Models

Everything the router can choose from.

88 targets of 7 kinds run on this deployment - models, agents, skills, tools and a human queue. 82 of them answer requests here; every one can be chosen, quoted and put in a plan. Each model shows the exact version it runs as; traffic is the last 7 days.

targets: 88
executable: 82
requests · 7d: 885

Vendors behind this deployment

HSB

Recommended per use case

Live quotes of representative prompts against this catalogue, refreshed every minute. Quote your own prompt on the cost estimator.

Everyday assistant

85 candidates

Small fast model

GPT-4.1 Nanollm

per request: $0.00016
quality: 0.66
latency: 300.0 ms

domain fit 50% · action fit 50% · complexity fit 100%

88 of 88

Target	Kind	Model	Price / 1M	Context	Latency	Tokens 7d	Quality
Small fast modelllm-small	llmexec	GPT-4.1 NanoOpenAI via azure/llm-small	$0.20	-	4.74 s	460.3K+304%	0.55
Small writing modelwriter-small	llmexec	ollama-qwen3-5-4b/qwen3.5:4b	$0.05	-	2.7 min	455K+48%	0.60
Document and image reader (OCR)vision-ocr	llmexec	ollama-glm-ocr/glm-ocr	$0.10	256K	7.6 min	425.7Knew	0.74
On-prem private modelllm-onprem	llmexec	ollama-qwen3-5-4b/qwen3.5:4b	$1.00	-	3.3 min	105.8K+>999%	0.70
Translation skillskill-translate	skillexec	ollama-translategemma-4b/translategemma:4b	$0.50	-	35.1 s	5.9K+>999%	0.85
Qwen3.5-9B (ollama-qwen3-embedding-4b)qwen/qwen3.5-9b@ollama-qwen3-embedding-4b	llmexec	Qwen3.5-9BQwen via ollama-qwen3-embedding-4b/qwen3.5:9b	$0.11	262.1K	17 min	2.9Knew	0.50
Mid-tier modelllm-mid	llmexec	GPT-4.1 MiniOpenAI via azure/llm-mid	$3.00	-	7.95 s	2.8K+>999%	0.75
Code modelcoder-small	llmexec	GLM 4.7 FlashZ.ai via ollama-glm-4-7-flash/glm-4.7-flash	$0.10	32K	2.7 min	1.7K-84%	0.66
gpt-oss-20b (ollama)openai/gpt-oss-20b@ollama	llmexec	gpt-oss-20bOpenAI via ollama/gpt-oss:20b	$0.06	131.1K	2.9 min	229new	0.36
Embedding modelembed-small	llmexec	ollama-qwen3-embedding-4b/qwen3-embedding:4b	$0.02	-	35.2 s	83-52%	0.70
Coding agentcoding-agent	agentexec	GLM 4.7 FlashZ.ai via ollama-glm-4-7-flash/glm-4.7-flash	$8.00	-	52.9 ms	11new	0.85
gpt-oss-20b (self-hosted)gpt-oss	llmexec	gpt-oss-20bOpenAI via ollama-gpt-oss-20b/gpt-oss:20b	$0.40	128K	23 min	2-100%	0.78
Frontier reasoning modelllm-frontier	llmexec	GPT-4.1OpenAI via azure/llm-frontier	$15	200K	38.8 ms	2+100%	0.93
Qwen3.5-9B (ollama)qwen/qwen3.5-9b@ollama	llmexec	Qwen3.5-9BQwen via ollama/qwen3.5:9b	$0.11	262.1K	21 min	2new	0.50
HHuman escalation queuehuman-escalation	humanexec	human/queue	$500	-	170.3 ms	1new	0.90
GPT-5.6 Luna (azure)openai/gpt-5.6-luna@azure	llmexec	GPT-5.6 LunaOpenAI via azure/gpt-5.6-luna	$0.45	1.1M	543.3 ms	1new	0.54
GPT Audio Mini (azure)openai/gpt-audio-mini@azure	llmexec	GPT Audio MiniOpenAI via azure/gpt-audio-mini	$1.05	128K	3.07 s	1new	0.60
GPT-3.5 Turbo (older v0613) (azure)openai/gpt-3.5-turbo-0613@azure	llmexec	GPT-3.5 Turbo (older v0613)OpenAI via azure/gpt-35-turbo-0613	$1.25	4.1K	900.0 ms	0no traffic	0.60
GPT-3.5 Turbo 16k (azure)openai/gpt-3.5-turbo-16k@azure	llmexec	GPT-3.5 Turbo 16kOpenAI via azure/gpt-35-turbo-16k	$3.25	16.4K	900.0 ms	0no traffic	0.70
GPT-3.5 Turbo Instruct (azure)openai/gpt-3.5-turbo-instruct@azure	llmexec	GPT-3.5 Turbo InstructOpenAI via azure/gpt-35-turbo-instruct	$1.63	4.1K	900.0 ms	0no traffic	0.60
GPT-3.5 Turbo (azure)openai/gpt-3.5-turbo@azure	llmexec	GPT-3.5 TurboOpenAI via azure/gpt-35-turbo	$0.75	16.4K	900.0 ms	0no traffic	0.60
GPT-4.1 Mini (azure)openai/gpt-4.1-mini@azure	llmexec	GPT-4.1 MiniOpenAI via azure/gpt-4.1-mini	$0.70	1M	900.0 ms	0no traffic	0.50
GPT-4.1 Nano (azure)openai/gpt-4.1-nano@azure	llmexec	GPT-4.1 NanoOpenAI via azure/gpt-4.1-nano	$0.17	1M	900.0 ms	0no traffic	0.50
GPT-4.1 (azure)openai/gpt-4.1@azure	llmexec	GPT-4.1OpenAI via azure/gpt-4.1	$3.50	1M	900.0 ms	0no traffic	0.70
GPT-4 (azure)openai/gpt-4@azure	llmexec	GPT-4OpenAI via azure/gpt-4	$38	8.2K	900.0 ms	0no traffic	0.70
GPT-4o (2024-05-13) (azure)openai/gpt-4o-2024-05-13@azure	llmexec	GPT-4o (2024-05-13)OpenAI via azure/gpt-4o-2024-05-13	$7.50	128K	900.0 ms	0no traffic	0.70
GPT-4o (2024-08-06) (azure)openai/gpt-4o-2024-08-06@azure	llmexec	GPT-4o (2024-08-06)OpenAI via azure/gpt-4o-2024-08-06	$4.38	128K	900.0 ms	0no traffic	0.70
GPT-4o (2024-11-20) (azure)openai/gpt-4o-2024-11-20@azure	llmexec	GPT-4o (2024-11-20)OpenAI via azure/gpt-4o-2024-11-20	$4.38	128K	900.0 ms	0no traffic	0.70
GPT-4o-mini (2024-07-18) (azure)openai/gpt-4o-mini-2024-07-18@azure	llmexec	GPT-4o-mini (2024-07-18)OpenAI via azure/gpt-4o-mini-2024-07-18	$0.26	128K	900.0 ms	0no traffic	0.50
GPT-4o-mini (azure)openai/gpt-4o-mini@azure	llmexec	GPT-4o-miniOpenAI via azure/gpt-4o-mini	$0.26	128K	900.0 ms	0no traffic	0.50
GPT-4o (azure)openai/gpt-4o@azure	llmexec	GPT-4oOpenAI via azure/gpt-4o	$4.38	128K	900.0 ms	0no traffic	0.70
GPT-5 Mini (azure)openai/gpt-5-mini@azure	llmexec	GPT-5 MiniOpenAI via azure/gpt-5-mini	$0.69	400K	1.80 s	0no traffic	0.41
GPT-5 Nano (azure)openai/gpt-5-nano@azure	llmexec	GPT-5 NanoOpenAI via azure/gpt-5-nano	$0.14	400K	1.80 s	0no traffic	0.50
GPT-5.1-Codex-Max (azure)openai/gpt-5.1-codex-max@azure	llmexec	GPT-5.1-Codex-MaxOpenAI via azure/gpt-5.1-codex-max	$3.44	400K	1.80 s	0no traffic	0.60
GPT-5.1 (azure)openai/gpt-5.1@azure	llmexec	GPT-5.1OpenAI via azure/gpt-5.1	$3.44	400K	1.80 s	0no traffic	0.60
GPT-5.2-Codex (azure)openai/gpt-5.2-codex@azure	llmexec	GPT-5.2-CodexOpenAI via azure/gpt-5.2-codex	$4.81	400K	1.80 s	0no traffic	0.60
GPT-5.2 (azure)openai/gpt-5.2@azure	llmexec	GPT-5.2OpenAI via azure/gpt-5.2	$4.81	400K	1.80 s	0no traffic	0.60
GPT-5.3-Codex (azure)openai/gpt-5.3-codex@azure	llmexec	GPT-5.3-CodexOpenAI via azure/gpt-5.3-codex	$4.81	400K	1.80 s	0no traffic	0.60
GPT-5.4 Mini (azure)openai/gpt-5.4-mini@azure	llmexec	GPT-5.4 MiniOpenAI via azure/gpt-5.4-mini	$1.69	400K	1.80 s	0no traffic	0.46
GPT-5.4 Nano (azure)openai/gpt-5.4-nano@azure	llmexec	GPT-5.4 NanoOpenAI via azure/gpt-5.4-nano	$0.46	400K	1.80 s	0no traffic	0.43
GPT-5.4 Pro (azure)openai/gpt-5.4-pro@azure	llmexec	GPT-5.4 ProOpenAI via azure/gpt-5.4-pro	$68	1.1M	1.80 s	0no traffic	0.70
GPT-5.4 (azure)openai/gpt-5.4@azure	llmexec	GPT-5.4OpenAI via azure/gpt-5.4	$5.63	1.1M	1.80 s	0no traffic	0.70
GPT-5.5 (azure)openai/gpt-5.5@azure	llmexec	GPT-5.5OpenAI via azure/gpt-5.5	$11	1.1M	1.80 s	0no traffic	0.55
GPT-5.6 Sol (azure)openai/gpt-5.6-sol@azure	llmexec	GPT-5.6 SolOpenAI via azure/gpt-5.6-sol	$4.00	1.1M	1.80 s	0no traffic	0.60
GPT-5.6 Terra (azure)openai/gpt-5.6-terra@azure	llmexec	GPT-5.6 TerraOpenAI via azure/gpt-5.6-terra	$4.50	1.1M	1.80 s	0no traffic	0.57
GPT-5 (azure)openai/gpt-5@azure	llmexec	GPT-5OpenAI via azure/gpt-5	$3.44	400K	1.80 s	0no traffic	0.60
GPT-6 Astra (azure)openai/gpt-6-astra@azure	llmexec	GPT-6 AstraOpenAI via azure/gpt-6-astra	$20	1.1M	1.80 s	0no traffic	0.64
GPT Audio (azure)openai/gpt-audio@azure	llmexec	GPT AudioOpenAI via azure/gpt-audio	$4.38	128K	900.0 ms	0no traffic	0.70
GPT Chat Latest (azure)openai/gpt-chat-latest@azure	llmexec	GPT Chat LatestOpenAI via azure/gpt-chat-latest	$11	400K	900.0 ms	0no traffic	0.70
gpt-oss-20b (ollama-glm-ocr)openai/gpt-oss-20b@ollama-glm-ocr	llmexec	gpt-oss-20bOpenAI via ollama-glm-ocr/gpt-oss:20b	$0.06	131.1K	1.80 s	0no traffic	0.36
gpt-oss-20b (ollama-gpt-oss-20b)openai/gpt-oss-20b@ollama-gpt-oss-20b	llmexec	gpt-oss-20bOpenAI via ollama-gpt-oss-20b/gpt-oss:20b	$0.06	131.1K	1.80 s	0no traffic	0.36
gpt-oss-20b (ollama-qwen3-5-4b)openai/gpt-oss-20b@ollama-qwen3-5-4b	llmexec	gpt-oss-20bOpenAI via ollama-qwen3-5-4b/gpt-oss:20b	$0.06	131.1K	1.80 s	0no traffic	0.36
gpt-oss-20b (ollama-qwen3-embedding-4b)openai/gpt-oss-20b@ollama-qwen3-embedding-4b	llmexec	gpt-oss-20bOpenAI via ollama-qwen3-embedding-4b/gpt-oss:20b	$0.06	131.1K	1.80 s	0no traffic	0.36
gpt-oss-20b (ollama-translategemma-4b)openai/gpt-oss-20b@ollama-translategemma-4b	llmexec	gpt-oss-20bOpenAI via ollama-translategemma-4b/gpt-oss:20b	$0.06	131.1K	1.80 s	0no traffic	0.36
o1-pro (azure)openai/o1-pro@azure	llmexec	o1-proOpenAI via azure/o1-pro	$263	200K	1.80 s	0no traffic	0.70
o1 (azure)openai/o1@azure	llmexec	o1OpenAI via azure/o1	$26	200K	1.80 s	0no traffic	0.70
o3 Mini (azure)openai/o3-mini@azure	llmexec	o3 MiniOpenAI via azure/o3-mini	$1.93	200K	1.80 s	0no traffic	0.60
o3 Pro (azure)openai/o3-pro@azure	llmexec	o3 ProOpenAI via azure/o3-pro	$35	200K	1.80 s	0no traffic	0.70
o3 (azure)openai/o3@azure	llmexec	o3OpenAI via azure/o3	$3.50	200K	1.80 s	0no traffic	0.70
o4 Mini (azure)openai/o4-mini@azure	llmexec	o4 MiniOpenAI via azure/o4-mini	$1.93	200K	1.80 s	0no traffic	0.60
UFriendly support personapersona-friendly-support	persona	-	free	-	-	0no traffic	0.75
ULegal counsel personapersona-legal-counsel	persona	-	free	-	-	0no traffic	0.80
USenior engineer personapersona-senior-engineer	persona	-	free	-	-	0no traffic	0.85
Qwen3 8B (ollama)qwen/qwen3-8b@ollama	llmexec	Qwen3 8BQwen via ollama/qwen3:8b	$0.20	131.1K	1.80 s	0no traffic	0.33
Qwen3 8B (ollama-glm-ocr)qwen/qwen3-8b@ollama-glm-ocr	llmexec	Qwen3 8BQwen via ollama-glm-ocr/qwen3:8b	$0.20	131.1K	1.80 s	0no traffic	0.33
Qwen3 8B (ollama-gpt-oss-20b)qwen/qwen3-8b@ollama-gpt-oss-20b	llmexec	Qwen3 8BQwen via ollama-gpt-oss-20b/qwen3:8b	$0.20	131.1K	1.80 s	0no traffic	0.33
Qwen3 8B (ollama-qwen3-5-4b)qwen/qwen3-8b@ollama-qwen3-5-4b	llmexec	Qwen3 8BQwen via ollama-qwen3-5-4b/qwen3:8b	$0.20	131.1K	1.80 s	0no traffic	0.33
Qwen3 8B (ollama-qwen3-embedding-4b)qwen/qwen3-8b@ollama-qwen3-embedding-4b	llmexec	Qwen3 8BQwen via ollama-qwen3-embedding-4b/qwen3:8b	$0.20	131.1K	1.80 s	0no traffic	0.33
Qwen3 8B (ollama-translategemma-4b)qwen/qwen3-8b@ollama-translategemma-4b	llmexec	Qwen3 8BQwen via ollama-translategemma-4b/qwen3:8b	$0.20	131.1K	1.80 s	0no traffic	0.33
Qwen3.5-9B (ollama-glm-ocr)qwen/qwen3.5-9b@ollama-glm-ocr	llmexec	Qwen3.5-9BQwen via ollama-glm-ocr/qwen3.5:9b	$0.11	262.1K	1.80 s	0no traffic	0.50
Qwen3.5-9B (ollama-gpt-oss-20b)qwen/qwen3.5-9b@ollama-gpt-oss-20b	llmexec	Qwen3.5-9BQwen via ollama-gpt-oss-20b/qwen3.5:9b	$0.11	262.1K	1.80 s	0no traffic	0.50
Qwen3.5-9B (ollama-qwen3-5-4b)qwen/qwen3.5-9b@ollama-qwen3-5-4b	llmexec	Qwen3.5-9BQwen via ollama-qwen3-5-4b/qwen3.5:9b	$0.11	262.1K	1.80 s	0no traffic	0.50
Qwen3.5-9B (ollama-translategemma-4b)qwen/qwen3.5-9b@ollama-translategemma-4b	llmexec	Qwen3.5-9BQwen via ollama-translategemma-4b/qwen3.5:9b	$0.11	262.1K	1.80 s	0no traffic	0.50
Research agentresearch-agent	agentexec	ollama-deepseek-r1-8b/deepseek-r1:8b	$6.00	-	8.00 s	0no traffic	0.80
USQL skillskill-sql	skill	-	$1.00	-	700.0 ms	0no traffic	0.80
USummarization skillskill-summarize	skill	-	$0.80	-	1.20 s	0no traffic	0.82
SText to speechspeak-small	toolexec	speaches/speaches-ai/Kokoro-82M-v1.0-ONNX	$60	-	2.50 s	0no traffic	0.80
Customer support agentsupport-agent	agentexec	ollama-qwen3-5-4b/qwen3.5:4b	$2.00	-	1.50 s	0no traffic	0.80
BCalculatortool-calculator	toolexec	builtin/calculator	free	-	5.0 ms	0no traffic	0.99
Image generatortool-image-gen	toolexec	azure/tool-image-gen	$40	-	9.00 s	0no traffic	0.85
SSpeech to texttranscribe-small	toolexec	speaches/deepdml/faster-whisper-large-v3-turbo-ct2	free	-	4.00 s	0no traffic	0.80
UCustomer notification workflowworkflow-notify-customer	workflow	-	free	-	2.00 s	0no traffic	0.90
GLM 4.7 Flash (ollama)z-ai/glm-4.7-flash@ollama	llmexec	GLM 4.7 FlashZ.ai via ollama/glm-4.7-flash:latest	$0.15	200K	1.80 s	0no traffic	0.50
GLM 4.7 Flash (ollama-glm-ocr)z-ai/glm-4.7-flash@ollama-glm-ocr	llmexec	GLM 4.7 FlashZ.ai via ollama-glm-ocr/glm-4.7-flash:latest	$0.15	200K	1.80 s	0no traffic	0.50
GLM 4.7 Flash (ollama-gpt-oss-20b)z-ai/glm-4.7-flash@ollama-gpt-oss-20b	llmexec	GLM 4.7 FlashZ.ai via ollama-gpt-oss-20b/glm-4.7-flash:latest	$0.15	200K	1.80 s	0no traffic	0.50
GLM 4.7 Flash (ollama-qwen3-5-4b)z-ai/glm-4.7-flash@ollama-qwen3-5-4b	llmexec	GLM 4.7 FlashZ.ai via ollama-qwen3-5-4b/glm-4.7-flash:latest	$0.15	200K	1.80 s	0no traffic	0.50
GLM 4.7 Flash (ollama-qwen3-embedding-4b)z-ai/glm-4.7-flash@ollama-qwen3-embedding-4b	llmexec	GLM 4.7 FlashZ.ai via ollama-qwen3-embedding-4b/glm-4.7-flash:latest	$0.15	200K	1.80 s	0no traffic	0.50
GLM 4.7 Flash (ollama-translategemma-4b)z-ai/glm-4.7-flash@ollama-translategemma-4b	llmexec	GLM 4.7 FlashZ.ai via ollama-translategemma-4b/glm-4.7-flash:latest	$0.15	200K	1.80 s	0no traffic	0.50

Add your own targets by editing targets.yaml; set metadata.model to a catalogue id such as anthropic/claude-sonnet-4 to link a target to its reference model. See the guide or the JSON behind this page.