Free Inference Watchdog

updated hourly

109 unique models137 endpoints7 gateways

model id	#	nous (7)	tokenrouter (2)	kilo (17)	openrouter (21)	amd (5)	bai (3)	nim (82)
01-ai/yi-large	1							●
nim01-ai/yi-largehttps://integrate.api.nvidia.com/v1/chat/completionsopenai_compatible
DeepSeek-V4-Flash	1					●
amdDeepSeek-V4-Flashhttps://developer.amd.com.cn/radeon/api/v1/chat/completionsopenai_compatible
DeepSeek-V4-Flash-Vision-Exp	1					●
amdDeepSeek-V4-Flash-Vision-Exphttps://developer.amd.com.cn/radeon/api/v1/chat/completionsopenai_compatible
MinerU2.5-Pro	1					●
amdMinerU2.5-Prohttps://developer.amd.com.cn/radeon/api/v1/chat/completionsopenai_compatible
MiniCPM5-2B	1					●
amdMiniCPM5-2Bhttps://developer.amd.com.cn/radeon/api/v1/chat/completionsopenai_compatible
Qwen3.8-Flash-Next	1					●
amdQwen3.8-Flash-Nexthttps://developer.amd.com.cn/radeon/api/v1/chat/completionsopenai_compatible
adept/fuyu-8b	1							●
nimadept/fuyu-8bhttps://integrate.api.nvidia.com/v1/chat/completionsopenai_compatible
ai21labs/jamba-1.5-large-instruct	1							●
nimai21labs/jamba-1.5-large-instructhttps://integrate.api.nvidia.com/v1/chat/completionsopenai_compatible
aisingapore/sea-lion-7b-instruct	1							●
nimaisingapore/sea-lion-7b-instructhttps://integrate.api.nvidia.com/v1/chat/completionsopenai_compatible
bigcode/starcoder2-15b	1							●
nimbigcode/starcoder2-15bhttps://integrate.api.nvidia.com/v1/chat/completionsopenai_compatible
cohere/north-mini-code	2			●	●
kilocohere/north-mini-code:freehttps://api.kilo.ai/api/gateway/v1/chat/completionsopenai_compatible
openroutercohere/north-mini-code:freehttps://openrouter.ai/api/v1/chat/completionsopenai_compatible
databricks/dbrx-instruct	1							●
nimdatabricks/dbrx-instructhttps://integrate.api.nvidia.com/v1/chat/completionsopenai_compatible
deepseek-ai/deepseek-coder-6.7b-instruct	1							●
nimdeepseek-ai/deepseek-coder-6.7b-instructhttps://integrate.api.nvidia.com/v1/chat/completionsopenai_compatible
deepseek-ai/deepseek-v4-flash-0731	1							●
nimdeepseek-ai/deepseek-v4-flash-0731https://integrate.api.nvidia.com/v1/chat/completionsopenai_compatible
deepseek-ai/deepseek-v4-pro-0813	1							●
nimdeepseek-ai/deepseek-v4-pro-0813https://integrate.api.nvidia.com/v1/chat/completionsopenai_compatible
dots-studio/dots-3-note-preview	2			●	●
kilodots-studio/dots-3-note-preview:freehttps://api.kilo.ai/api/gateway/v1/chat/completionsopenai_compatible
openrouterdots-studio/dots-3-note-preview:freehttps://openrouter.ai/api/v1/chat/completionsopenai_compatible
google/codegemma-1.1-7b	1							●
nimgoogle/codegemma-1.1-7bhttps://integrate.api.nvidia.com/v1/chat/completionsopenai_compatible
google/codegemma-7b	1							●
nimgoogle/codegemma-7bhttps://integrate.api.nvidia.com/v1/chat/completionsopenai_compatible
google/deplot	1							●
nimgoogle/deplothttps://integrate.api.nvidia.com/v1/chat/completionsopenai_compatible
google/diffusiongemma-26b-a4b-it	1							●
nimgoogle/diffusiongemma-26b-a4b-ithttps://integrate.api.nvidia.com/v1/chat/completionsopenai_compatible
google/gemma-2b	1							●
nimgoogle/gemma-2bhttps://integrate.api.nvidia.com/v1/chat/completionsopenai_compatible
google/gemma-3-12b-it	1							●
nimgoogle/gemma-3-12b-ithttps://integrate.api.nvidia.com/v1/chat/completionsopenai_compatible
google/gemma-3-4b-it	1							●
nimgoogle/gemma-3-4b-ithttps://integrate.api.nvidia.com/v1/chat/completionsopenai_compatible
google/gemma-4-26b-a4b-it	1				●
openroutergoogle/gemma-4-26b-a4b-it:freehttps://openrouter.ai/api/v1/chat/completionsopenai_compatible
google/gemma-4-31b-it	2				●			●
openroutergoogle/gemma-4-31b-it:freehttps://openrouter.ai/api/v1/chat/completionsopenai_compatible
nimgoogle/gemma-4-31b-ithttps://integrate.api.nvidia.com/v1/chat/completionsopenai_compatible
google/lyria-3-clip-preview	1				●
openroutergoogle/lyria-3-clip-previewhttps://openrouter.ai/api/v1/chat/completionsopenai_compatible
google/lyria-3-pro-preview	1				●
openroutergoogle/lyria-3-pro-previewhttps://openrouter.ai/api/v1/chat/completionsopenai_compatible
google/recurrentgemma-2b	1							●
nimgoogle/recurrentgemma-2bhttps://integrate.api.nvidia.com/v1/chat/completionsopenai_compatible
hy3	1						●
baihy3https://api.b.ai/v1/chat/completionsopenai_compatible
ibm/granite-3.0-3b-a800m-instruct	1							●
nimibm/granite-3.0-3b-a800m-instructhttps://integrate.api.nvidia.com/v1/chat/completionsopenai_compatible
ibm/granite-3.0-8b-instruct	1							●
nimibm/granite-3.0-8b-instructhttps://integrate.api.nvidia.com/v1/chat/completionsopenai_compatible
ibm/granite-34b-code-instruct	1							●
nimibm/granite-34b-code-instructhttps://integrate.api.nvidia.com/v1/chat/completionsopenai_compatible
ibm/granite-8b-code-instruct	1							●
nimibm/granite-8b-code-instructhttps://integrate.api.nvidia.com/v1/chat/completionsopenai_compatible
inclusionai/ling-3.0-flash-fin	3	●		●	●
nousinclusionai/ling-3.0-flash-fin:freehttps://inference-api.nousresearch.com/v1/chat/completionsopenai_compatible
kiloinclusionai/ling-3.0-flash-fin:freehttps://api.kilo.ai/api/gateway/v1/chat/completionsopenai_compatible
openrouterinclusionai/ling-3.0-flash-fin:freehttps://openrouter.ai/api/v1/chat/completionsopenai_compatible
inclusionai/ling-3.0-flash-sante	3	●		●	●
nousinclusionai/ling-3.0-flash-sante:freehttps://inference-api.nousresearch.com/v1/chat/completionsopenai_compatible
kiloinclusionai/ling-3.0-flash-sante:freehttps://api.kilo.ai/api/gateway/v1/chat/completionsopenai_compatible
openrouterinclusionai/ling-3.0-flash-sante:freehttps://openrouter.ai/api/v1/chat/completionsopenai_compatible
inclusionai/ling-3.0-flash-vl	2			●	●
kiloinclusionai/ling-3.0-flash-vl:freehttps://api.kilo.ai/api/gateway/v1/chat/completionsopenai_compatible
openrouterinclusionai/ling-3.0-flash-vl:freehttps://openrouter.ai/api/v1/chat/completionsopenai_compatible
liquid/lfm-2.5-2.6b	2			●	●
kiloliquid/lfm-2.5-2.6b:freehttps://api.kilo.ai/api/gateway/v1/chat/completionsopenai_compatible
openrouterliquid/lfm-2.5-2.6b:freehttps://openrouter.ai/api/v1/chat/completionsopenai_compatible
meituan/longcat-2.0	1	●
nousmeituan/longcat-2.0:freehttps://inference-api.nousresearch.com/v1/chat/completionsopenai_compatible
meta/codellama-70b	1							●
nimmeta/codellama-70bhttps://integrate.api.nvidia.com/v1/chat/completionsopenai_compatible
meta/llama-3.2-11b-vision-instruct	1							●
nimmeta/llama-3.2-11b-vision-instructhttps://integrate.api.nvidia.com/v1/chat/completionsopenai_compatible
meta/llama-3.2-90b-vision-instruct	1							●
nimmeta/llama-3.2-90b-vision-instructhttps://integrate.api.nvidia.com/v1/chat/completionsopenai_compatible
meta/llama-guard-4-12b	1							●
nimmeta/llama-guard-4-12bhttps://integrate.api.nvidia.com/v1/chat/completionsopenai_compatible
meta/llama2-70b	1							●
nimmeta/llama2-70bhttps://integrate.api.nvidia.com/v1/chat/completionsopenai_compatible
meta/muse-glimmer-30b	1							●
nimmeta/muse-glimmer-30bhttps://integrate.api.nvidia.com/v1/chat/completionsopenai_compatible
microsoft/kosmos-2	1							●
nimmicrosoft/kosmos-2https://integrate.api.nvidia.com/v1/chat/completionsopenai_compatible
microsoft/phi-3-vision-128k-instruct	1							●
nimmicrosoft/phi-3-vision-128k-instructhttps://integrate.api.nvidia.com/v1/chat/completionsopenai_compatible
microsoft/phi-3.5-moe-instruct	1							●
nimmicrosoft/phi-3.5-moe-instructhttps://integrate.api.nvidia.com/v1/chat/completionsopenai_compatible
mimo-v2.5	1						●
baimimo-v2.5https://api.b.ai/v1/chat/completionsopenai_compatible
mistralai/codestral-22b-instruct-v0.1	1							●
nimmistralai/codestral-22b-instruct-v0.1https://integrate.api.nvidia.com/v1/chat/completionsopenai_compatible
mistralai/mistral-7b-instruct-v0.3	1							●
nimmistralai/mistral-7b-instruct-v0.3https://integrate.api.nvidia.com/v1/chat/completionsopenai_compatible
mistralai/mistral-large	1							●
nimmistralai/mistral-largehttps://integrate.api.nvidia.com/v1/chat/completionsopenai_compatible
mistralai/mistral-large-2-instruct	1							●
nimmistralai/mistral-large-2-instructhttps://integrate.api.nvidia.com/v1/chat/completionsopenai_compatible
mistralai/mistral-nemotron	1							●
nimmistralai/mistral-nemotronhttps://integrate.api.nvidia.com/v1/chat/completionsopenai_compatible
mistralai/mixtral-8x22b-v0.1	1							●
nimmistralai/mixtral-8x22b-v0.1https://integrate.api.nvidia.com/v1/chat/completionsopenai_compatible
moonshotai/kimi-k2.6	1							●
nimmoonshotai/kimi-k2.6https://integrate.api.nvidia.com/v1/chat/completionsopenai_compatible
moonshotai/kimi-k3	1							●
nimmoonshotai/kimi-k3https://integrate.api.nvidia.com/v1/chat/completionsopenai_compatible
nex-agi/nex-n2.5-mini	2			●	●
kilonex-agi/nex-n2.5-mini:freehttps://api.kilo.ai/api/gateway/v1/chat/completionsopenai_compatible
openrouternex-agi/nex-n2.5-mini:freehttps://openrouter.ai/api/v1/chat/completionsopenai_compatible
nex-agi/nex-n2.5-pro	2			●	●
kilonex-agi/nex-n2.5-pro:freehttps://api.kilo.ai/api/gateway/v1/chat/completionsopenai_compatible
openrouternex-agi/nex-n2.5-pro:freehttps://openrouter.ai/api/v1/chat/completionsopenai_compatible
nv-mistralai/mistral-nemo-12b-instruct	1							●
nimnv-mistralai/mistral-nemo-12b-instructhttps://integrate.api.nvidia.com/v1/chat/completionsopenai_compatible
nvidia/ai-synthetic-video-detector	1							●
nimnvidia/ai-synthetic-video-detectorhttps://integrate.api.nvidia.com/v1/chat/completionsopenai_compatible
nvidia/cosmos-reason2-8b	1							●
nimnvidia/cosmos-reason2-8bhttps://integrate.api.nvidia.com/v1/chat/completionsopenai_compatible
nvidia/embed-qa-4	1							●
nimnvidia/embed-qa-4https://integrate.api.nvidia.com/v1/chat/completionsopenai_compatible
nvidia/ising-calibration-1.5-31b	1							●
nimnvidia/ising-calibration-1.5-31bhttps://integrate.api.nvidia.com/v1/chat/completionsopenai_compatible
nvidia/llama-3.1-nemoguard-8b-content-safety	1							●
nimnvidia/llama-3.1-nemoguard-8b-content-safetyhttps://integrate.api.nvidia.com/v1/chat/completionsopenai_compatible
nvidia/llama-3.1-nemoguard-8b-topic-control	1							●
nimnvidia/llama-3.1-nemoguard-8b-topic-controlhttps://integrate.api.nvidia.com/v1/chat/completionsopenai_compatible
nvidia/llama-3.1-nemotron-51b-instruct	1							●
nimnvidia/llama-3.1-nemotron-51b-instructhttps://integrate.api.nvidia.com/v1/chat/completionsopenai_compatible
nvidia/llama-3.1-nemotron-70b-instruct	1							●
nimnvidia/llama-3.1-nemotron-70b-instructhttps://integrate.api.nvidia.com/v1/chat/completionsopenai_compatible
nvidia/llama-3.1-nemotron-safety-guard-8b-v3	1							●
nimnvidia/llama-3.1-nemotron-safety-guard-8b-v3https://integrate.api.nvidia.com/v1/chat/completionsopenai_compatible
nvidia/llama-3.1-nemotron-ultra-253b-v1	1							●
nimnvidia/llama-3.1-nemotron-ultra-253b-v1https://integrate.api.nvidia.com/v1/chat/completionsopenai_compatible
nvidia/llama-3.2-nemoretriever-1b-vlm-embed-v1	1							●
nimnvidia/llama-3.2-nemoretriever-1b-vlm-embed-v1https://integrate.api.nvidia.com/v1/chat/completionsopenai_compatible
nvidia/llama-3.2-nv-embedqa-1b-v1	1							●
nimnvidia/llama-3.2-nv-embedqa-1b-v1https://integrate.api.nvidia.com/v1/chat/completionsopenai_compatible
nvidia/llama-nemotron-embed-vl-1b-v2	1							●
nimnvidia/llama-nemotron-embed-vl-1b-v2https://integrate.api.nvidia.com/v1/chat/completionsopenai_compatible
nvidia/llama3-chatqa-1.5-70b	1							●
nimnvidia/llama3-chatqa-1.5-70bhttps://integrate.api.nvidia.com/v1/chat/completionsopenai_compatible
nvidia/mistral-nemo-minitron-8b-8k-instruct	1							●
nimnvidia/mistral-nemo-minitron-8b-8k-instructhttps://integrate.api.nvidia.com/v1/chat/completionsopenai_compatible
nvidia/nemotron-3-embed-1b	1							●
nimnvidia/nemotron-3-embed-1bhttps://integrate.api.nvidia.com/v1/chat/completionsopenai_compatible
nvidia/nemotron-3-nano-omni-30b-a3b-reasoning	4		●	●	●			●
tokenrouternvidia/nemotron-3-nano-omni-30b-a3b-reasoning:freehttps://api.tokenrouter.com/v1/chat/completionsopenai_compatible
kilonvidia/nemotron-3-nano-omni-30b-a3b-reasoning:freehttps://api.kilo.ai/api/gateway/v1/chat/completionsopenai_compatible
openrouternvidia/nemotron-3-nano-omni-30b-a3b-reasoning:freehttps://openrouter.ai/api/v1/chat/completionsopenai_compatible
nimnvidia/nemotron-3-nano-omni-30b-a3b-reasoninghttps://integrate.api.nvidia.com/v1/chat/completionsopenai_compatible
nvidia/nemotron-3-super-120b-a12b	3			●	●			●
kilonvidia/nemotron-3-super-120b-a12b:freehttps://api.kilo.ai/api/gateway/v1/chat/completionsopenai_compatible
openrouternvidia/nemotron-3-super-120b-a12b:freehttps://openrouter.ai/api/v1/chat/completionsopenai_compatible
nimnvidia/nemotron-3-super-120b-a12bhttps://integrate.api.nvidia.com/v1/chat/completionsopenai_compatible
nvidia/nemotron-3-ultra-550b-a55b	3			●	●			●
kilonvidia/nemotron-3-ultra-550b-a55b:freehttps://api.kilo.ai/api/gateway/v1/chat/completionsopenai_compatible
openrouternvidia/nemotron-3-ultra-550b-a55b:freehttps://openrouter.ai/api/v1/chat/completionsopenai_compatible
nimnvidia/nemotron-3-ultra-550b-a55bhttps://integrate.api.nvidia.com/v1/chat/completionsopenai_compatible
nvidia/nemotron-3.5-content-safety	3			●	●			●
kilonvidia/nemotron-3.5-content-safety:freehttps://api.kilo.ai/api/gateway/v1/chat/completionsopenai_compatible
openrouternvidia/nemotron-3.5-content-safety:freehttps://openrouter.ai/api/v1/chat/completionsopenai_compatible
nimnvidia/nemotron-3.5-content-safetyhttps://integrate.api.nvidia.com/v1/chat/completionsopenai_compatible
nvidia/nemotron-3.5-lightning	2			●	●
kilonvidia/nemotron-3.5-lightning:freehttps://api.kilo.ai/api/gateway/v1/chat/completionsopenai_compatible
openrouternvidia/nemotron-3.5-lightning:freehttps://openrouter.ai/api/v1/chat/completionsopenai_compatible
nvidia/nemotron-3.5-lightning-30b-a3b	1							●
nimnvidia/nemotron-3.5-lightning-30b-a3bhttps://integrate.api.nvidia.com/v1/chat/completionsopenai_compatible
nvidia/nemotron-4-340b-instruct	1							●
nimnvidia/nemotron-4-340b-instructhttps://integrate.api.nvidia.com/v1/chat/completionsopenai_compatible
nvidia/nemotron-4-340b-reward	1							●
nimnvidia/nemotron-4-340b-rewardhttps://integrate.api.nvidia.com/v1/chat/completionsopenai_compatible
nvidia/nemotron-nano-3-30b-a3b	1							●
nimnvidia/nemotron-nano-3-30b-a3bhttps://integrate.api.nvidia.com/v1/chat/completionsopenai_compatible
nvidia/nemotron-parse	1							●
nimnvidia/nemotron-parsehttps://integrate.api.nvidia.com/v1/chat/completionsopenai_compatible
nvidia/nemotron-parse-2.0	1							●
nimnvidia/nemotron-parse-2.0https://integrate.api.nvidia.com/v1/chat/completionsopenai_compatible
nvidia/neva-22b	1							●
nimnvidia/neva-22bhttps://integrate.api.nvidia.com/v1/chat/completionsopenai_compatible
nvidia/nv-embedqa-mistral-7b-v2	1							●
nimnvidia/nv-embedqa-mistral-7b-v2https://integrate.api.nvidia.com/v1/chat/completionsopenai_compatible
nvidia/nvclip	1							●
nimnvidia/nvcliphttps://integrate.api.nvidia.com/v1/chat/completionsopenai_compatible
nvidia/riva-translate-4b-instruct	1							●
nimnvidia/riva-translate-4b-instructhttps://integrate.api.nvidia.com/v1/chat/completionsopenai_compatible
nvidia/riva-translate-4b-instruct-v1.1	1							●
nimnvidia/riva-translate-4b-instruct-v1.1https://integrate.api.nvidia.com/v1/chat/completionsopenai_compatible
nvidia/riva-translate-4b-instruct-v2	1							●
nimnvidia/riva-translate-4b-instruct-v2https://integrate.api.nvidia.com/v1/chat/completionsopenai_compatible
nvidia/vila	1							●
nimnvidia/vilahttps://integrate.api.nvidia.com/v1/chat/completionsopenai_compatible
openai/gpt-oss-20b	1							●
nimopenai/gpt-oss-20bhttps://integrate.api.nvidia.com/v1/chat/completionsopenai_compatible
poolside/laguna-s-2.1	3	●		●	●
nouspoolside/laguna-s-2.1:freehttps://inference-api.nousresearch.com/v1/chat/completionsopenai_compatible
kilopoolside/laguna-s-2.1:freehttps://api.kilo.ai/api/gateway/v1/chat/completionsopenai_compatible
openrouterpoolside/laguna-s-2.1:freehttps://openrouter.ai/api/v1/chat/completionsopenai_compatible
poolside/laguna-xs-2.1	4	●		●	●			●
nouspoolside/laguna-xs-2.1:freehttps://inference-api.nousresearch.com/v1/chat/completionsopenai_compatible
kilopoolside/laguna-xs-2.1:freehttps://api.kilo.ai/api/gateway/v1/chat/completionsopenai_compatible
openrouterpoolside/laguna-xs-2.1:freehttps://openrouter.ai/api/v1/chat/completionsopenai_compatible
nimpoolside/laguna-xs-2.1https://integrate.api.nvidia.com/v1/chat/completionsopenai_compatible
qwen3.8-flash	1						●
baiqwen3.8-flashhttps://api.b.ai/v1/chat/completionsopenai_compatible
snowflake/arctic-embed-l	1							●
nimsnowflake/arctic-embed-lhttps://integrate.api.nvidia.com/v1/chat/completionsopenai_compatible
stepfun/step-3.7-flash	2	●		●
nousstepfun/step-3.7-flash:freehttps://inference-api.nousresearch.com/v1/chat/completionsopenai_compatible
kilostepfun/step-3.7-flash:freehttps://api.kilo.ai/api/gateway/v1/chat/completionsopenai_compatible
thinkingmachines/inkling	1				●
openrouterthinkingmachines/inkling:freehttps://openrouter.ai/api/v1/chat/completionsopenai_compatible
thinkingmachines/inkling-small	2			●	●
kilothinkingmachines/inkling-small:freehttps://api.kilo.ai/api/gateway/v1/chat/completionsopenai_compatible
openrouterthinkingmachines/inkling-small:freehttps://openrouter.ai/api/v1/chat/completionsopenai_compatible
upstage/solar-pro4	1	●
nousupstage/solar-pro4:freehttps://inference-api.nousresearch.com/v1/chat/completionsopenai_compatible
writer/palmyra-creative-122b	1							●
nimwriter/palmyra-creative-122bhttps://integrate.api.nvidia.com/v1/chat/completionsopenai_compatible
writer/palmyra-fin-70b-32k	1							●
nimwriter/palmyra-fin-70b-32khttps://integrate.api.nvidia.com/v1/chat/completionsopenai_compatible
writer/palmyra-med-70b	1							●
nimwriter/palmyra-med-70bhttps://integrate.api.nvidia.com/v1/chat/completionsopenai_compatible
writer/palmyra-med-70b-32k	1							●
nimwriter/palmyra-med-70b-32khttps://integrate.api.nvidia.com/v1/chat/completionsopenai_compatible
z-ai/glm-5.3	1		●
tokenrouterz-ai/glm-5.3-freehttps://api.tokenrouter.com/v1/chat/completionsopenai_compatible
z-ai/glm-5.3-flash	1							●
nimz-ai/glm-5.3-flashhttps://integrate.api.nvidia.com/v1/chat/completionsopenai_compatible
zyphra/zamba2-7b-instruct	1							●
nimzyphra/zamba2-7b-instructhttps://integrate.api.nvidia.com/v1/chat/completionsopenai_compatible
tracked ids per gateway		7	2	17	21	5	3	82