, and UTC timestamp (unauthenticated)</td></tr>
</table>
</div>