-
Notifications
You must be signed in to change notification settings - Fork 0
Expand file tree
/
Copy pathconfig.yaml
More file actions
2206 lines (2170 loc) · 58.1 KB
/
config.yaml
File metadata and controls
2206 lines (2170 loc) · 58.1 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
auto_update:
allow_major: false
apply_command: faigate-update
enabled: false
maintenance_window:
days:
- sat
- sun
enabled: false
end_hour: 5
start_hour: 2
timezone: UTC
max_unhealthy_providers: 0
min_release_age_hours: 0
provider_scope:
allow_providers: []
deny_providers:
- openrouter-fallback
require_healthy_providers: true
rollout_ring: early
verification:
command: faigate-health
enabled: false
rollback_command: ''
timeout_seconds: 30
metadata:
enabled: true
on_startup: false
refresh_interval_hours: 24
timeout_seconds: 10
client_profiles:
default: generic
enabled: true
presets:
- openclaw
- n8n
- cli
profiles:
cli:
routing_mode: auto
generic: {}
local-only:
capability_values:
local: true
n8n:
prefer_tiers:
- cheap
- default
routing_mode: eco
antigravity:
prefer_providers:
- gemini-flash-lite
- gemini-flash
- gemini-pro-high
prefer_tiers:
- cheap
- default
routing_mode: eco
claude:
routing_mode: coding-auto
codex:
routing_mode: coding-auto
deepseek-cli:
prefer_providers:
- deepseek-v4-flash
- deepseek-v4-pro
- anthropic-haiku
prefer_tiers:
- default
- reasoning
routing_mode: auto
gemini-cli:
prefer_providers:
- gemini-flash
- gemini-flash-lite
- gemini-pro-high
prefer_tiers:
- cheap
- default
- mid
routing_mode: auto
kilocode:
routing_mode: coding-fast
openclaw:
routing_mode: coding-auto
opencode:
# The chatgpt.com Codex backend gates `gpt-5-codex` to Pro accounts only,
# so the auto-router must not pick codex providers as a fallback for the
# opencode client. Explicit invocation via model_shortcuts still works.
deny_providers:
- openai-codex
- openai-codex-mini
- openai-codex-spark
- openai-codex-high
- openai-codex-xhigh
- openai-codex-low
- openai-codex-5.4-low
- openai-codex-5.4-medium
- openai-codex-5.4-high
- openai-codex-5.4-xhigh
routing_mode: coding-auto
# ── opencode named profiles (selectable as model in opencode UI) ─────────
coding:
deny_providers:
- openai-codex
- openai-codex-mini
- openai-codex-spark
- openai-codex-high
- openai-codex-xhigh
- openai-codex-low
- openai-codex-5.4-low
- openai-codex-5.4-medium
- openai-codex-5.4-high
- openai-codex-5.4-xhigh
routing_mode: coding-auto
coding-free:
prefer_providers:
- pollinations
- groq
- cerebras
- kilocode
- blackbox-free
- gemini-flash-lite
prefer_tiers:
- free
- cheap
routing_mode: free
research:
routing_mode: premium
rules:
- match:
any:
- header_contains:
x-faigate-client:
- antigravity
profile: antigravity
- match:
any:
- header_contains:
x-faigate-client:
- claude
- claude-code
profile: claude
- match:
any:
- header_contains:
x-faigate-client:
- codex
profile: codex
- match:
any:
- header_contains:
x-faigate-client:
- deepseek-cli
profile: deepseek-cli
- match:
any:
- header_contains:
x-faigate-client:
- gemini-cli
profile: gemini-cli
- match:
any:
- header_contains:
x-faigate-client:
- kilocode
- kilo
profile: kilocode
- match:
any:
- header_contains:
x-faigate-client:
- opencode
profile: opencode
- match:
any:
- header_contains:
x-faigate-client:
- coding
- coding-auto
profile: coding
- match:
any:
- header_contains:
x-faigate-client:
- coding-free
- free
profile: coding-free
- match:
any:
- header_contains:
x-faigate-client:
- research
profile: research
fallback_chain:
- deepseek-v4-flash
- anthropic-haiku
- gemini-flash
- deepseek-v4-pro
- anthropic-sonnet
- gemini-pro-high
- openai-gpt4o
- openrouter-fallback
- anthropic-claude
- kilocode
- blackbox-free
health:
check_interval_seconds: 300
consecutive_failures_before_skip: 3
recovery_check_interval_seconds: 60
timeout_seconds: 10
heuristic_rules:
enabled: true
rules:
- match:
message_keywords:
any_of:
- prove
- beweis
- beweise
- theorem
- integral
- derivative
- equation
- gleichung
- induction
- induktion
- \boxed
- \frac
- \sum
- \int
- latex
- step by step
- "schritt f\xFCr schritt"
- warum
- why does
- explain why
- "erkl\xE4re warum"
- "\u8BC1\u660E"
- "\u5B9A\u7406"
- "\u8A3C\u660E"
- "\u0434\u043E\u043A\u0430\u0437\u0430\u0442\u044C"
min_matches: 2
name: math-reasoning
route_to: deepseek-v4-pro
- match:
message_keywords:
any_of:
- refactor
- debug
- architecture
- design pattern
- race condition
- memory leak
- optimize
- complexity
- security vulnerability
- code review
- performance bottleneck
- type error
- deadlock
min_matches: 2
name: complex-code
route_to: deepseek-v4-pro
- match:
message_keywords:
any_of:
- what is
- was ist
- define
- definiere
- translate
- "\xFCbersetze"
- hi
- hello
- hallo
- thanks
- danke
- 'yes'
- ja
- 'no'
- nein
- "\u0447\u0442\u043E \u0442\u0430\u043A\u043E\u0435"
- "\u4F60\u597D"
- "\u3053\u3093\u306B\u3061\u306F"
min_matches: 1
name: simple-query
route_to: gemini-flash-lite
- match:
has_tools: true
name: tool-use
route_to: deepseek-v4-flash
- match:
estimated_tokens:
less_than: 100
name: short-message
route_to: deepseek-v4-flash
- match:
estimated_tokens:
greater_than: 50000
name: long-context
route_to: deepseek-v4-flash
- match:
fallthrough: true
name: general-default
route_to: deepseek-v4-flash
llm_classifier:
category_routing:
AGENT: deepseek-v4-flash
CODING: deepseek-v4-flash
REASONING: deepseek-v4-pro
SIMPLE: gemini-flash-lite
classifier_provider: gemini-flash-lite
enabled: false
fallback_on_timeout: deepseek-v4-flash
max_classify_tokens: 50
prompt: 'Classify this task into exactly one category. Reply with ONLY the category
name.
Categories:
- REASONING: math proofs, logic puzzles, complex analysis, debugging
- CODING: code generation, refactoring, architecture decisions
- SIMPLE: greetings, status checks, short lookups, translations
- AGENT: tool use, file operations, search, API calls
User message: {last_user_message}
Category:
'
timeout_ms: 3000
metrics:
db_path: faigate.db
enabled: true
log_requests: false
log_routing_decisions: false
model_shortcuts:
enabled: false
shortcuts:
anthropic-claude:
aliases:
- opus
- claude-opus
description: Anthropic Claude Opus 4.6 (premium)
target: anthropic-claude
anthropic-sonnet:
aliases:
- sonnet
- claude-sonnet
- claude
description: Anthropic Claude Sonnet 4.6 (balanced)
target: anthropic-sonnet
anthropic-haiku:
aliases:
- haiku
- claude-haiku
description: Anthropic Claude Haiku 3.5 (fast/cheap)
target: anthropic-haiku
gemini-pro:
aliases:
- pro
- gemini-pro-high
description: Gemini 3.1 Pro (High) (quality)
target: gemini-pro-high
gemini-pro-low:
aliases:
- pro-low
description: Gemini 3.1 Pro (Low) (balanced)
target: gemini-pro-low
blackbox-free:
aliases:
- blackbox
- bb
description: BLACKBOX budget burst route (legacy id)
target: blackbox-free
deepseek-v4-flash:
aliases:
- chat
- ds
description: DeepSeek Chat
target: deepseek-v4-flash
deepseek-v4-pro:
aliases: []
description: DeepSeek reasoning path
target: deepseek-v4-pro
flash:
aliases:
- gemini
description: Gemini 3 Flash
target: gemini-flash
gemini-flash:
aliases: []
description: Gemini Flash
target: gemini-flash
kilocode:
aliases:
- kilo
- glm5
description: Kilo free-tier gateway path
target: kilocode
openai-gpt4o:
aliases:
- gpt4o
- gpt-4o
description: OpenAI GPT-4o
target: openai-gpt4o
openai-images:
aliases:
- img
- image
- gpt-image
description: OpenAI image generation and editing
target: openai-images
r1:
aliases:
- reasoner
- think
description: DeepSeek reasoning path
target: deepseek-v4-pro
prompt_caching:
stabilize_prefix: false
track_metrics: true
provider_catalog_check:
enabled: true
max_catalog_age_days: 30
warn_on_model_drift: true
warn_on_unofficial_sources: true
warn_on_untracked: true
warn_on_volatile_offers: true
providers:
anthropic-haiku:
api_key: ${ANTHROPIC_API_KEY}
backend: anthropic-compat
base_url: ${ANTHROPIC_BASE_URL:-https://api.anthropic.com/v1}
capabilities:
cost_tier: cheap
latency_tier: fast
streaming: true
lane:
benchmark_cluster: balanced-coding
canonical_model: anthropic/haiku-3.5
cluster: fast-workhorse
context_strength: mid
degrade_to:
- deepseek/v4-flash
- google/gemini-flash
family: anthropic
freshness_hint: benchmark and cost assumptions were reviewed recently
freshness_status: fresh
last_reviewed: '2026-03-24'
name: fast
quality_tier: mid
reasoning_strength: mid
review_age_days: 0
route_type: direct
same_model_group: anthropic/haiku-3.5
tool_strength: medium
max_tokens: 8096
model: claude-haiku-3-5
pricing:
cache_read: 0.08
input: 0.8
output: 4.0
tier: default
timeout:
connect_s: 10
read_s: 45
anthropic-sonnet:
api_key: ${ANTHROPIC_API_KEY}
backend: anthropic-compat
base_url: ${ANTHROPIC_BASE_URL:-https://api.anthropic.com/v1}
capabilities:
cost_tier: standard
latency_tier: balanced
reasoning: true
streaming: true
lane:
benchmark_cluster: quality-coding
canonical_model: anthropic/sonnet-4.6
cluster: quality-workhorse
context_strength: high
degrade_to:
- anthropic/haiku-3.5
- deepseek/v4-flash
- google/gemini-flash
family: anthropic
freshness_hint: benchmark and cost assumptions were reviewed recently
freshness_status: fresh
last_reviewed: '2026-03-24'
name: balanced
quality_tier: high
reasoning_strength: high
review_age_days: 0
route_type: direct
same_model_group: anthropic/sonnet-4.6
tool_strength: high
max_tokens: 16000
model: claude-sonnet-4-6
pricing:
cache_read: 0.3
input: 3.0
output: 15.0
tier: mid
timeout:
connect_s: 10
read_s: 90
anthropic-claude:
api_key: ${ANTHROPIC_API_KEY}
backend: anthropic-compat
base_url: ${ANTHROPIC_BASE_URL:-https://api.anthropic.com/v1}
capabilities:
cost_tier: premium
latency_tier: quality
reasoning: true
lane:
benchmark_cluster: quality-coding
canonical_model: anthropic/opus-4.6
cluster: elite-reasoning
context_strength: high
degrade_to:
- anthropic/sonnet-4.6
- openai/gpt-4o
- deepseek/v4-pro
family: anthropic
freshness_hint: benchmark and cost assumptions were reviewed recently
freshness_status: fresh
last_reviewed: '2026-03-22'
name: quality
quality_tier: premium
reasoning_strength: high
review_age_days: 1
route_type: direct
same_model_group: anthropic/opus-4.6
tool_strength: medium
max_tokens: 64000
model: claude-opus-4-6
tier: mid
timeout:
connect_s: 10
read_s: 120
blackbox-free:
api_key: ${BLACKBOX_API_KEY}
backend: openai-compat
base_url: ${BLACKBOX_BASE_URL:-https://api.blackbox.ai}
capabilities:
cost_tier: cheap
latency_tier: fast
lane:
benchmark_cluster: budget-chat
canonical_model: aggregator/blackbox-grok-code-fast
cluster: budget-general
context_strength: mid
degrade_to:
- aggregator/kilo-glm5-free
- google/gemini-flash-lite
family: blackbox
freshness_hint: benchmark and cost assumptions were reviewed recently
freshness_status: fresh
last_reviewed: '2026-03-22'
name: burst
quality_tier: budget
reasoning_strength: mid
review_age_days: 1
route_type: aggregator
same_model_group: aggregator/blackbox-grok-code-fast
tool_strength: mid
max_tokens: 8000
model: blackboxai/x-ai/grok-code-fast-1
tier: fallback
timeout:
connect_s: 10
read_s: 60
deepseek-v4-flash:
api_key: ${DEEPSEEK_API_KEY}
backend: openai-compat
base_url: ${DEEPSEEK_BASE_URL:-https://api.deepseek.com/v1}
capabilities:
cost_tier: cheap
latency_tier: fast
streaming: true
lane:
benchmark_cluster: balanced-coding
canonical_model: deepseek/v4-flash
cluster: balanced-workhorse
context_strength: high
degrade_to:
- google/gemini-flash
- aggregator/openrouter-auto
family: deepseek
freshness_hint: DeepSeek V4 (Apr 2026) — replaces V3.2 chat lane, 1M ctx
freshness_status: fresh
last_reviewed: '2026-04-26'
name: workhorse
quality_tier: mid
reasoning_strength: mid
review_age_days: 0
route_type: direct
same_model_group: deepseek/v4-flash
tool_strength: medium
max_tokens: 64000
model: deepseek-v4-flash
pricing:
cache_read: 0.028
input: 0.14
output: 0.28
tier: default
timeout:
connect_s: 10
read_s: 60
deepseek-v4-pro:
api_key: ${DEEPSEEK_API_KEY}
backend: openai-compat
base_url: ${DEEPSEEK_BASE_URL:-https://api.deepseek.com/v1}
capabilities:
cost_tier: standard
latency_tier: balanced
reasoning: true
streaming: true
lane:
benchmark_cluster: reasoning-coding
canonical_model: deepseek/v4-pro
cluster: elite-reasoning
context_strength: high
degrade_to:
- deepseek/v4-flash
- google/gemini-pro-high
family: deepseek
freshness_hint: DeepSeek V4 Pro (Apr 2026) — replaces V3.2 reasoner, 1M ctx, unified reasoning
freshness_status: fresh
last_reviewed: '2026-04-26'
name: reasoning
quality_tier: premium
reasoning_strength: high
review_age_days: 0
route_type: direct
same_model_group: deepseek/v4-pro
tool_strength: high
max_tokens: 64000
model: deepseek-v4-pro
pricing:
cache_read: 0.145
input: 1.74
output: 3.48
tier: reasoning
timeout:
connect_s: 10
read_s: 120
gemini-flash:
api_key: ${GEMINI_API_KEY}
backend: google-genai
base_url: ${GEMINI_BASE_URL:-https://generativelanguage.googleapis.com/v1beta}
capabilities:
cost_tier: cheap
latency_tier: fast
lane:
benchmark_cluster: fast-general
canonical_model: google/gemini-flash
cluster: fast-workhorse
context_strength: mid
degrade_to:
- google/gemini-flash-lite
- deepseek/v4-flash
family: google
freshness_hint: benchmark and cost assumptions were reviewed recently
freshness_status: fresh
last_reviewed: '2026-03-22'
name: fast
quality_tier: mid
reasoning_strength: mid
review_age_days: 1
route_type: direct
same_model_group: google/gemini-flash
tool_strength: medium
max_tokens: 8000
model: gemini-3-flash
tier: mid
timeout:
connect_s: 10
read_s: 60
gemini-flash-lite:
api_key: ${GEMINI_API_KEY}
backend: google-genai
base_url: ${GEMINI_BASE_URL:-https://generativelanguage.googleapis.com/v1beta}
capabilities:
cost_tier: cheap
latency_tier: fast
lane:
benchmark_cluster: budget-chat
canonical_model: google/gemini-flash-lite
cluster: budget-general
context_strength: mid
degrade_to:
- aggregator/kilo-glm5-free
- aggregator/blackbox-grok-code-fast
family: google
freshness_hint: benchmark and cost assumptions were reviewed recently
freshness_status: fresh
last_reviewed: '2026-03-24'
name: cheap
quality_tier: budget
reasoning_strength: low
review_age_days: 0
route_type: direct
same_model_group: google/gemini-flash-lite
tool_strength: low
max_tokens: 8000
model: gemini-3-flash-lite
pricing:
cache_read: 0.02
input: 0.075
output: 0.3
tier: cheap
timeout:
connect_s: 10
read_s: 30
gemini-pro-high:
api_key: ${GEMINI_API_KEY}
backend: google-genai
base_url: ${GEMINI_BASE_URL:-https://generativelanguage.googleapis.com/v1beta}
capabilities:
cost_tier: premium
latency_tier: balanced
reasoning: true
lane:
benchmark_cluster: quality-coding
canonical_model: google/gemini-pro-high
cluster: quality-workhorse
context_strength: high
degrade_to:
- google/gemini-pro-low
- google/gemini-flash
- deepseek/v4-pro
family: google
freshness_hint: benchmark and cost assumptions were reviewed recently
freshness_status: fresh
last_reviewed: '2026-03-29'
name: pro-high
quality_tier: high
reasoning_strength: high
review_age_days: 0
route_type: direct
same_model_group: google/gemini-pro-high
tool_strength: high
max_tokens: 65536
model: gemini-3.1-pro
pricing:
cache_read: 0.31
input: 1.25
output: 10.0
tier: mid
timeout:
connect_s: 10
read_s: 120
gemini-pro-low:
api_key: ${GEMINI_API_KEY}
backend: google-genai
base_url: ${GEMINI_BASE_URL:-https://generativelanguage.googleapis.com/v1beta}
capabilities:
cost_tier: premium
latency_tier: balanced
reasoning: true
lane:
benchmark_cluster: balanced-coding
canonical_model: google/gemini-pro-low
cluster: balanced-workhorse
context_strength: high
degrade_to:
- google/gemini-flash
- deepseek/v4-flash
family: google
freshness_hint: benchmark and cost assumptions were reviewed recently
freshness_status: fresh
last_reviewed: '2026-03-29'
name: pro-low
quality_tier: mid
reasoning_strength: mid
review_age_days: 0
route_type: direct
same_model_group: google/gemini-pro-low
tool_strength: medium
max_tokens: 65536
model: gemini-3.1-pro
pricing:
cache_read: 0.20
input: 0.80
output: 4.0
tier: mid
timeout:
connect_s: 10
read_s: 90
kilocode:
api_key: ${KILOCODE_API_KEY}
backend: openai-compat
base_url: ${KILOCODE_BASE_URL:-https://api.kilo.ai/api/gateway}
capabilities:
cost_tier: free
latency_tier: balanced
lane:
benchmark_cluster: free-coding
canonical_model: aggregator/kilo-glm5-free
cluster: budget-general
context_strength: mid
degrade_to:
- aggregator/blackbox-grok-code-fast
- google/gemini-flash-lite
family: kilo
freshness_hint: benchmark and cost assumptions were reviewed recently
freshness_status: fresh
last_reviewed: '2026-03-22'
name: free
quality_tier: free
reasoning_strength: mid
review_age_days: 1
route_type: aggregator
same_model_group: aggregator/kilo-glm5-free
tool_strength: low
max_tokens: 8000
model: z-ai/glm-5:free
tier: fallback
timeout:
connect_s: 10
read_s: 60
kilo-auto/frontier:
api_key: ${KILOCODE_API_KEY}
backend: openai-compat
base_url: ${KILOCODE_BASE_URL:-https://api.kilo.ai/api/gateway}
capabilities:
cost_tier: premium
latency_tier: balanced
max_tokens: 32000
model: kilo-auto/frontier
tier: premium
timeout:
connect_s: 10
read_s: 120
kilo-auto/balanced:
api_key: ${KILOCODE_API_KEY}
backend: openai-compat
base_url: ${KILOCODE_BASE_URL:-https://api.kilo.ai/api/gateway}
capabilities:
cost_tier: mid
latency_tier: balanced
max_tokens: 16000
model: kilo-auto/balanced
tier: mid
timeout:
connect_s: 10
read_s: 90
kilo-auto/free:
api_key: ${KILOCODE_API_KEY}
backend: openai-compat
base_url: ${KILOCODE_BASE_URL:-https://api.kilo.ai/api/gateway}
capabilities:
cost_tier: free
latency_tier: balanced
max_tokens: 8000
model: kilo-auto/free
tier: fallback
timeout:
connect_s: 10
read_s: 60
kilo-auto/small:
api_key: ${KILOCODE_API_KEY}
backend: openai-compat
base_url: ${KILOCODE_BASE_URL:-https://api.kilo.ai/api/gateway}
capabilities:
cost_tier: cheap
latency_tier: fast
max_tokens: 8000
model: kilo-auto/small
tier: cheap
timeout:
connect_s: 10
read_s: 60
openai-gpt4o:
api_key: ${OPENAI_API_KEY}
backend: openai-compat
base_url: ${OPENAI_BASE_URL:-https://api.openai.com/v1}
capabilities:
cost_tier: premium
latency_tier: balanced
lane:
benchmark_cluster: quality-coding
canonical_model: openai/gpt-4o
cluster: quality-workhorse
context_strength: high
degrade_to:
- openai/gpt-4o-mini
- google/gemini-pro-high
family: openai
freshness_hint: benchmark and cost assumptions were reviewed recently
freshness_status: fresh
last_reviewed: '2026-03-22'
name: balanced
quality_tier: high
reasoning_strength: high
review_age_days: 1
route_type: direct
same_model_group: openai/gpt-4o
tool_strength: high
max_tokens: 8192
model: gpt-4o
tier: mid
timeout:
connect_s: 10
read_s: 60
openai-images:
api_key: ${OPENAI_API_KEY}
backend: openai-compat
base_url: ${OPENAI_BASE_URL:-https://api.openai.com/v1}
capabilities:
cost_tier: premium
image_editing: true
contract: image-provider
image:
max_outputs: 4
max_side_px: 2048
policy_tags:
- quality
- editing
- batch
supported_sizes:
- 1024x1024
- 1536x1024
- 1024x1536
model: gpt-image-1
tier: specialty
openrouter-fallback:
api_key: ${OPENROUTER_API_KEY}
backend: openai-compat
base_url: ${OPENROUTER_BASE_URL:-https://openrouter.ai/api/v1}
capabilities:
cost_tier: marketplace
latency_tier: balanced
streaming: true
lane:
benchmark_cluster: marketplace-general
canonical_model: aggregator/openrouter-auto
cluster: aggregator-fallback
context_strength: variable
degrade_to:
- aggregator/kilo-glm5-free
- aggregator/blackbox-grok-code-fast
family: openrouter
freshness_hint: benchmark and cost assumptions were reviewed recently
freshness_status: fresh
last_reviewed: '2026-03-22'
name: router
quality_tier: variable
reasoning_strength: variable
review_age_days: 1
route_type: aggregator
same_model_group: aggregator/openrouter-auto
tool_strength: variable
max_tokens: 8000
model: openrouter/auto
tier: fallback
timeout:
connect_s: 10
read_s: 90
# ── Free Providers (OmniRoute-inspired zero-cost fallback stack) ────────────
pollinations:
api_key: ""
backend: openai-compat
base_url: https://text.pollinations.ai/openai
capabilities:
cost_tier: free
latency_tier: balanced
streaming: true
lane:
benchmark_cluster: budget-chat
canonical_model: aggregator/pollinations-openai
cluster: budget-general
context_strength: mid
degrade_to: []
family: pollinations
freshness_hint: free no-key provider — polling models endpoint for availability
freshness_status: fresh
last_reviewed: '2026-05-04'
name: free
quality_tier: free
reasoning_strength: variable
review_age_days: 0
route_type: aggregator
same_model_group: aggregator/pollinations-openai
tool_strength: low
max_tokens: 8000
model: openai
tier: free
timeout:
connect_s: 10
read_s: 60
transport: