model,key,endpoint,extra
deepseek-v4-flash-free,-,https://opencode.ai/zen,
mimo-v2.5-free,-,https://opencode.ai/zen,
hy3-free,-,https://opencode.ai/zen,
nemotron-3-ultra-free,-,https://opencode.ai/zen,
north-mini-code-free,-,https://opencode.ai/zen,
kilo-auto/free,-,https://api.kilo.ai/api/openrouter,
tencent/hy3:free,-,https://api.kilo.ai/api/openrouter,
stepfun/step-3.7-flash:free,-,https://api.kilo.ai/api/openrouter,
poolside/laguna-xs-2.1:free,-,https://api.kilo.ai/api/openrouter,
cohere/north-mini-code:free,-,https://api.kilo.ai/api/openrouter,
nvidia/nemotron-3.5-content-safety:free,-,https://api.kilo.ai/api/openrouter,
nvidia/nemotron-3-ultra-550b-a55b:free,-,https://api.kilo.ai/api/openrouter,
nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free,-,https://api.kilo.ai/api/openrouter,
poolside/laguna-m.1:free,-,https://api.kilo.ai/api/openrouter,
nvidia/nemotron-3-super-120b-a12b:free,-,https://api.kilo.ai/api/openrouter,
openrouter/free,-,https://api.kilo.ai/api/openrouter,
openai-fast,-,https://text.pollinations.ai/openai,
nvidia/nemotron-3-nano-30b-a3b,-,https://g4f.space/api/nvidia,
z-ai/glm-5.2,-,https://g4f.space/api/nvidia,
deepseek-ai/deepseek-v4-pro,-,https://g4f.space/api/nvidia,
minimaxai/minimax-m2.7,-,https://g4f.space/api/nvidia,
stepfun-ai/step-3.7-flash,-,https://g4f.space/api/nvidia,
minimaxai/minimax-m3,-,https://g4f.space/api/nvidia,
nvidia/nemotron-3-super-120b-a12b,-,https://g4f.space/api/nvidia,
nvidia/nemotron-3-ultra-550b-a55b,-,https://g4f.space/api/nvidia,
mistralai/mistral-large-3-675b-instruct-2512,-,https://g4f.space/api/nvidia,
meta/llama-3.1-70b-instruct,-,https://g4f.space/api/nvidia,
meta/llama-3.1-8b-instruct,-,https://g4f.space/api/nvidia,
google/diffusiongemma-26b-a4b-it,-,https://g4f.space/api/nvidia,
openai/gpt-oss-120b,-,https://g4f.space/api/nvidia,
qwen/qwen3.5-397b-a17b,-,https://g4f.space/api/nvidia,
deepseek-ai/deepseek-v4-flash,-,https://g4f.space/api/nvidia,
abacusai/dracarys-llama-3.1-70b-instruct,-,https://g4f.space/api/nvidia,
mistralai/mistral-small-4-119b-2603,-,https://g4f.space/api/nvidia,
meta/llama-3.2-11b-vision-instruct,-,https://g4f.space/api/nvidia,
meta/llama-3.2-90b-vision-instruct,-,https://g4f.space/api/nvidia,
nvidia/nemotron-nano-12b-v2-vl,-,https://g4f.space/api/nvidia,
nvidia/llama-3.3-nemotron-super-49b-v1.5,-,https://g4f.space/api/nvidia,
microsoft/phi-4-mini-instruct,-,https://g4f.space/api/nvidia,
qwen/qwen3.5-122b-a10b,-,https://g4f.space/api/nvidia,
google/gemma-4-31b-it,-,https://g4f.space/api/nvidia,
mistralai/mistral-medium-3.5-128b,-,https://g4f.space/api/nvidia,
stepfun-ai/step-3.5-flash,-,https://g4f.space/api/nvidia,
meta/llama-3.3-70b-instruct,-,https://g4f.space/api/nvidia,
mistralai/ministral-14b-instruct-2512,-,https://g4f.space/api/nvidia,
openai/gpt-oss-20b,-,https://g4f.space/api/nvidia,
nvidia/nemotron-content-safety-reasoning-4b,-,https://g4f.space/api/nvidia,
nvidia/nemotron-mini-4b-instruct,-,https://g4f.space/api/nvidia,
meta/llama-guard-4-12b,-,https://g4f.space/api/nvidia,
01-ai/yi-large,-,https://g4f.space/api/nvidia,
adept/fuyu-8b,-,https://g4f.space/api/nvidia,
ai21labs/jamba-1.5-large-instruct,-,https://g4f.space/api/nvidia,
aisingapore/sea-lion-7b-instruct,-,https://g4f.space/api/nvidia,
baai/bge-m3,-,https://g4f.space/api/nvidia,
bigcode/starcoder2-15b,-,https://g4f.space/api/nvidia,
bytedance/seed-oss-36b-instruct,-,https://g4f.space/api/nvidia,
databricks/dbrx-instruct,-,https://g4f.space/api/nvidia,
deepseek-ai/deepseek-coder-6.7b-instruct,-,https://g4f.space/api/nvidia,
google/codegemma-1.1-7b,-,https://g4f.space/api/nvidia,
google/codegemma-7b,-,https://g4f.space/api/nvidia,
google/deplot,-,https://g4f.space/api/nvidia,
google/gemma-2-2b-it,-,https://g4f.space/api/nvidia,
google/gemma-2b,-,https://g4f.space/api/nvidia,
google/gemma-3-12b-it,-,https://g4f.space/api/nvidia,
google/gemma-3-4b-it,-,https://g4f.space/api/nvidia,
google/gemma-3n-e2b-it,-,https://g4f.space/api/nvidia,
google/gemma-3n-e4b-it,-,https://g4f.space/api/nvidia,
google/recurrentgemma-2b,-,https://g4f.space/api/nvidia,
ibm/granite-3.0-3b-a800m-instruct,-,https://g4f.space/api/nvidia,
ibm/granite-3.0-8b-instruct,-,https://g4f.space/api/nvidia,
ibm/granite-34b-code-instruct,-,https://g4f.space/api/nvidia,
ibm/granite-8b-code-instruct,-,https://g4f.space/api/nvidia,
meta/codellama-70b,-,https://g4f.space/api/nvidia,
meta/llama-3.2-1b-instruct,-,https://g4f.space/api/nvidia,
meta/llama-3.2-3b-instruct,-,https://g4f.space/api/nvidia,
meta/llama-4-maverick-17b-128e-instruct,-,https://g4f.space/api/nvidia,
meta/llama2-70b,-,https://g4f.space/api/nvidia,
microsoft/kosmos-2,-,https://g4f.space/api/nvidia,
microsoft/phi-3-vision-128k-instruct,-,https://g4f.space/api/nvidia,
microsoft/phi-3.5-moe-instruct,-,https://g4f.space/api/nvidia,
microsoft/phi-4-multimodal-instruct,-,https://g4f.space/api/nvidia,
mistralai/codestral-22b-instruct-v0.1,-,https://g4f.space/api/nvidia,
mistralai/mistral-7b-instruct-v0.3,-,https://g4f.space/api/nvidia,
mistralai/mistral-large,-,https://g4f.space/api/nvidia,
mistralai/mistral-large-2-instruct,-,https://g4f.space/api/nvidia,
mistralai/mistral-nemotron,-,https://g4f.space/api/nvidia,
mistralai/mixtral-8x22b-v0.1,-,https://g4f.space/api/nvidia,
mistralai/mixtral-8x7b-instruct-v0.1,-,https://g4f.space/api/nvidia,
moonshotai/kimi-k2.6,-,https://g4f.space/api/nvidia,
nv-mistralai/mistral-nemo-12b-instruct,-,https://g4f.space/api/nvidia,
nvidia/ai-synthetic-video-detector,-,https://g4f.space/api/nvidia,
nvidia/cosmos-reason2-8b,-,https://g4f.space/api/nvidia,
nvidia/embed-qa-4,-,https://g4f.space/api/nvidia,
nvidia/gliner-pii,-,https://g4f.space/api/nvidia,
nvidia/ising-calibration-1-35b-a3b,-,https://g4f.space/api/nvidia,
nvidia/llama-3.1-nemoguard-8b-content-safety,-,https://g4f.space/api/nvidia,
nvidia/llama-3.1-nemoguard-8b-topic-control,-,https://g4f.space/api/nvidia,
nvidia/llama-3.1-nemotron-51b-instruct,-,https://g4f.space/api/nvidia,
nvidia/llama-3.1-nemotron-70b-instruct,-,https://g4f.space/api/nvidia,
nvidia/llama-3.1-nemotron-nano-8b-v1,-,https://g4f.space/api/nvidia,
nvidia/llama-3.1-nemotron-nano-vl-8b-v1,-,https://g4f.space/api/nvidia,
nvidia/llama-3.1-nemotron-safety-guard-8b-v3,-,https://g4f.space/api/nvidia,
nvidia/llama-3.1-nemotron-ultra-253b-v1,-,https://g4f.space/api/nvidia,
nvidia/llama-3.2-nemoretriever-1b-vlm-embed-v1,-,https://g4f.space/api/nvidia,
nvidia/llama-3.2-nv-embedqa-1b-v1,-,https://g4f.space/api/nvidia,
nvidia/llama-3.3-nemotron-super-49b-v1,-,https://g4f.space/api/nvidia,
nvidia/llama-nemotron-embed-1b-v2,-,https://g4f.space/api/nvidia,
nvidia/llama-nemotron-embed-vl-1b-v2,-,https://g4f.space/api/nvidia,
nvidia/llama3-chatqa-1.5-70b,-,https://g4f.space/api/nvidia,
nvidia/mistral-nemo-minitron-8b-8k-instruct,-,https://g4f.space/api/nvidia,
nvidia/nemoretriever-parse,-,https://g4f.space/api/nvidia,
nvidia/nemotron-3-content-safety,-,https://g4f.space/api/nvidia,
nvidia/nemotron-3-nano-omni-30b-a3b-reasoning,-,https://g4f.space/api/nvidia,
nvidia/nemotron-3.5-content-safety,-,https://g4f.space/api/nvidia,
nvidia/nemotron-4-340b-instruct,-,https://g4f.space/api/nvidia,
nvidia/nemotron-4-340b-reward,-,https://g4f.space/api/nvidia,
nvidia/nemotron-nano-3-30b-a3b,-,https://g4f.space/api/nvidia,
nvidia/nemotron-parse,-,https://g4f.space/api/nvidia,
nvidia/neva-22b,-,https://g4f.space/api/nvidia,
nvidia/nv-embed-v1,-,https://g4f.space/api/nvidia,
nvidia/nv-embedcode-7b-v1,-,https://g4f.space/api/nvidia,
nvidia/nv-embedqa-e5-v5,-,https://g4f.space/api/nvidia,
nvidia/nv-embedqa-mistral-7b-v2,-,https://g4f.space/api/nvidia,
nvidia/nvclip,-,https://g4f.space/api/nvidia,
nvidia/nvidia-nemotron-nano-9b-v2,-,https://g4f.space/api/nvidia,
nvidia/riva-translate-4b-instruct,-,https://g4f.space/api/nvidia,
nvidia/riva-translate-4b-instruct-v1.1,-,https://g4f.space/api/nvidia,
nvidia/vila,-,https://g4f.space/api/nvidia,
qwen/qwen3-next-80b-a3b-instruct,-,https://g4f.space/api/nvidia,
sarvamai/sarvam-m,-,https://g4f.space/api/nvidia,
snowflake/arctic-embed-l,-,https://g4f.space/api/nvidia,
stockmark/stockmark-2-100b-instruct,-,https://g4f.space/api/nvidia,
upstage/solar-10.7b-instruct,-,https://g4f.space/api/nvidia,
writer/palmyra-creative-122b,-,https://g4f.space/api/nvidia,
writer/palmyra-fin-70b-32k,-,https://g4f.space/api/nvidia,
writer/palmyra-med-70b,-,https://g4f.space/api/nvidia,
writer/palmyra-med-70b-32k,-,https://g4f.space/api/nvidia,
zyphra/zamba2-7b-instruct,-,https://g4f.space/api/nvidia,
gemma4:31b,-,https://g4f.space/api/ollama,
nemotron-3-super,-,https://g4f.space/api/ollama,
nemotron-3-nano:30b,-,https://g4f.space/api/ollama,
glm-4.7,-,https://g4f.space/api/ollama,
gpt-oss:120b,-,https://g4f.space/api/ollama,
ministral-3:8b,-,https://g4f.space/api/ollama,
gemma3:27b,-,https://g4f.space/api/ollama,
qwen3-coder-next,-,https://g4f.space/api/ollama,
devstral-2:123b,-,https://g4f.space/api/ollama,
gemma3:12b,-,https://g4f.space/api/ollama,
minimax-m2.5,-,https://g4f.space/api/ollama,
gemma3:4b,-,https://g4f.space/api/ollama,
devstral-small-2:24b,-,https://g4f.space/api/ollama,
gpt-oss:20b,-,https://g4f.space/api/ollama,
ministral-3:14b,-,https://g4f.space/api/ollama,
ministral-3:3b,-,https://g4f.space/api/ollama,
minimax-m2.1,-,https://g4f.space/api/ollama,
meta-llama/llama-4-scout-17b-16e-instruct,-,https://g4f.space/api/groq,
llama-3.1-8b-instant,-,https://g4f.space/api/groq,
openai/gpt-oss-120b,-,https://g4f.space/api/groq,
openai/gpt-oss-20b,-,https://g4f.space/api/groq,
llama-3.3-70b-versatile,-,https://g4f.space/api/groq,
qwen/qwen3.6-27b,-,https://g4f.space/api/groq,
qwen/qwen3-32b,-,https://g4f.space/api/groq,
groq/compound-mini,-,https://g4f.space/api/groq,
groq/compound,-,https://g4f.space/api/groq,
openai/gpt-oss-safeguard-20b,-,https://g4f.space/api/groq,
meta-llama/llama-prompt-guard-2-22m,-,https://g4f.space/api/groq,
whisper-large-v3,-,https://g4f.space/api/groq,
meta-llama/llama-prompt-guard-2-86m,-,https://g4f.space/api/groq,
whisper-large-v3-turbo,-,https://g4f.space/api/groq,
canopylabs/orpheus-arabic-saudi,-,https://g4f.space/api/groq,
allam-2-7b,-,https://g4f.space/api/groq,
canopylabs/orpheus-v1-english,-,https://g4f.space/api/groq,
Qwen3-Embedding-8B,-,https://oai.endpoints.kepler.ai.cloud.ovh.net,
Qwen3-32B,-,https://oai.endpoints.kepler.ai.cloud.ovh.net,
Mistral-Nemo-Instruct-2407,-,https://oai.endpoints.kepler.ai.cloud.ovh.net,
Qwen3.5-397B-A17B,-,https://oai.endpoints.kepler.ai.cloud.ovh.net,
gpt-oss-120b,-,https://oai.endpoints.kepler.ai.cloud.ovh.net,
Mistral-Small-3.2-24B-Instruct-2506,-,https://oai.endpoints.kepler.ai.cloud.ovh.net,
Qwen2.5-VL-72B-Instruct,-,https://oai.endpoints.kepler.ai.cloud.ovh.net,
Mistral-7B-Instruct-v0.3,-,https://oai.endpoints.kepler.ai.cloud.ovh.net,
Qwen3-Coder-30B-A3B-Instruct,-,https://oai.endpoints.kepler.ai.cloud.ovh.net,
Qwen3.6-27B,-,https://oai.endpoints.kepler.ai.cloud.ovh.net,
gpt-oss-20b,-,https://oai.endpoints.kepler.ai.cloud.ovh.net,
Qwen3.5-9B,-,https://oai.endpoints.kepler.ai.cloud.ovh.net,
Meta-Llama-3_3-70B-Instruct,-,https://oai.endpoints.kepler.ai.cloud.ovh.net,