Model Name Provider Use Case Price Price Units Role
01-ai/yi-large openrouter generation 3.1579 per 1M tokens input
01-ai/yi-large openrouter generation 3.1579 per 1M tokens output
@cf/deepseek-ai/deepseek-r1-distill-qwen-32b cloudflare-workers-ai generation 0.4970 per 1M tokens input
@cf/deepseek-ai/deepseek-r1-distill-qwen-32b cloudflare-workers-ai generation 4.8810 per 1M tokens output
@cf/google/gemma-3-12b-it cloudflare-workers-ai generation 0.3450 per 1M tokens input
@cf/google/gemma-3-12b-it cloudflare-workers-ai generation 0.5560 per 1M tokens output
@cf/meta/llama-2-7b-chat-fp16 cloudflare-workers-ai generation 0.5560 per 1M tokens input
@cf/meta/llama-2-7b-chat-fp16 cloudflare-workers-ai generation 6.6670 per 1M tokens output
@cf/meta/llama-3-8b-instruct cloudflare-workers-ai generation 0.2820 per 1M tokens input
@cf/meta/llama-3-8b-instruct cloudflare-workers-ai generation 0.8270 per 1M tokens output
@cf/meta/llama-3-8b-instruct-awq cloudflare-workers-ai generation 0.1230 per 1M tokens input
@cf/meta/llama-3-8b-instruct-awq cloudflare-workers-ai generation 0.2660 per 1M tokens output
@cf/meta/llama-3.1-70b-instruct-fp8-fast cloudflare-workers-ai generation 0.2930 per 1M tokens input
@cf/meta/llama-3.1-70b-instruct-fp8-fast cloudflare-workers-ai generation 2.2530 per 1M tokens output
@cf/meta/llama-3.1-8b-instruct cloudflare-workers-ai generation 0.2820 per 1M tokens input
@cf/meta/llama-3.1-8b-instruct cloudflare-workers-ai generation 0.8270 per 1M tokens output
@cf/meta/llama-3.1-8b-instruct-awq cloudflare-workers-ai generation 0.1230 per 1M tokens input
@cf/meta/llama-3.1-8b-instruct-awq cloudflare-workers-ai generation 0.2660 per 1M tokens output
@cf/meta/llama-3.1-8b-instruct-fp8 cloudflare-workers-ai generation 0.1520 per 1M tokens input
@cf/meta/llama-3.1-8b-instruct-fp8 cloudflare-workers-ai generation 0.2870 per 1M tokens output
@cf/meta/llama-3.1-8b-instruct-fp8-fast cloudflare-workers-ai generation 0.0450 per 1M tokens input
@cf/meta/llama-3.1-8b-instruct-fp8-fast cloudflare-workers-ai generation 0.3840 per 1M tokens output
@cf/meta/llama-3.2-11b-vision-instruct cloudflare-workers-ai generation 0.0490 per 1M tokens input
@cf/meta/llama-3.2-11b-vision-instruct cloudflare-workers-ai generation 0.6760 per 1M tokens output
@cf/meta/llama-3.2-1b-instruct cloudflare-workers-ai generation 0.0270 per 1M tokens input
@cf/meta/llama-3.2-1b-instruct cloudflare-workers-ai generation 0.2010 per 1M tokens output
@cf/meta/llama-3.2-3b-instruct cloudflare-workers-ai generation 0.0510 per 1M tokens input
@cf/meta/llama-3.2-3b-instruct cloudflare-workers-ai generation 0.3350 per 1M tokens output
@cf/meta/llama-3.3-70b-instruct-fp8-fast cloudflare-workers-ai generation 0.2930 per 1M tokens input
@cf/meta/llama-3.3-70b-instruct-fp8-fast cloudflare-workers-ai generation 2.2530 per 1M tokens output
@cf/meta/llama-4-scout-17b-16e-instruct cloudflare-workers-ai generation 0.2700 per 1M tokens input
@cf/meta/llama-4-scout-17b-16e-instruct cloudflare-workers-ai generation 0.8500 per 1M tokens output
@cf/meta/llama-guard-3-8b cloudflare-workers-ai generation 0.4840 per 1M tokens input
@cf/meta/llama-guard-3-8b cloudflare-workers-ai generation 0.0300 per 1M tokens output
@cf/mistral/mistral-7b-instruct-v0.1 cloudflare-workers-ai generation 0.1100 per 1M tokens input
@cf/mistral/mistral-7b-instruct-v0.1 cloudflare-workers-ai generation 0.1900 per 1M tokens output
@cf/mistralai/mistral-small-3.1-24b-instruct cloudflare-workers-ai generation 0.3510 per 1M tokens input
@cf/mistralai/mistral-small-3.1-24b-instruct cloudflare-workers-ai generation 0.5550 per 1M tokens output
@cf/qwen/qwen2.5-coder-32b-instruct cloudflare-workers-ai generation 0.6600 per 1M tokens input
@cf/qwen/qwen2.5-coder-32b-instruct cloudflare-workers-ai generation 1.0000 per 1M tokens output
@cf/qwen/qwq-32b cloudflare-workers-ai generation 0.6600 per 1M tokens input
@cf/qwen/qwq-32b cloudflare-workers-ai generation 1.0000 per 1M tokens output
Ai2/OLMo-7B-Instruct-HF nebius generation 0.0800 per 1M tokens input
Ai2/OLMo-7B-Instruct-HF nebius generation 0.2400 per 1M tokens output
BAAI/bge-en-icl nebius embeddings 0.0100 per 1M tokens input
BAAI/bge-multilingual-gemma2 nebius embeddings 0.0100 per 1M tokens input
Custom LLM - Nvidia A100 GPU deepinfra custom-deployment 1.5000 per GPU-hour total
Custom LLM - Nvidia H100 GPU deepinfra custom-deployment 2.4000 per GPU-hour total
Custom LLM - Nvidia H200 GPU deepinfra custom-deployment 3.0000 per GPU-hour total
DALL·E 2 openai generation 0.0200 per 1024x1024 Standard image total
DALL·E 2 openai generation 0.0160 per 256x256 Standard image total
DALL·E 2 openai generation 0.0180 per 512x512 Standard image total
DALL·E 3 openai generation 0.0800 per 1024x1024 HD image total
DALL·E 3 openai generation 0.0400 per 1024x1024 Standard image total
DALL·E 3 openai generation 0.1200 per 1024x1792 HD image total
DALL·E 3 openai generation 0.0800 per 1024x1792 Standard image total
DALL·E 3 openai generation 0.1200 per 1792x1024 HD image total
DALL·E 3 openai generation 0.0800 per 1792x1024 Standard image total
GPT Image 1 openai generation 0.1670 per 1024x1024 High image total
GPT Image 1 openai generation 0.0110 per 1024x1024 Low image total
GPT Image 1 openai generation 0.0420 per 1024x1024 Medium image total
GPT Image 1 openai generation 0.2500 per 1024x1536 High image total
GPT Image 1 openai generation 0.0160 per 1024x1536 Low image total
GPT Image 1 openai generation 0.0630 per 1024x1536 Medium image total
GPT Image 1 openai generation 0.2500 per 1536x1024 High image total
GPT Image 1 openai generation 0.0160 per 1536x1024 Low image total
GPT Image 1 openai generation 0.0630 per 1536x1024 Medium image total
Gemini 2.5 Flash google-vertex-ai generation 0.1500 per 1M tokens input (<= 200K input tokens)
Gemini 2.5 Flash google-vertex-ai generation 0.1500 per 1M image tokens input (<= 200K input tokens)
Gemini 2.5 Flash google-vertex-ai generation 0.1500 per 1M video tokens input (<= 200K input tokens)
Gemini 2.5 Flash google-vertex-ai generation 1.0000 per 1M audio tokens input (<= 200K input tokens)
Gemini 2.5 Flash google-vertex-ai generation 0.1500 per 1M tokens input (> 200K input tokens)
Gemini 2.5 Flash google-vertex-ai generation 0.1500 per 1M image tokens input (> 200K input tokens)
Gemini 2.5 Flash google-vertex-ai generation 0.1500 per 1M video tokens input (> 200K input tokens)
Gemini 2.5 Flash google-vertex-ai generation 1.0000 per 1M audio tokens input (> 200K input tokens)
Gemini 2.5 Flash google-vertex-ai generation 0.6000 per 1M tokens output (<= 200K input tokens)
Gemini 2.5 Flash google-vertex-ai generation 3.5000 per 1M tokens output (<= 200K input tokens)
Gemini 2.5 Flash google-vertex-ai generation 0.6000 per 1M tokens output (> 200K input tokens)
Gemini 2.5 Flash google-vertex-ai generation 3.5000 per 1M tokens output (> 200K input tokens)
Gemini 2.5 Flash google-vertex-ai generation 3.5000 per 1M tokens reasoning (<= 200K input tokens)
Gemini 2.5 Flash google-vertex-ai generation 3.5000 per 1M tokens reasoning (> 200K input tokens)
Gemini 2.5 Pro google-vertex-ai generation 1.2500 per 1M tokens input (<= 200K input tokens)
Gemini 2.5 Pro google-vertex-ai generation 1.2500 per 1M image tokens input (<= 200K input tokens)
Gemini 2.5 Pro google-vertex-ai generation 1.2500 per 1M audio tokens input (<= 200K input tokens)
Gemini 2.5 Pro google-vertex-ai generation 1.2500 per 1M video tokens input (<= 200K input tokens)
Gemini 2.5 Pro google-vertex-ai generation 2.5000 per 1M tokens input (> 200K input tokens)
Gemini 2.5 Pro google-vertex-ai generation 2.5000 per 1M image tokens input (> 200K input tokens)
Gemini 2.5 Pro google-vertex-ai generation 2.5000 per 1M audio tokens input (> 200K input tokens)
Gemini 2.5 Pro google-vertex-ai generation 2.5000 per 1M video tokens input (> 200K input tokens)
Gemini 2.5 Pro google-vertex-ai generation 10.0000 per 1M tokens output (<= 200K input tokens)
Gemini 2.5 Pro google-vertex-ai generation 15.0000 per 1M tokens output (> 200K input tokens)
Gemini 2.5 Pro google-vertex-ai generation 10.0000 per 1M tokens reasoning (<= 200K input tokens)
Gemini 2.5 Pro google-vertex-ai generation 15.0000 per 1M tokens reasoning (> 200K input tokens)
Google-Gemma-2-27B-it nebius generation 0.1000 per 1M tokens input
Google-Gemma-2-27B-it nebius generation 0.1700 per 1M tokens input
Google-Gemma-2-27B-it nebius generation 0.3000 per 1M tokens output
Google-Gemma-2-27B-it nebius generation 0.5100 per 1M tokens output
Google-Gemma-2-9B-it nebius generation 0.0200 per 1M tokens input
Google-Gemma-2-9B-it nebius generation 0.0300 per 1M tokens input
Google-Gemma-2-9B-it nebius generation 0.0600 per 1M tokens output
Google-Gemma-2-9B-it nebius generation 0.0900 per 1M tokens output
Llama-3-70B-Instruct deepinfra generation 0.3000 per 1M tokens input
Llama-3-70B-Instruct deepinfra generation 0.4000 per 1M tokens output
Llama-3-8B-Instruct deepinfra generation 0.0300 per 1M tokens input
Llama-3-8B-Instruct deepinfra generation 0.0600 per 1M tokens output
Llama-3.1-70B-Instruct deepinfra generation 0.2300 per 1M tokens input
Llama-3.1-70B-Instruct deepinfra generation 0.4000 per 1M tokens output
Llama-3.1-8B-Instruct deepinfra generation 0.0300 per 1M tokens input
Llama-3.1-8B-Instruct deepinfra generation 0.0500 per 1M tokens output
Llava-hf/llava-1.5-13b-hf nebius vision 0.0400 per 1M tokens input
Llava-hf/llava-1.5-13b-hf nebius vision 0.1200 per 1M tokens output
Llava-hf/llava-1.5-7b-hf nebius vision 0.0400 per 1M tokens input
Llava-hf/llava-1.5-7b-hf nebius vision 0.1200 per 1M tokens output
Meta-llama/Llama-Guard-3-8B nebius moderation 0.2000 per 1M tokens input
Meta-llama/Llama-Guard-3-8B nebius moderation 0.6000 per 1M tokens output
Meta/Llama-3.1-405B-Instruct nebius generation 1.0000 per 1M tokens input
Meta/Llama-3.1-405B-Instruct nebius generation 3.0000 per 1M tokens output
Meta/Llama-3.1-70B-Instruct nebius generation 0.1300 per 1M tokens input
Meta/Llama-3.1-70B-Instruct nebius generation 0.2500 per 1M tokens input
Meta/Llama-3.1-70B-Instruct nebius generation 0.4000 per 1M tokens output
Meta/Llama-3.1-70B-Instruct nebius generation 0.7500 per 1M tokens output
Meta/Llama-3.1-8B-Instruct nebius generation 0.0200 per 1M tokens input
Meta/Llama-3.1-8B-Instruct nebius generation 0.0300 per 1M tokens input
Meta/Llama-3.1-8B-Instruct nebius generation 0.0600 per 1M tokens output
Meta/Llama-3.1-8B-Instruct nebius generation 0.0900 per 1M tokens output
Meta/Llama-3.2-1B-Instruct nebius generation 0.0050 per 1M tokens input
Meta/Llama-3.2-1B-Instruct nebius generation 0.0100 per 1M tokens output
Meta/Llama-3.2-3B-Instruct nebius generation 0.0100 per 1M tokens input
Meta/Llama-3.2-3B-Instruct nebius generation 0.0200 per 1M tokens output
Meta/Llama-3.3-70B-Instruct nebius generation 0.1300 per 1M tokens input
Meta/Llama-3.3-70B-Instruct nebius generation 0.2500 per 1M tokens input
Meta/Llama-3.3-70B-Instruct nebius generation 0.4000 per 1M tokens output
Meta/Llama-3.3-70B-Instruct nebius generation 0.7500 per 1M tokens output
Meta/Llama-Guard-3 nebius generation 0.0200 per 1M tokens input
Meta/Llama-Guard-3 nebius generation 0.0600 per 1M tokens output
Microsoft-Phi-3-Medium-128k-instruct nebius generation 0.1000 per 1M tokens input
Microsoft-Phi-3-Medium-128k-instruct nebius generation 0.1500 per 1M tokens input
Microsoft-Phi-3-Medium-128k-instruct nebius generation 0.3000 per 1M tokens output
Microsoft-Phi-3-Medium-128k-instruct nebius generation 0.4500 per 1M tokens output
Microsoft/Phi-3-mini-4k-instruct nebius generation 0.0400 per 1M tokens input
Microsoft/Phi-3-mini-4k-instruct nebius generation 0.1300 per 1M tokens input
Microsoft/Phi-3-mini-4k-instruct nebius generation 0.1300 per 1M tokens output
Microsoft/Phi-3-mini-4k-instruct nebius generation 0.4000 per 1M tokens output
Mistral-7B-v3 deepinfra generation 0.0290 per 1M tokens input
Mistral-7B-v3 deepinfra generation 0.0550 per 1M tokens output
MistralAI/Mistral-Nemo-Instruct-2407 nebius generation 0.0400 per 1M tokens input
MistralAI/Mistral-Nemo-Instruct-2407 nebius generation 0.0800 per 1M tokens input
MistralAI/Mistral-Nemo-Instruct-2407 nebius generation 0.1200 per 1M tokens output
MistralAI/Mistral-Nemo-Instruct-2407 nebius generation 0.2400 per 1M tokens output
MistralAI/Mixtral-8x22B-Instruct-v0.1 nebius generation 0.4000 per 1M tokens input
MistralAI/Mixtral-8x22B-Instruct-v0.1 nebius generation 0.7000 per 1M tokens input
MistralAI/Mixtral-8x22B-Instruct-v0.1 nebius generation 1.2000 per 1M tokens output
MistralAI/Mixtral-8x22B-Instruct-v0.1 nebius generation 2.1000 per 1M tokens output
MistralAI/Mixtral-8x7B-Instruct-v0.1 nebius generation 0.0800 per 1M tokens input
MistralAI/Mixtral-8x7B-Instruct-v0.1 nebius generation 0.1500 per 1M tokens input
MistralAI/Mixtral-8x7B-Instruct-v0.1 nebius generation 0.2400 per 1M tokens output
MistralAI/Mixtral-8x7B-Instruct-v0.1 nebius generation 0.4500 per 1M tokens output
MistralAI/dolphin-2.9.2-mixtral-8x22b nebius generation 0.4000 per 1M tokens input
MistralAI/dolphin-2.9.2-mixtral-8x22b nebius generation 1.2000 per 1M tokens output
MythoMax-L2-13b deepinfra generation 0.0650 per 1M tokens input
MythoMax-L2-13b deepinfra generation 0.0650 per 1M tokens output
NousResearch/Hermes-3-Llama-405B nebius generation 1.0000 per 1M tokens input
NousResearch/Hermes-3-Llama-405B nebius generation 3.0000 per 1M tokens output
Nvidia/Llama-3.1-Nemotron-70B-Instruct-HF nebius generation 0.1300 per 1M tokens input
Nvidia/Llama-3.1-Nemotron-70B-Instruct-HF nebius generation 0.2500 per 1M tokens input
Nvidia/Llama-3.1-Nemotron-70B-Instruct-HF nebius generation 0.4000 per 1M tokens output
Nvidia/Llama-3.1-Nemotron-70B-Instruct-HF nebius generation 0.7500 per 1M tokens output
Nvidia/Llama-3_1-Nemotron-Ultra-253B-v1 nebius generation 0.6000 per 1M tokens input
Nvidia/Llama-3_1-Nemotron-Ultra-253B-v1 nebius generation 1.8000 per 1M tokens output
Phi-3.5-MoE-instruct nebius generation 0.1000 per 1M tokens input
Phi-3.5-MoE-instruct nebius generation 0.3000 per 1M tokens output
Phi-3.5-mini-instruct nebius generation 0.0300 per 1M tokens input
Phi-3.5-mini-instruct nebius generation 0.0900 per 1M tokens output
QwQ-32B nebius generation 0.1500 per 1M tokens input
QwQ-32B nebius generation 0.5000 per 1M tokens input
QwQ-32B nebius generation 0.4500 per 1M tokens output
QwQ-32B nebius generation 1.5000 per 1M tokens output
QwQ-32B-Preview nebius generation 0.0900 per 1M tokens input
QwQ-32B-Preview nebius generation 0.2700 per 1M tokens output
Qwen/QVQ-72B-preview nebius vision 0.2000 per 1M tokens input
Qwen/QVQ-72B-preview nebius vision 0.6000 per 1M tokens output
Qwen/Qwen2-VL-72B-Instruct nebius vision 0.1300 per 1M tokens input
Qwen/Qwen2-VL-72B-Instruct nebius vision 0.4000 per 1M tokens output
Qwen/Qwen2-VL-7B-Instruct nebius vision 0.0400 per 1M tokens input
Qwen/Qwen2-VL-7B-Instruct nebius vision 0.1200 per 1M tokens output
Qwen2-VL-72B-Instruct nebius generation 0.1300 per 1M tokens input
Qwen2-VL-72B-Instruct nebius generation 0.4000 per 1M tokens output
Qwen2-VL-7B-Instruct nebius generation 0.0400 per 1M tokens input
Qwen2-VL-7B-Instruct nebius generation 0.1200 per 1M tokens output
Qwen2.5-1.5B-Instruct nebius generation 0.0200 per 1M tokens input
Qwen2.5-1.5B-Instruct nebius generation 0.0600 per 1M tokens output
Qwen2.5-32B-Instruct nebius generation 0.0600 per 1M tokens input
Qwen2.5-32B-Instruct nebius generation 0.1300 per 1M tokens input
Qwen2.5-32B-Instruct nebius generation 0.2000 per 1M tokens output
Qwen2.5-32B-Instruct nebius generation 0.4000 per 1M tokens output
Qwen2.5-72B-Instruct nebius generation 0.1300 per 1M tokens input
Qwen2.5-72B-Instruct nebius generation 0.2500 per 1M tokens input
Qwen2.5-72B-Instruct nebius generation 0.4000 per 1M tokens output
Qwen2.5-72B-Instruct nebius generation 0.7500 per 1M tokens output
Qwen2.5-Coder-7B nebius generation 0.0100 per 1M tokens input
Qwen2.5-Coder-7B nebius generation 0.0300 per 1M tokens input
Qwen2.5-Coder-7B nebius generation 0.0300 per 1M tokens output
Qwen2.5-Coder-7B nebius generation 0.0900 per 1M tokens output
Qwen2.5-Coder-7B-Instruct nebius generation 0.0100 per 1M tokens input
Qwen2.5-Coder-7B-Instruct nebius generation 0.0300 per 1M tokens input
Qwen2.5-Coder-7B-Instruct nebius generation 0.0300 per 1M tokens output
Qwen2.5-Coder-7B-Instruct nebius generation 0.0900 per 1M tokens output
TTS openai generation 15.0000 per 1M characters total
TTS HD openai generation 30.0000 per 1M characters total
Whisper openai generation 0.0060 per audio minute total
aaditya/Llama3-OpenBioLLM-70B nebius generation 0.1300 per 1M tokens input
aaditya/Llama3-OpenBioLLM-70B nebius generation 0.4000 per 1M tokens output
aaditya/Llama3-OpenBioLLM-8B nebius generation 0.0200 per 1M tokens input
aaditya/Llama3-OpenBioLLM-8B nebius generation 0.0600 per 1M tokens output
aetherwiing/mn-starcannon-12b openrouter generation 0.8421 per 1M tokens input
aetherwiing/mn-starcannon-12b openrouter generation 1.2632 per 1M tokens output
agentica-org/deepcoder-14b-preview openrouter generation 0.0000 per 1M tokens input
agentica-org/deepcoder-14b-preview openrouter generation 0.0000 per 1M tokens output
ai21/jamba-1-5-large openrouter generation 2.1053 per 1M tokens input
ai21/jamba-1-5-large openrouter generation 8.4211 per 1M tokens output
ai21/jamba-1-5-mini openrouter generation 0.2105 per 1M tokens input
ai21/jamba-1-5-mini openrouter generation 0.4211 per 1M tokens output
ai21/jamba-1.6-large openrouter generation 2.1053 per 1M tokens input
ai21/jamba-1.6-large openrouter generation 8.4211 per 1M tokens output
ai21/jamba-1.6-mini openrouter generation 0.2105 per 1M tokens input
ai21/jamba-1.6-mini openrouter generation 0.4211 per 1M tokens output
ai21/jamba-instruct openrouter generation 0.5263 per 1M tokens input
ai21/jamba-instruct openrouter generation 0.7368 per 1M tokens output
aion-labs/aion-1.0 openrouter generation 4.2105 per 1M tokens input
aion-labs/aion-1.0 openrouter generation 8.4211 per 1M tokens output
aion-labs/aion-1.0-mini openrouter generation 0.7368 per 1M tokens input
aion-labs/aion-1.0-mini openrouter generation 1.4737 per 1M tokens output
aion-labs/aion-rp-llama-3.1-8b openrouter generation 0.2105 per 1M tokens input
aion-labs/aion-rp-llama-3.1-8b openrouter generation 0.2105 per 1M tokens output
alfredpros/codellama-7b-instruct-solidity openrouter generation 0.8421 per 1M tokens input
alfredpros/codellama-7b-instruct-solidity openrouter generation 1.2632 per 1M tokens output
all-hands/openhands-lm-32b-v0.1 openrouter generation 2.7368 per 1M tokens input
all-hands/openhands-lm-32b-v0.1 openrouter generation 3.5789 per 1M tokens output
allenai/molmo-7b-d openrouter generation 0.0000 per 1M tokens input
allenai/molmo-7b-d openrouter generation 0.0000 per 1M tokens output
allenai/olmo-7b-instruct openrouter generation 0.0842 per 1M tokens input
allenai/olmo-7b-instruct openrouter generation 0.2526 per 1M tokens output
alpindale/goliath-120b openrouter generation 6.9079 per 1M tokens input
alpindale/goliath-120b openrouter generation 9.8684 per 1M tokens output
alpindale/magnum-72b openrouter generation 4.2105 per 1M tokens input
alpindale/magnum-72b openrouter generation 6.3158 per 1M tokens output
amazon/nova-lite-v1 openrouter generation 0.0632 per 1M tokens input
amazon/nova-lite-v1 openrouter generation 0.2526 per 1M tokens output
amazon/nova-micro-v1 openrouter generation 0.0368 per 1M tokens input
amazon/nova-micro-v1 openrouter generation 0.1474 per 1M tokens output
amazon/nova-pro-v1 openrouter generation 0.8421 per 1M tokens input
amazon/nova-pro-v1 openrouter generation 3.3684 per 1M tokens output
anthracite-org/magnum-v2-72b openrouter generation 3.1579 per 1M tokens input
anthracite-org/magnum-v2-72b openrouter generation 3.1579 per 1M tokens output
anthracite-org/magnum-v4-72b openrouter generation 1.5789 per 1M tokens input
anthracite-org/magnum-v4-72b openrouter generation 2.3684 per 1M tokens output
anthropic/claude-2 openrouter generation 8.4211 per 1M tokens input
anthropic/claude-2 openrouter generation 8.4211 per 1M tokens input
anthropic/claude-2 openrouter generation 25.2632 per 1M tokens output
anthropic/claude-2 openrouter generation 25.2632 per 1M tokens output
anthropic/claude-2.0 openrouter generation 8.4211 per 1M tokens input
anthropic/claude-2.0 openrouter generation 8.4211 per 1M tokens input
anthropic/claude-2.0 openrouter generation 25.2632 per 1M tokens output
anthropic/claude-2.0 openrouter generation 25.2632 per 1M tokens output
anthropic/claude-2.1 openrouter generation 8.4211 per 1M tokens input
anthropic/claude-2.1 openrouter generation 8.4211 per 1M tokens input
anthropic/claude-2.1 openrouter generation 25.2632 per 1M tokens output
anthropic/claude-2.1 openrouter generation 25.2632 per 1M tokens output
anthropic/claude-3-haiku openrouter generation 0.2632 per 1M tokens input
anthropic/claude-3-haiku openrouter generation 0.2632 per 1M tokens input
anthropic/claude-3-haiku openrouter generation 1.3158 per 1M tokens output
anthropic/claude-3-haiku openrouter generation 1.3158 per 1M tokens output
anthropic/claude-3-opus openrouter generation 15.7895 per 1M tokens input
anthropic/claude-3-opus openrouter generation 15.7895 per 1M tokens input
anthropic/claude-3-opus openrouter generation 78.9474 per 1M tokens output
anthropic/claude-3-opus openrouter generation 78.9474 per 1M tokens output
anthropic/claude-3-sonnet openrouter generation 3.1579 per 1M tokens input
anthropic/claude-3-sonnet openrouter generation 3.1579 per 1M tokens input
anthropic/claude-3-sonnet openrouter generation 15.7895 per 1M tokens output
anthropic/claude-3-sonnet openrouter generation 15.7895 per 1M tokens output
anthropic/claude-3.5-haiku openrouter generation 0.8421 per 1M tokens input
anthropic/claude-3.5-haiku openrouter generation 0.8421 per 1M tokens input
anthropic/claude-3.5-haiku openrouter generation 4.2105 per 1M tokens output
anthropic/claude-3.5-haiku openrouter generation 4.2105 per 1M tokens output
anthropic/claude-3.5-haiku-20241022 openrouter generation 0.8421 per 1M tokens input
anthropic/claude-3.5-haiku-20241022 openrouter generation 0.8421 per 1M tokens input
anthropic/claude-3.5-haiku-20241022 openrouter generation 4.2105 per 1M tokens output
anthropic/claude-3.5-haiku-20241022 openrouter generation 4.2105 per 1M tokens output
anthropic/claude-3.5-sonnet openrouter generation 3.1579 per 1M tokens input
anthropic/claude-3.5-sonnet openrouter generation 3.1579 per 1M tokens input
anthropic/claude-3.5-sonnet openrouter generation 15.7895 per 1M tokens output
anthropic/claude-3.5-sonnet openrouter generation 15.7895 per 1M tokens output
anthropic/claude-3.5-sonnet-20240620 openrouter generation 3.1579 per 1M tokens input
anthropic/claude-3.5-sonnet-20240620 openrouter generation 3.1579 per 1M tokens input
anthropic/claude-3.5-sonnet-20240620 openrouter generation 15.7895 per 1M tokens output
anthropic/claude-3.5-sonnet-20240620 openrouter generation 15.7895 per 1M tokens output
anthropic/claude-3.7-sonnet openrouter generation 3.1579 per 1M tokens input
anthropic/claude-3.7-sonnet openrouter generation 15.7895 per 1M tokens output
anthropic/claude-3.7-sonnet openrouter generation 3.1579 per 1M tokens input
anthropic/claude-3.7-sonnet openrouter generation 3.1579 per 1M tokens input
anthropic/claude-3.7-sonnet openrouter generation 15.7895 per 1M tokens output
anthropic/claude-3.7-sonnet openrouter generation 15.7895 per 1M tokens output
arliai/qwq-32b-arliai-rpr-v1 openrouter generation 0.0000 per 1M tokens input
arliai/qwq-32b-arliai-rpr-v1 openrouter generation 0.0000 per 1M tokens output
babbage-002 openai fine-tuning 0.8000 per 1M tokens input
babbage-002 openai fine-tuning 1.6000 per 1M tokens input
babbage-002 openai fine-tuning 0.8000 per 1M tokens input
babbage-002 openai fine-tuning 0.8000 per 1M tokens output
babbage-002 openai fine-tuning 1.6000 per 1M tokens output
babbage-002 openai fine-tuning 0.8000 per 1M tokens output
babbage-002 openai fine-tuning 0.4000 per 1M tokens training
babbage-002 openai generation 0.2000 per 1M tokens input
babbage-002 openai generation 0.4000 per 1M tokens input
babbage-002 openai generation 0.2000 per 1M tokens input
babbage-002 openai generation 0.2000 per 1M tokens output
babbage-002 openai generation 0.4000 per 1M tokens output
babbage-002 openai generation 0.2000 per 1M tokens output
bge-base-en-v1.5 deepinfra embeddings 0.0050 per 1M tokens total
bge-large-en-v1.5 deepinfra embeddings 0.0100 per 1M tokens total
black-forest-labs/flux-dev nebius image-generation 0.0070 per image input
black-forest-labs/flux-schnell nebius image-generation 0.0013 per image input
bytedance-research/ui-tars-72b openrouter generation 0.0000 per 1M tokens input
bytedance-research/ui-tars-72b openrouter generation 0.0000 per 1M tokens output
chatgpt-4o-latest openai generation 5.0000 per 1M tokens input
chatgpt-4o-latest openai generation 15.0000 per 1M tokens output
cognitivecomputations/dolphin-mixtral-8x22b openrouter generation 0.9474 per 1M tokens input
cognitivecomputations/dolphin-mixtral-8x22b openrouter generation 0.9474 per 1M tokens output
cognitivecomputations/dolphin3.0-mistral-24b openrouter generation 0.0000 per 1M tokens input
cognitivecomputations/dolphin3.0-mistral-24b openrouter generation 0.0000 per 1M tokens output
cognitivecomputations/dolphin3.0-r1-mistral-24b openrouter generation 0.0000 per 1M tokens input
cognitivecomputations/dolphin3.0-r1-mistral-24b openrouter generation 0.0000 per 1M tokens output
cohere/command openrouter generation 1.0526 per 1M tokens input
cohere/command openrouter generation 2.1053 per 1M tokens output
cohere/command-a openrouter generation 2.6316 per 1M tokens input
cohere/command-a openrouter generation 10.5263 per 1M tokens output
cohere/command-r openrouter generation 0.5263 per 1M tokens input
cohere/command-r openrouter generation 1.5789 per 1M tokens output
cohere/command-r-03-2024 openrouter generation 0.5263 per 1M tokens input
cohere/command-r-03-2024 openrouter generation 1.5789 per 1M tokens output
cohere/command-r-08-2024 openrouter generation 0.1579 per 1M tokens input
cohere/command-r-08-2024 openrouter generation 0.6316 per 1M tokens output
cohere/command-r-plus openrouter generation 3.1579 per 1M tokens input
cohere/command-r-plus openrouter generation 15.7895 per 1M tokens output
cohere/command-r-plus-04-2024 openrouter generation 3.1579 per 1M tokens input
cohere/command-r-plus-04-2024 openrouter generation 15.7895 per 1M tokens output
cohere/command-r-plus-08-2024 openrouter generation 2.6316 per 1M tokens input
cohere/command-r-plus-08-2024 openrouter generation 10.5263 per 1M tokens output
cohere/command-r7b-12-2024 openrouter generation 0.0395 per 1M tokens input
cohere/command-r7b-12-2024 openrouter generation 0.1579 per 1M tokens output
computer-use-preview openai generation 1.5000 per 1M tokens input
computer-use-preview openai generation 3.0000 per 1M tokens input
computer-use-preview openai generation 1.5000 per 1M tokens input
computer-use-preview openai generation 6.0000 per 1M tokens output
computer-use-preview openai generation 12.0000 per 1M tokens output
computer-use-preview openai generation 6.0000 per 1M tokens output
davinci-002 openai fine-tuning 6.0000 per 1M tokens input
davinci-002 openai fine-tuning 12.0000 per 1M tokens input
davinci-002 openai fine-tuning 6.0000 per 1M tokens input
davinci-002 openai fine-tuning 6.0000 per 1M tokens output
davinci-002 openai fine-tuning 12.0000 per 1M tokens output
davinci-002 openai fine-tuning 6.0000 per 1M tokens output
davinci-002 openai fine-tuning 6.0000 per 1M tokens training
davinci-002 openai generation 1.0000 per 1M tokens input
davinci-002 openai generation 2.0000 per 1M tokens input
davinci-002 openai generation 1.0000 per 1M tokens input
davinci-002 openai generation 1.0000 per 1M tokens output
davinci-002 openai generation 2.0000 per 1M tokens output
davinci-002 openai generation 1.0000 per 1M tokens output
deepseek-ai/DeepSeek-Coder-V2-Lite-Instruct-FP8 nebius generation 0.0400 per 1M tokens input
deepseek-ai/DeepSeek-Coder-V2-Lite-Instruct-FP8 nebius generation 0.0800 per 1M tokens input
deepseek-ai/DeepSeek-Coder-V2-Lite-Instruct-FP8 nebius generation 0.1200 per 1M tokens output
deepseek-ai/DeepSeek-Coder-V2-Lite-Instruct-FP8 nebius generation 0.2400 per 1M tokens output
deepseek-ai/DeepSeek-R1 nebius generation 0.8000 per 1M tokens input
deepseek-ai/DeepSeek-R1 nebius generation 2.4000 per 1M tokens output
deepseek-ai/DeepSeek-R1-Distill-Llama-70B nebius generation 0.2500 per 1M tokens input
deepseek-ai/DeepSeek-R1-Distill-Llama-70B nebius generation 0.7500 per 1M tokens output
deepseek-ai/DeepSeek-V3 nebius generation 0.5000 per 1M tokens input
deepseek-ai/DeepSeek-V3 nebius generation 1.5000 per 1M tokens output
deepseek-ai/DeepSeek-V3-0324 nebius generation 0.5000 per 1M tokens input
deepseek-ai/DeepSeek-V3-0324 nebius generation 2.0000 per 1M tokens input
deepseek-ai/DeepSeek-V3-0324 nebius generation 1.5000 per 1M tokens output
deepseek-ai/DeepSeek-V3-0324 nebius generation 6.0000 per 1M tokens output
deepseek/deepseek-chat openrouter generation 0.0000 per 1M tokens input
deepseek/deepseek-chat openrouter generation 0.4000 per 1M tokens input
deepseek/deepseek-chat openrouter generation 0.0000 per 1M tokens output
deepseek/deepseek-chat openrouter generation 0.9368 per 1M tokens output
deepseek/deepseek-chat-v3-0324 openrouter generation 0.0000 per 1M tokens input
deepseek/deepseek-chat-v3-0324 openrouter generation 0.0000 per 1M tokens output
deepseek/deepseek-chat-v3-0324 openrouter generation 0.2842 per 1M tokens input
deepseek/deepseek-chat-v3-0324 openrouter generation 1.1579 per 1M tokens output
deepseek/deepseek-coder openrouter generation 0.0421 per 1M tokens input
deepseek/deepseek-coder openrouter generation 0.1263 per 1M tokens output
deepseek/deepseek-prover-v2 openrouter generation 0.0000 per 1M tokens input
deepseek/deepseek-prover-v2 openrouter generation 0.5263 per 1M tokens input
deepseek/deepseek-prover-v2 openrouter generation 0.0000 per 1M tokens output
deepseek/deepseek-prover-v2 openrouter generation 2.2947 per 1M tokens output
deepseek/deepseek-r1 openrouter generation 0.0000 per 1M tokens input
deepseek/deepseek-r1 openrouter generation 0.5263 per 1M tokens input
deepseek/deepseek-r1 openrouter generation 0.0000 per 1M tokens output
deepseek/deepseek-r1 openrouter generation 2.2947 per 1M tokens output
deepseek/deepseek-r1-distill-llama-70b openrouter generation 0.1053 per 1M tokens input
deepseek/deepseek-r1-distill-llama-70b openrouter generation 0.4211 per 1M tokens output
deepseek/deepseek-r1-distill-llama-70b openrouter generation 0.0000 per 1M tokens input
deepseek/deepseek-r1-distill-llama-70b openrouter generation 0.0000 per 1M tokens output
deepseek/deepseek-r1-distill-llama-8b openrouter generation 0.0421 per 1M tokens input
deepseek/deepseek-r1-distill-llama-8b openrouter generation 0.0421 per 1M tokens output
deepseek/deepseek-r1-distill-qwen-1.5b openrouter generation 0.1895 per 1M tokens input
deepseek/deepseek-r1-distill-qwen-1.5b openrouter generation 0.1895 per 1M tokens output
deepseek/deepseek-r1-distill-qwen-14b openrouter generation 0.0000 per 1M tokens input
deepseek/deepseek-r1-distill-qwen-14b openrouter generation 0.0000 per 1M tokens output
deepseek/deepseek-r1-distill-qwen-14b openrouter generation 0.1579 per 1M tokens input
deepseek/deepseek-r1-distill-qwen-14b openrouter generation 0.1579 per 1M tokens output
deepseek/deepseek-r1-distill-qwen-32b openrouter generation 0.0000 per 1M tokens input
deepseek/deepseek-r1-distill-qwen-32b openrouter generation 0.0000 per 1M tokens output
deepseek/deepseek-r1-distill-qwen-32b openrouter generation 0.1263 per 1M tokens input
deepseek/deepseek-r1-distill-qwen-32b openrouter generation 0.1895 per 1M tokens output
deepseek/deepseek-r1-zero openrouter generation 0.0000 per 1M tokens input
deepseek/deepseek-r1-zero openrouter generation 0.0000 per 1M tokens output
deepseek/deepseek-v3-base openrouter generation 0.0000 per 1M tokens input
deepseek/deepseek-v3-base openrouter generation 0.0000 per 1M tokens output
e5-base-v2 deepinfra embeddings 0.0050 per 1M tokens total
e5-large-v2 deepinfra embeddings 0.0100 per 1M tokens total
eleutherai/llemma_7b openrouter generation 0.8421 per 1M tokens input
eleutherai/llemma_7b openrouter generation 1.2632 per 1M tokens output
eva-unit-01/eva-llama-3.33-70b openrouter generation 4.2105 per 1M tokens input
eva-unit-01/eva-llama-3.33-70b openrouter generation 6.3158 per 1M tokens output
eva-unit-01/eva-qwen-2.5-32b openrouter generation 2.7368 per 1M tokens input
eva-unit-01/eva-qwen-2.5-32b openrouter generation 3.5789 per 1M tokens output
eva-unit-01/eva-qwen-2.5-72b openrouter generation 4.2105 per 1M tokens input
eva-unit-01/eva-qwen-2.5-72b openrouter generation 6.3158 per 1M tokens output
featherless/qwerky-72b openrouter generation 0.0000 per 1M tokens input
featherless/qwerky-72b openrouter generation 0.0000 per 1M tokens output
google/gemini-2.0-flash-001 openrouter generation 0.1053 per 1M tokens input
google/gemini-2.0-flash-001 openrouter generation 0.4211 per 1M tokens output
google/gemini-2.0-flash-exp openrouter generation 0.0000 per 1M tokens input
google/gemini-2.0-flash-exp openrouter generation 0.0000 per 1M tokens output
google/gemini-2.0-flash-lite-001 openrouter generation 0.0789 per 1M tokens input
google/gemini-2.0-flash-lite-001 openrouter generation 0.3158 per 1M tokens output
google/gemini-2.5-flash-preview openrouter generation 0.1579 per 1M tokens input
google/gemini-2.5-flash-preview openrouter generation 0.1579 per 1M tokens input
google/gemini-2.5-flash-preview openrouter generation 0.6316 per 1M tokens output
google/gemini-2.5-flash-preview openrouter generation 3.6842 per 1M tokens output
google/gemini-2.5-pro-exp-03-25 openrouter generation 0.0000 per 1M tokens input
google/gemini-2.5-pro-exp-03-25 openrouter generation 0.0000 per 1M tokens output
google/gemini-2.5-pro-preview-03-25 openrouter generation 1.3158 per 1M tokens input
google/gemini-2.5-pro-preview-03-25 openrouter generation 10.5263 per 1M tokens output
google/gemini-flash-1.5 openrouter generation 0.0789 per 1M tokens input
google/gemini-flash-1.5 openrouter generation 0.3158 per 1M tokens output
google/gemini-flash-1.5-8b openrouter generation 0.0395 per 1M tokens input
google/gemini-flash-1.5-8b openrouter generation 0.1579 per 1M tokens output
google/gemini-flash-1.5-8b-exp openrouter generation 0.0000 per 1M tokens input
google/gemini-flash-1.5-8b-exp openrouter generation 0.0000 per 1M tokens output
google/gemini-pro-1.5 openrouter generation 1.3158 per 1M tokens input
google/gemini-pro-1.5 openrouter generation 5.2632 per 1M tokens output
google/gemini-pro-vision openrouter generation 0.5263 per 1M tokens input
google/gemini-pro-vision openrouter generation 1.5789 per 1M tokens output
google/gemma-2-27b-it openrouter generation 0.1053 per 1M tokens input
google/gemma-2-27b-it openrouter generation 0.3158 per 1M tokens output
google/gemma-2-9b-it openrouter generation 0.0211 per 1M tokens input
google/gemma-2-9b-it openrouter generation 0.0632 per 1M tokens output
google/gemma-2-9b-it openrouter generation 0.0000 per 1M tokens input
google/gemma-2-9b-it openrouter generation 0.0000 per 1M tokens output
google/gemma-3-12b-it openrouter generation 0.0526 per 1M tokens input
google/gemma-3-12b-it openrouter generation 0.1053 per 1M tokens output
google/gemma-3-12b-it openrouter generation 0.0000 per 1M tokens input
google/gemma-3-12b-it openrouter generation 0.0000 per 1M tokens output
google/gemma-3-1b-it openrouter generation 0.0000 per 1M tokens input
google/gemma-3-1b-it openrouter generation 0.0000 per 1M tokens output
google/gemma-3-27b-it nebius vision 0.1000 per 1M tokens input
google/gemma-3-27b-it nebius vision 0.3000 per 1M tokens output
google/gemma-3-27b-it openrouter generation 0.1053 per 1M tokens input
google/gemma-3-27b-it openrouter generation 0.2105 per 1M tokens output
google/gemma-3-27b-it openrouter generation 0.0000 per 1M tokens input
google/gemma-3-27b-it openrouter generation 0.0000 per 1M tokens output
google/gemma-3-27b-it-fast nebius vision 0.2000 per 1M tokens input
google/gemma-3-27b-it-fast nebius vision 0.6000 per 1M tokens output
google/gemma-3-4b-it openrouter generation 0.0211 per 1M tokens input
google/gemma-3-4b-it openrouter generation 0.0421 per 1M tokens output
google/gemma-3-4b-it openrouter generation 0.0000 per 1M tokens input
google/gemma-3-4b-it openrouter generation 0.0000 per 1M tokens output
google/learnlm-1.5-pro-experimental openrouter generation 0.0000 per 1M tokens input
google/learnlm-1.5-pro-experimental openrouter generation 0.0000 per 1M tokens output
gpt-3.5-turbo openai fine-tuning 1.5000 per 1M tokens input
gpt-3.5-turbo openai fine-tuning 3.0000 per 1M tokens input
gpt-3.5-turbo openai fine-tuning 1.5000 per 1M tokens input
gpt-3.5-turbo openai fine-tuning 3.0000 per 1M tokens output
gpt-3.5-turbo openai fine-tuning 6.0000 per 1M tokens output
gpt-3.5-turbo openai fine-tuning 3.0000 per 1M tokens output
gpt-3.5-turbo openai fine-tuning 8.0000 per 1M tokens training
gpt-3.5-turbo openai generation 0.7500 per 1M tokens input
gpt-3.5-turbo openai generation 1.5000 per 1M tokens input
gpt-3.5-turbo openai generation 0.7500 per 1M tokens input
gpt-3.5-turbo openai generation 1.0000 per 1M tokens output
gpt-3.5-turbo openai generation 2.0000 per 1M tokens output
gpt-3.5-turbo openai generation 1.0000 per 1M tokens output
gpt-3.5-turbo openai generation 0.2500 per 1M tokens input
gpt-3.5-turbo openai generation 0.5000 per 1M tokens input
gpt-3.5-turbo openai generation 0.2500 per 1M tokens input
gpt-3.5-turbo openai generation 0.7500 per 1M tokens output
gpt-3.5-turbo openai generation 1.5000 per 1M tokens output
gpt-3.5-turbo openai generation 0.7500 per 1M tokens output
gpt-3.5-turbo openai generation 0.7500 per 1M tokens input
gpt-3.5-turbo openai generation 1.5000 per 1M tokens input
gpt-3.5-turbo openai generation 0.7500 per 1M tokens input
gpt-3.5-turbo openai generation 1.0000 per 1M tokens output
gpt-3.5-turbo openai generation 2.0000 per 1M tokens output
gpt-3.5-turbo openai generation 1.0000 per 1M tokens output
gpt-3.5-turbo openai generation 0.5000 per 1M tokens input
gpt-3.5-turbo openai generation 1.0000 per 1M tokens input
gpt-3.5-turbo openai generation 0.5000 per 1M tokens input
gpt-3.5-turbo openai generation 1.0000 per 1M tokens output
gpt-3.5-turbo openai generation 2.0000 per 1M tokens output
gpt-3.5-turbo openai generation 1.0000 per 1M tokens output
gpt-3.5-turbo-16k-0613 openai generation 1.5000 per 1M tokens input
gpt-3.5-turbo-16k-0613 openai generation 3.0000 per 1M tokens input
gpt-3.5-turbo-16k-0613 openai generation 1.5000 per 1M tokens input
gpt-3.5-turbo-16k-0613 openai generation 2.0000 per 1M tokens output
gpt-3.5-turbo-16k-0613 openai generation 4.0000 per 1M tokens output
gpt-3.5-turbo-16k-0613 openai generation 2.0000 per 1M tokens output
gpt-3.5-turbo-instruct openai generation 1.5000 per 1M tokens input
gpt-3.5-turbo-instruct openai generation 2.0000 per 1M tokens output
gpt-4 openai generation 15.0000 per 1M tokens input
gpt-4 openai generation 30.0000 per 1M tokens input
gpt-4 openai generation 15.0000 per 1M tokens input
gpt-4 openai generation 30.0000 per 1M tokens output
gpt-4 openai generation 60.0000 per 1M tokens output
gpt-4 openai generation 30.0000 per 1M tokens output
gpt-4 openai generation 15.0000 per 1M tokens input
gpt-4 openai generation 30.0000 per 1M tokens input
gpt-4 openai generation 15.0000 per 1M tokens input
gpt-4 openai generation 30.0000 per 1M tokens output
gpt-4 openai generation 60.0000 per 1M tokens output
gpt-4 openai generation 30.0000 per 1M tokens output
gpt-4-32k openai generation 30.0000 per 1M tokens input
gpt-4-32k openai generation 60.0000 per 1M tokens input
gpt-4-32k openai generation 30.0000 per 1M tokens input
gpt-4-32k openai generation 60.0000 per 1M tokens output
gpt-4-32k openai generation 120.0000 per 1M tokens output
gpt-4-32k openai generation 60.0000 per 1M tokens output
gpt-4-turbo openai generation 5.0000 per 1M tokens input
gpt-4-turbo openai generation 10.0000 per 1M tokens input
gpt-4-turbo openai generation 5.0000 per 1M tokens input
gpt-4-turbo openai generation 15.0000 per 1M tokens output
gpt-4-turbo openai generation 30.0000 per 1M tokens output
gpt-4-turbo openai generation 15.0000 per 1M tokens output
gpt-4-turbo openai generation 5.0000 per 1M tokens input
gpt-4-turbo openai generation 10.0000 per 1M tokens input
gpt-4-turbo openai generation 5.0000 per 1M tokens input
gpt-4-turbo openai generation 15.0000 per 1M tokens output
gpt-4-turbo openai generation 30.0000 per 1M tokens output
gpt-4-turbo openai generation 15.0000 per 1M tokens output
gpt-4-turbo openai generation 5.0000 per 1M tokens input
gpt-4-turbo openai generation 10.0000 per 1M tokens input
gpt-4-turbo openai generation 5.0000 per 1M tokens input
gpt-4-turbo openai generation 15.0000 per 1M tokens output
gpt-4-turbo openai generation 30.0000 per 1M tokens output
gpt-4-turbo openai generation 15.0000 per 1M tokens output
gpt-4-turbo openai generation 5.0000 per 1M tokens input
gpt-4-turbo openai generation 10.0000 per 1M tokens input
gpt-4-turbo openai generation 5.0000 per 1M tokens input
gpt-4-turbo openai generation 15.0000 per 1M tokens output
gpt-4-turbo openai generation 30.0000 per 1M tokens output
gpt-4-turbo openai generation 15.0000 per 1M tokens output
gpt-4.1 openai generation 1.0000 per 1M tokens input
gpt-4.1 openai generation 2.0000 per 1M tokens input
gpt-4.1 openai generation 1.0000 per 1M tokens input
gpt-4.1 openai generation 4.0000 per 1M tokens output
gpt-4.1 openai generation 8.0000 per 1M tokens output
gpt-4.1 openai generation 4.0000 per 1M tokens output
gpt-4.1-2025-04-14 openai fine-tuning 1.5000 per 1M tokens input
gpt-4.1-2025-04-14 openai fine-tuning 3.0000 per 1M tokens input
gpt-4.1-2025-04-14 openai fine-tuning 1.5000 per 1M tokens input
gpt-4.1-2025-04-14 openai fine-tuning 6.0000 per 1M tokens output
gpt-4.1-2025-04-14 openai fine-tuning 12.0000 per 1M tokens output
gpt-4.1-2025-04-14 openai fine-tuning 6.0000 per 1M tokens output
gpt-4.1-2025-04-14 openai fine-tuning 25.0000 per 1M tokens training
gpt-4.1-mini openai generation 0.2000 per 1M tokens input
gpt-4.1-mini openai generation 0.4000 per 1M tokens input
gpt-4.1-mini openai generation 0.2000 per 1M tokens input
gpt-4.1-mini openai generation 0.8000 per 1M tokens output
gpt-4.1-mini openai generation 1.6000 per 1M tokens output
gpt-4.1-mini openai generation 0.8000 per 1M tokens output
gpt-4.1-mini-2025-04-14 openai fine-tuning 0.4000 per 1M tokens input
gpt-4.1-mini-2025-04-14 openai fine-tuning 0.8000 per 1M tokens input
gpt-4.1-mini-2025-04-14 openai fine-tuning 0.4000 per 1M tokens input
gpt-4.1-mini-2025-04-14 openai fine-tuning 1.6000 per 1M tokens output
gpt-4.1-mini-2025-04-14 openai fine-tuning 3.2000 per 1M tokens output
gpt-4.1-mini-2025-04-14 openai fine-tuning 1.6000 per 1M tokens output
gpt-4.1-mini-2025-04-14 openai fine-tuning 5.0000 per 1M tokens training
gpt-4.1-nano openai generation 0.0500 per 1M tokens input
gpt-4.1-nano openai generation 0.1000 per 1M tokens input
gpt-4.1-nano openai generation 0.0500 per 1M tokens input
gpt-4.1-nano openai generation 0.2000 per 1M tokens output
gpt-4.1-nano openai generation 0.4000 per 1M tokens output
gpt-4.1-nano openai generation 0.2000 per 1M tokens output
gpt-4.5-preview openai generation 37.5000 per 1M tokens input
gpt-4.5-preview openai generation 75.0000 per 1M tokens input
gpt-4.5-preview openai generation 37.5000 per 1M tokens input
gpt-4.5-preview openai generation 75.0000 per 1M tokens output
gpt-4.5-preview openai generation 150.0000 per 1M tokens output
gpt-4.5-preview openai generation 75.0000 per 1M tokens output
gpt-4o openai generation 2.5000 per 1M tokens input
gpt-4o openai generation 5.0000 per 1M tokens input
gpt-4o openai generation 2.5000 per 1M tokens input
gpt-4o openai generation 7.5000 per 1M tokens output
gpt-4o openai generation 15.0000 per 1M tokens output
gpt-4o openai generation 7.5000 per 1M tokens output
gpt-4o openai generation 1.2500 per 1M tokens input
gpt-4o openai generation 2.5000 per 1M tokens input
gpt-4o openai generation 1.2500 per 1M tokens input
gpt-4o openai generation 5.0000 per 1M tokens output
gpt-4o openai generation 10.0000 per 1M tokens output
gpt-4o openai generation 5.0000 per 1M tokens output
gpt-4o openai generation 1.2500 per 1M tokens input
gpt-4o openai generation 2.5000 per 1M tokens input
gpt-4o openai generation 1.2500 per 1M tokens input
gpt-4o openai generation 5.0000 per 1M tokens output
gpt-4o openai generation 10.0000 per 1M tokens output
gpt-4o openai generation 5.0000 per 1M tokens output
gpt-4o-2024-08-06 openai fine-tuning 1.8750 per 1M tokens input
gpt-4o-2024-08-06 openai fine-tuning 3.7500 per 1M tokens input
gpt-4o-2024-08-06 openai fine-tuning 1.8750 per 1M tokens input
gpt-4o-2024-08-06 openai fine-tuning 7.5000 per 1M tokens output
gpt-4o-2024-08-06 openai fine-tuning 15.0000 per 1M tokens output
gpt-4o-2024-08-06 openai fine-tuning 7.5000 per 1M tokens output
gpt-4o-2024-08-06 openai fine-tuning 25.0000 per 1M tokens training
gpt-4o-audio-preview openai generation 100.0000 per 1M audio tokens input
gpt-4o-audio-preview openai generation 100.0000 per 1M audio tokens input
gpt-4o-audio-preview openai generation 2.5000 per 1M tokens input
gpt-4o-audio-preview openai generation 100.0000 per 1M audio tokens input
gpt-4o-audio-preview openai generation 200.0000 per 1M audio tokens output
gpt-4o-audio-preview openai generation 200.0000 per 1M audio tokens output
gpt-4o-audio-preview openai generation 10.0000 per 1M tokens output
gpt-4o-audio-preview openai generation 200.0000 per 1M audio tokens output
gpt-4o-audio-preview openai generation 40.0000 per 1M audio tokens input
gpt-4o-audio-preview openai generation 40.0000 per 1M audio tokens input
gpt-4o-audio-preview openai generation 2.5000 per 1M tokens input
gpt-4o-audio-preview openai generation 40.0000 per 1M audio tokens input
gpt-4o-audio-preview openai generation 80.0000 per 1M audio tokens output
gpt-4o-audio-preview openai generation 80.0000 per 1M audio tokens output
gpt-4o-audio-preview openai generation 10.0000 per 1M tokens output
gpt-4o-audio-preview openai generation 80.0000 per 1M audio tokens output
gpt-4o-mini openai generation 0.0750 per 1M tokens input
gpt-4o-mini openai generation 0.1500 per 1M tokens input
gpt-4o-mini openai generation 0.0750 per 1M tokens input
gpt-4o-mini openai generation 0.3000 per 1M tokens output
gpt-4o-mini openai generation 0.6000 per 1M tokens output
gpt-4o-mini openai generation 0.3000 per 1M tokens output
gpt-4o-mini-2024-07-18 openai fine-tuning 0.1500 per 1M tokens input
gpt-4o-mini-2024-07-18 openai fine-tuning 0.3000 per 1M tokens input
gpt-4o-mini-2024-07-18 openai fine-tuning 0.1500 per 1M tokens input
gpt-4o-mini-2024-07-18 openai fine-tuning 0.6000 per 1M tokens output
gpt-4o-mini-2024-07-18 openai fine-tuning 1.2000 per 1M tokens output
gpt-4o-mini-2024-07-18 openai fine-tuning 0.6000 per 1M tokens output
gpt-4o-mini-2024-07-18 openai fine-tuning 3.0000 per 1M tokens training
gpt-4o-mini-audio-preview openai generation 10.0000 per 1M audio tokens input
gpt-4o-mini-audio-preview openai generation 10.0000 per 1M audio tokens input
gpt-4o-mini-audio-preview openai generation 0.1500 per 1M tokens input
gpt-4o-mini-audio-preview openai generation 10.0000 per 1M audio tokens input
gpt-4o-mini-audio-preview openai generation 20.0000 per 1M audio tokens output
gpt-4o-mini-audio-preview openai generation 20.0000 per 1M audio tokens output
gpt-4o-mini-audio-preview openai generation 0.6000 per 1M tokens output
gpt-4o-mini-audio-preview openai generation 20.0000 per 1M audio tokens output
gpt-4o-mini-realtime-preview openai generation 10.0000 per 1M audio tokens input
gpt-4o-mini-realtime-preview openai generation 10.0000 per 1M audio tokens input
gpt-4o-mini-realtime-preview openai generation 0.6000 per 1M tokens input
gpt-4o-mini-realtime-preview openai generation 10.0000 per 1M audio tokens input
gpt-4o-mini-realtime-preview openai generation 20.0000 per 1M audio tokens output
gpt-4o-mini-realtime-preview openai generation 20.0000 per 1M audio tokens output
gpt-4o-mini-realtime-preview openai generation 2.4000 per 1M tokens output
gpt-4o-mini-realtime-preview openai generation 20.0000 per 1M audio tokens output
gpt-4o-mini-search-preview openai generation 0.1500 per 1M tokens input
gpt-4o-mini-search-preview openai generation 0.6000 per 1M tokens output
gpt-4o-mini-transcribe openai generation 3.0000 per 1M audio tokens input
gpt-4o-mini-transcribe openai generation 1.2500 per 1M text tokens input
gpt-4o-mini-transcribe openai generation 5.0000 per 1M text tokens output
gpt-4o-mini-transcribe openai generation 0.0030 per audio minute total
gpt-4o-mini-tts openai generation 0.6000 per 1M text tokens input
gpt-4o-mini-tts openai generation 12.0000 per 1M audio tokens output
gpt-4o-mini-tts openai generation 0.0150 per audio minute total
gpt-4o-realtime-preview openai generation 100.0000 per 1M audio tokens input
gpt-4o-realtime-preview openai generation 100.0000 per 1M audio tokens input
gpt-4o-realtime-preview openai generation 5.0000 per 1M tokens input
gpt-4o-realtime-preview openai generation 100.0000 per 1M audio tokens input
gpt-4o-realtime-preview openai generation 200.0000 per 1M audio tokens output
gpt-4o-realtime-preview openai generation 200.0000 per 1M audio tokens output
gpt-4o-realtime-preview openai generation 20.0000 per 1M tokens output
gpt-4o-realtime-preview openai generation 200.0000 per 1M audio tokens output
gpt-4o-realtime-preview openai generation 40.0000 per 1M audio tokens input
gpt-4o-realtime-preview openai generation 40.0000 per 1M audio tokens input
gpt-4o-realtime-preview openai generation 5.0000 per 1M tokens input
gpt-4o-realtime-preview openai generation 40.0000 per 1M audio tokens input
gpt-4o-realtime-preview openai generation 80.0000 per 1M audio tokens output
gpt-4o-realtime-preview openai generation 80.0000 per 1M audio tokens output
gpt-4o-realtime-preview openai generation 20.0000 per 1M tokens output
gpt-4o-realtime-preview openai generation 80.0000 per 1M audio tokens output
gpt-4o-search-preview openai generation 2.5000 per 1M tokens input
gpt-4o-search-preview openai generation 10.0000 per 1M tokens output
gpt-4o-transcribe openai generation 6.0000 per 1M audio tokens input
gpt-4o-transcribe openai generation 2.5000 per 1M text tokens input
gpt-4o-transcribe openai generation 10.0000 per 1M text tokens output
gpt-4o-transcribe openai generation 0.0060 per audio minute total
gpt-image-1 openai generation 10.0000 per 1M image tokens input
gpt-image-1 openai generation 10.0000 per 1M image tokens input
gpt-image-1 openai generation 5.0000 per 1M tokens input
gpt-image-1 openai generation 10.0000 per 1M image tokens input
gpt-image-1 openai generation 40.0000 per 1M image tokens output
gpt-image-1 openai generation 40.0000 per 1M image tokens output
gpt-image-1 openai generation 40.0000 per 1M image tokens output
gryphe/mythomax-l2-13b openrouter generation 0.0684 per 1M tokens input
gryphe/mythomax-l2-13b openrouter generation 0.0684 per 1M tokens output
gte-base deepinfra embeddings 0.0050 per 1M tokens total
gte-large deepinfra embeddings 0.0100 per 1M tokens total
huggingfaceh4/zephyr-7b-beta openrouter generation 0.0000 per 1M tokens input
huggingfaceh4/zephyr-7b-beta openrouter generation 0.0000 per 1M tokens output
inception/mercury-coder-small-beta openrouter generation 0.2632 per 1M tokens input
inception/mercury-coder-small-beta openrouter generation 1.0526 per 1M tokens output
infermatic/mn-inferor-12b openrouter generation 0.8421 per 1M tokens input
infermatic/mn-inferor-12b openrouter generation 1.2632 per 1M tokens output
inflection/inflection-3-pi openrouter generation 2.6316 per 1M tokens input
inflection/inflection-3-pi openrouter generation 10.5263 per 1M tokens output
inflection/inflection-3-productivity openrouter generation 2.6316 per 1M tokens input
inflection/inflection-3-productivity openrouter generation 10.5263 per 1M tokens output
intfloat/e5-mistral-7b-instruct nebius embeddings 0.0100 per 1M tokens input
jondurbin/airoboros-l2-70b openrouter generation 0.5263 per 1M tokens input
jondurbin/airoboros-l2-70b openrouter generation 0.5263 per 1M tokens output
liquid/lfm-3b openrouter generation 0.0211 per 1M tokens input
liquid/lfm-3b openrouter generation 0.0211 per 1M tokens output
liquid/lfm-40b openrouter generation 0.1579 per 1M tokens input
liquid/lfm-40b openrouter generation 0.1579 per 1M tokens output
liquid/lfm-7b openrouter generation 0.0105 per 1M tokens input
liquid/lfm-7b openrouter generation 0.0105 per 1M tokens output
llava-1.5-7B-HF nebius generation 0.0400 per 1M tokens input
llava-1.5-7B-HF nebius generation 0.1200 per 1M tokens output
llava-v1.5-13B nebius generation 0.0400 per 1M tokens input
llava-v1.5-13B nebius generation 0.1200 per 1M tokens output
m42-health/Llama3-Med42-8B nebius generation 0.0200 per 1M tokens input
m42-health/Llama3-Med42-8B nebius generation 0.0600 per 1M tokens output
mancer/weaver openrouter generation 1.1842 per 1M tokens input
mancer/weaver openrouter generation 1.1842 per 1M tokens output
meta-llama/llama-2-70b-chat openrouter generation 0.9474 per 1M tokens input
meta-llama/llama-2-70b-chat openrouter generation 0.9474 per 1M tokens output
meta-llama/llama-3-70b-instruct openrouter generation 0.3158 per 1M tokens input
meta-llama/llama-3-70b-instruct openrouter generation 0.4211 per 1M tokens output
meta-llama/llama-3-8b-instruct openrouter generation 0.0316 per 1M tokens input
meta-llama/llama-3-8b-instruct openrouter generation 0.0632 per 1M tokens output
meta-llama/llama-3.1-405b openrouter generation 0.0000 per 1M tokens input
meta-llama/llama-3.1-405b openrouter generation 0.0000 per 1M tokens output
meta-llama/llama-3.1-405b openrouter generation 2.1053 per 1M tokens input
meta-llama/llama-3.1-405b openrouter generation 2.1053 per 1M tokens output
meta-llama/llama-3.1-405b-instruct openrouter generation 0.8421 per 1M tokens input
meta-llama/llama-3.1-405b-instruct openrouter generation 0.8421 per 1M tokens output
meta-llama/llama-3.1-70b-instruct openrouter generation 0.1053 per 1M tokens input
meta-llama/llama-3.1-70b-instruct openrouter generation 0.2947 per 1M tokens output
meta-llama/llama-3.1-8b-instruct openrouter generation 0.0000 per 1M tokens input
meta-llama/llama-3.1-8b-instruct openrouter generation 0.0000 per 1M tokens output
meta-llama/llama-3.1-8b-instruct openrouter generation 0.0211 per 1M tokens input
meta-llama/llama-3.1-8b-instruct openrouter generation 0.0316 per 1M tokens output
meta-llama/llama-3.2-11b-vision-instruct openrouter generation 0.0516 per 1M tokens input
meta-llama/llama-3.2-11b-vision-instruct openrouter generation 0.0516 per 1M tokens output
meta-llama/llama-3.2-11b-vision-instruct openrouter generation 0.0000 per 1M tokens input
meta-llama/llama-3.2-11b-vision-instruct openrouter generation 0.0000 per 1M tokens output
meta-llama/llama-3.2-1b-instruct openrouter generation 0.0053 per 1M tokens input
meta-llama/llama-3.2-1b-instruct openrouter generation 0.0105 per 1M tokens output
meta-llama/llama-3.2-1b-instruct openrouter generation 0.0000 per 1M tokens input
meta-llama/llama-3.2-1b-instruct openrouter generation 0.0000 per 1M tokens output
meta-llama/llama-3.2-3b-instruct openrouter generation 0.0105 per 1M tokens input
meta-llama/llama-3.2-3b-instruct openrouter generation 0.0211 per 1M tokens output
meta-llama/llama-3.2-3b-instruct openrouter generation 0.0000 per 1M tokens input
meta-llama/llama-3.2-3b-instruct openrouter generation 0.0000 per 1M tokens output
meta-llama/llama-3.2-90b-vision-instruct openrouter generation 1.2632 per 1M tokens input
meta-llama/llama-3.2-90b-vision-instruct openrouter generation 1.2632 per 1M tokens output
meta-llama/llama-3.3-70b-instruct openrouter generation 0.0000 per 1M tokens input
meta-llama/llama-3.3-70b-instruct openrouter generation 0.0000 per 1M tokens output
meta-llama/llama-3.3-70b-instruct openrouter generation 0.1053 per 1M tokens input
meta-llama/llama-3.3-70b-instruct openrouter generation 0.2632 per 1M tokens output
meta-llama/llama-4-maverick openrouter generation 0.0000 per 1M tokens input
meta-llama/llama-4-maverick openrouter generation 0.0000 per 1M tokens output
meta-llama/llama-4-maverick openrouter generation 0.1789 per 1M tokens input
meta-llama/llama-4-maverick openrouter generation 0.6316 per 1M tokens output
meta-llama/llama-4-scout openrouter generation 0.0000 per 1M tokens input
meta-llama/llama-4-scout openrouter generation 0.0000 per 1M tokens output
meta-llama/llama-4-scout openrouter generation 0.0842 per 1M tokens input
meta-llama/llama-4-scout openrouter generation 0.3158 per 1M tokens output
meta-llama/llama-guard-2-8b openrouter generation 0.2105 per 1M tokens input
meta-llama/llama-guard-2-8b openrouter generation 0.2105 per 1M tokens output
meta-llama/llama-guard-3-8b openrouter generation 0.0211 per 1M tokens input
meta-llama/llama-guard-3-8b openrouter generation 0.0632 per 1M tokens output
meta-llama/llama-guard-4-12b openrouter generation 0.0526 per 1M tokens input
meta-llama/llama-guard-4-12b openrouter generation 0.0526 per 1M tokens output
microsoft/mai-ds-r1 openrouter generation 0.0000 per 1M tokens input
microsoft/mai-ds-r1 openrouter generation 0.0000 per 1M tokens output
microsoft/phi-3-medium-128k-instruct openrouter generation 0.1053 per 1M tokens input
microsoft/phi-3-medium-128k-instruct openrouter generation 0.3158 per 1M tokens output
microsoft/phi-3-mini-128k-instruct openrouter generation 0.1053 per 1M tokens input
microsoft/phi-3-mini-128k-instruct openrouter generation 0.1053 per 1M tokens output
microsoft/phi-3.5-mini-128k-instruct openrouter generation 0.0316 per 1M tokens input
microsoft/phi-3.5-mini-128k-instruct openrouter generation 0.0947 per 1M tokens output
microsoft/phi-4 nebius generation 0.1000 per 1M tokens input
microsoft/phi-4 nebius generation 0.3000 per 1M tokens output
microsoft/phi-4 openrouter generation 0.0737 per 1M tokens input
microsoft/phi-4 openrouter generation 0.1474 per 1M tokens output
microsoft/phi-4-multimodal-instruct openrouter generation 0.0526 per 1M tokens input
microsoft/phi-4-multimodal-instruct openrouter generation 0.1053 per 1M tokens output
microsoft/phi-4-reasoning openrouter generation 0.0000 per 1M tokens input
microsoft/phi-4-reasoning openrouter generation 0.0000 per 1M tokens output
microsoft/phi-4-reasoning-plus openrouter generation 0.0000 per 1M tokens input
microsoft/phi-4-reasoning-plus openrouter generation 0.0000 per 1M tokens output
microsoft/phi-4-reasoning-plus openrouter generation 0.0737 per 1M tokens input
microsoft/phi-4-reasoning-plus openrouter generation 0.3684 per 1M tokens output
microsoft/wizardlm-2-8x22b openrouter generation 0.5263 per 1M tokens input
microsoft/wizardlm-2-8x22b openrouter generation 0.5263 per 1M tokens output
minimax/minimax-01 openrouter generation 0.2105 per 1M tokens input
minimax/minimax-01 openrouter generation 1.1579 per 1M tokens output
mistral/ministral-8b openrouter generation 0.1053 per 1M tokens input
mistral/ministral-8b openrouter generation 0.1053 per 1M tokens output
mistralai/codestral-2501 openrouter generation 0.3158 per 1M tokens input
mistralai/codestral-2501 openrouter generation 0.9474 per 1M tokens output
mistralai/codestral-mamba openrouter generation 0.2632 per 1M tokens input
mistralai/codestral-mamba openrouter generation 0.2632 per 1M tokens output
mistralai/ministral-3b openrouter generation 0.0421 per 1M tokens input
mistralai/ministral-3b openrouter generation 0.0421 per 1M tokens output
mistralai/ministral-8b openrouter generation 0.1053 per 1M tokens input
mistralai/ministral-8b openrouter generation 0.1053 per 1M tokens output
mistralai/mistral-7b-instruct openrouter generation 0.0000 per 1M tokens input
mistralai/mistral-7b-instruct openrouter generation 0.0000 per 1M tokens output
mistralai/mistral-7b-instruct openrouter generation 0.0295 per 1M tokens input
mistralai/mistral-7b-instruct openrouter generation 0.0568 per 1M tokens output
mistralai/mistral-7b-instruct-v0.1 openrouter generation 0.1158 per 1M tokens input
mistralai/mistral-7b-instruct-v0.1 openrouter generation 0.2000 per 1M tokens output
mistralai/mistral-7b-instruct-v0.2 openrouter generation 0.2105 per 1M tokens input
mistralai/mistral-7b-instruct-v0.2 openrouter generation 0.2105 per 1M tokens output
mistralai/mistral-7b-instruct-v0.3 openrouter generation 0.0295 per 1M tokens input
mistralai/mistral-7b-instruct-v0.3 openrouter generation 0.0568 per 1M tokens output
mistralai/mistral-large openrouter generation 2.1053 per 1M tokens input
mistralai/mistral-large openrouter generation 6.3158 per 1M tokens output
mistralai/mistral-large-2407 openrouter generation 2.1053 per 1M tokens input
mistralai/mistral-large-2407 openrouter generation 6.3158 per 1M tokens output
mistralai/mistral-large-2411 openrouter generation 2.1053 per 1M tokens input
mistralai/mistral-large-2411 openrouter generation 6.3158 per 1M tokens output
mistralai/mistral-medium openrouter generation 2.8947 per 1M tokens input
mistralai/mistral-medium openrouter generation 8.5263 per 1M tokens output
mistralai/mistral-nemo openrouter generation 0.0316 per 1M tokens input
mistralai/mistral-nemo openrouter generation 0.0737 per 1M tokens output
mistralai/mistral-nemo openrouter generation 0.0000 per 1M tokens input
mistralai/mistral-nemo openrouter generation 0.0000 per 1M tokens output
mistralai/mistral-saba openrouter generation 0.2105 per 1M tokens input
mistralai/mistral-saba openrouter generation 0.6316 per 1M tokens output
mistralai/mistral-small openrouter generation 0.2105 per 1M tokens input
mistralai/mistral-small openrouter generation 0.6316 per 1M tokens output
mistralai/mistral-small-24b-instruct-2501 openrouter generation 0.0632 per 1M tokens input
mistralai/mistral-small-24b-instruct-2501 openrouter generation 0.1263 per 1M tokens output
mistralai/mistral-small-24b-instruct-2501 openrouter generation 0.0000 per 1M tokens input
mistralai/mistral-small-24b-instruct-2501 openrouter generation 0.0000 per 1M tokens output
mistralai/mistral-small-3.1-24b-instruct openrouter generation 0.0000 per 1M tokens input
mistralai/mistral-small-3.1-24b-instruct openrouter generation 0.0000 per 1M tokens output
mistralai/mistral-small-3.1-24b-instruct openrouter generation 0.0526 per 1M tokens input
mistralai/mistral-small-3.1-24b-instruct openrouter generation 0.1579 per 1M tokens output
mistralai/mistral-tiny openrouter generation 0.2632 per 1M tokens input
mistralai/mistral-tiny openrouter generation 0.2632 per 1M tokens output
mistralai/mixtral-8x22b-instruct openrouter generation 0.4211 per 1M tokens input
mistralai/mixtral-8x22b-instruct openrouter generation 1.2632 per 1M tokens output
mistralai/mixtral-8x7b-instruct openrouter generation 0.0842 per 1M tokens input
mistralai/mixtral-8x7b-instruct openrouter generation 0.2526 per 1M tokens output
mistralai/pixtral-12b openrouter generation 0.1053 per 1M tokens input
mistralai/pixtral-12b openrouter generation 0.1053 per 1M tokens output
mistralai/pixtral-large-2411 openrouter generation 2.1053 per 1M tokens input
mistralai/pixtral-large-2411 openrouter generation 6.3158 per 1M tokens output
mixtral-8x7B-chat deepinfra generation 0.2400 per 1M tokens input
mixtral-8x7B-chat deepinfra generation 0.2400 per 1M tokens output
moonshotai/kimi-vl-a3b-thinking openrouter generation 0.0000 per 1M tokens input
moonshotai/kimi-vl-a3b-thinking openrouter generation 0.0000 per 1M tokens output
moonshotai/moonlight-16b-a3b-instruct openrouter generation 0.0000 per 1M tokens input
moonshotai/moonlight-16b-a3b-instruct openrouter generation 0.0000 per 1M tokens output
neversleep/llama-3-lumimaid-70b openrouter generation 4.2105 per 1M tokens input
neversleep/llama-3-lumimaid-70b openrouter generation 6.3158 per 1M tokens output
neversleep/llama-3-lumimaid-8b openrouter generation 0.0987 per 1M tokens input
neversleep/llama-3-lumimaid-8b openrouter generation 0.0987 per 1M tokens input
neversleep/llama-3-lumimaid-8b openrouter generation 0.7895 per 1M tokens output
neversleep/llama-3-lumimaid-8b openrouter generation 0.7895 per 1M tokens output
neversleep/llama-3.1-lumimaid-70b openrouter generation 1.5789 per 1M tokens input
neversleep/llama-3.1-lumimaid-70b openrouter generation 2.3684 per 1M tokens output
neversleep/llama-3.1-lumimaid-8b openrouter generation 0.0987 per 1M tokens input
neversleep/llama-3.1-lumimaid-8b openrouter generation 0.7895 per 1M tokens output
neversleep/noromaid-20b openrouter generation 0.7895 per 1M tokens input
neversleep/noromaid-20b openrouter generation 1.5789 per 1M tokens output
nothingiisreal/mn-celeste-12b openrouter generation 0.8421 per 1M tokens input
nothingiisreal/mn-celeste-12b openrouter generation 1.2632 per 1M tokens output
nousresearch/deephermes-3-llama-3-8b-preview openrouter generation 0.0000 per 1M tokens input
nousresearch/deephermes-3-llama-3-8b-preview openrouter generation 0.0000 per 1M tokens output
nousresearch/hermes-2-pro-llama-3-8b openrouter generation 0.0263 per 1M tokens input
nousresearch/hermes-2-pro-llama-3-8b openrouter generation 0.0421 per 1M tokens output
nousresearch/hermes-3-llama-3.1-405b openrouter generation 0.8421 per 1M tokens input
nousresearch/hermes-3-llama-3.1-405b openrouter generation 0.8421 per 1M tokens output
nousresearch/hermes-3-llama-3.1-70b openrouter generation 0.1263 per 1M tokens input
nousresearch/hermes-3-llama-3.1-70b openrouter generation 0.3158 per 1M tokens output
nousresearch/nous-hermes-2-mixtral-8x7b-dpo openrouter generation 0.6316 per 1M tokens input
nousresearch/nous-hermes-2-mixtral-8x7b-dpo openrouter generation 0.6316 per 1M tokens output
nvidia/llama-3.1-nemotron-70b-instruct openrouter generation 0.1263 per 1M tokens input
nvidia/llama-3.1-nemotron-70b-instruct openrouter generation 0.3158 per 1M tokens output
nvidia/llama-3.1-nemotron-ultra-253b-v1 openrouter generation 0.0000 per 1M tokens input
nvidia/llama-3.1-nemotron-ultra-253b-v1 openrouter generation 0.0000 per 1M tokens output
nvidia/llama-3.3-nemotron-super-49b-v1 openrouter generation 0.0000 per 1M tokens input
nvidia/llama-3.3-nemotron-super-49b-v1 openrouter generation 0.1368 per 1M tokens input
nvidia/llama-3.3-nemotron-super-49b-v1 openrouter generation 0.0000 per 1M tokens output
nvidia/llama-3.3-nemotron-super-49b-v1 openrouter generation 0.4211 per 1M tokens output
o1 openai generation 7.5000 per 1M tokens input
o1 openai generation 15.0000 per 1M tokens input
o1 openai generation 7.5000 per 1M tokens input
o1 openai generation 30.0000 per 1M tokens output
o1 openai generation 60.0000 per 1M tokens output
o1 openai generation 30.0000 per 1M tokens output
o1 openai generation 7.5000 per 1M tokens input
o1 openai generation 15.0000 per 1M tokens input
o1 openai generation 7.5000 per 1M tokens input
o1 openai generation 30.0000 per 1M tokens output
o1 openai generation 60.0000 per 1M tokens output
o1 openai generation 30.0000 per 1M tokens output
o1-mini openai generation 0.5500 per 1M tokens input
o1-mini openai generation 1.1000 per 1M tokens input
o1-mini openai generation 0.5500 per 1M tokens input
o1-mini openai generation 2.2000 per 1M tokens output
o1-mini openai generation 4.4000 per 1M tokens output
o1-mini openai generation 2.2000 per 1M tokens output
o1-pro openai generation 75.0000 per 1M tokens input
o1-pro openai generation 150.0000 per 1M tokens input
o1-pro openai generation 75.0000 per 1M tokens input
o1-pro openai generation 300.0000 per 1M tokens output
o1-pro openai generation 600.0000 per 1M tokens output
o1-pro openai generation 300.0000 per 1M tokens output
o3 openai generation 5.0000 per 1M tokens input
o3 openai generation 5.0000 per 1M tokens input
o3 openai generation 10.0000 per 1M tokens input
o3 openai generation 5.0000 per 1M tokens input
o3 openai generation 5.0000 per 1M tokens input
o3 openai generation 5.0000 per 1M tokens input
o3 openai generation 20.0000 per 1M tokens output
o3 openai generation 20.0000 per 1M tokens output
o3 openai generation 40.0000 per 1M tokens output
o3 openai generation 20.0000 per 1M tokens output
o3 openai generation 20.0000 per 1M tokens output
o3 openai generation 20.0000 per 1M tokens output
o3-mini openai generation 0.5500 per 1M tokens input
o3-mini openai generation 1.1000 per 1M tokens input
o3-mini openai generation 0.5500 per 1M tokens input
o3-mini openai generation 2.2000 per 1M tokens output
o3-mini openai generation 4.4000 per 1M tokens output
o3-mini openai generation 2.2000 per 1M tokens output
o4-mini openai generation 0.5500 per 1M tokens input
o4-mini openai generation 0.5500 per 1M tokens input
o4-mini openai generation 1.1000 per 1M tokens input
o4-mini openai generation 0.5500 per 1M tokens input
o4-mini openai generation 0.5500 per 1M tokens input
o4-mini openai generation 0.5500 per 1M tokens input
o4-mini openai generation 2.2000 per 1M tokens output
o4-mini openai generation 2.2000 per 1M tokens output
o4-mini openai generation 4.4000 per 1M tokens output
o4-mini openai generation 2.2000 per 1M tokens output
o4-mini openai generation 2.2000 per 1M tokens output
o4-mini openai generation 2.2000 per 1M tokens output
open-r1/olympiccoder-32b openrouter generation 0.0000 per 1M tokens input
open-r1/olympiccoder-32b openrouter generation 0.0000 per 1M tokens output
openai/chatgpt-4o-latest openrouter generation 5.2632 per 1M tokens input
openai/chatgpt-4o-latest openrouter generation 15.7895 per 1M tokens output
openai/gpt-3.5-turbo openrouter generation 0.5263 per 1M tokens input
openai/gpt-3.5-turbo openrouter generation 1.5789 per 1M tokens output
openai/gpt-3.5-turbo-0125 openrouter generation 0.5263 per 1M tokens input
openai/gpt-3.5-turbo-0125 openrouter generation 1.5789 per 1M tokens output
openai/gpt-3.5-turbo-0613 openrouter generation 1.0526 per 1M tokens input
openai/gpt-3.5-turbo-0613 openrouter generation 2.1053 per 1M tokens output
openai/gpt-3.5-turbo-1106 openrouter generation 1.0526 per 1M tokens input
openai/gpt-3.5-turbo-1106 openrouter generation 2.1053 per 1M tokens output
openai/gpt-3.5-turbo-16k openrouter generation 3.1579 per 1M tokens input
openai/gpt-3.5-turbo-16k openrouter generation 4.2105 per 1M tokens output
openai/gpt-3.5-turbo-instruct openrouter generation 1.5789 per 1M tokens input
openai/gpt-3.5-turbo-instruct openrouter generation 2.1053 per 1M tokens output
openai/gpt-4 openrouter generation 31.5789 per 1M tokens input
openai/gpt-4 openrouter generation 63.1579 per 1M tokens output
openai/gpt-4-0314 openrouter generation 31.5789 per 1M tokens input
openai/gpt-4-0314 openrouter generation 63.1579 per 1M tokens output
openai/gpt-4-1106-preview openrouter generation 10.5263 per 1M tokens input
openai/gpt-4-1106-preview openrouter generation 31.5789 per 1M tokens output
openai/gpt-4-32k openrouter generation 63.1579 per 1M tokens input
openai/gpt-4-32k openrouter generation 126.3158 per 1M tokens output
openai/gpt-4-32k-0314 openrouter generation 63.1579 per 1M tokens input
openai/gpt-4-32k-0314 openrouter generation 126.3158 per 1M tokens output
openai/gpt-4-turbo openrouter generation 10.5263 per 1M tokens input
openai/gpt-4-turbo openrouter generation 31.5789 per 1M tokens output
openai/gpt-4-turbo-preview openrouter generation 10.5263 per 1M tokens input
openai/gpt-4-turbo-preview openrouter generation 31.5789 per 1M tokens output
openai/gpt-4.1 openrouter generation 2.1053 per 1M tokens input
openai/gpt-4.1 openrouter generation 8.4211 per 1M tokens output
openai/gpt-4.1-mini openrouter generation 0.4211 per 1M tokens input
openai/gpt-4.1-mini openrouter generation 1.6842 per 1M tokens output
openai/gpt-4.1-nano openrouter generation 0.1053 per 1M tokens input
openai/gpt-4.1-nano openrouter generation 0.4211 per 1M tokens output
openai/gpt-4.5-preview openrouter generation 78.9474 per 1M tokens input
openai/gpt-4.5-preview openrouter generation 157.8947 per 1M tokens output
openai/gpt-4o openrouter generation 2.6316 per 1M tokens input
openai/gpt-4o openrouter generation 10.5263 per 1M tokens output
openai/gpt-4o openrouter generation 6.3158 per 1M tokens input
openai/gpt-4o openrouter generation 18.9474 per 1M tokens output
openai/gpt-4o-2024-05-13 openrouter generation 5.2632 per 1M tokens input
openai/gpt-4o-2024-05-13 openrouter generation 15.7895 per 1M tokens output
openai/gpt-4o-2024-08-06 openrouter generation 2.6316 per 1M tokens input
openai/gpt-4o-2024-08-06 openrouter generation 10.5263 per 1M tokens output
openai/gpt-4o-2024-11-20 openrouter generation 2.6316 per 1M tokens input
openai/gpt-4o-2024-11-20 openrouter generation 10.5263 per 1M tokens output
openai/gpt-4o-mini openrouter generation 0.1579 per 1M tokens input
openai/gpt-4o-mini openrouter generation 0.6316 per 1M tokens output
openai/gpt-4o-mini-2024-07-18 openrouter generation 0.1579 per 1M tokens input
openai/gpt-4o-mini-2024-07-18 openrouter generation 0.6316 per 1M tokens output
openai/gpt-4o-mini-search-preview openrouter generation 0.1579 per 1M tokens input
openai/gpt-4o-mini-search-preview openrouter generation 0.6316 per 1M tokens output
openai/gpt-4o-search-preview openrouter generation 2.6316 per 1M tokens input
openai/gpt-4o-search-preview openrouter generation 10.5263 per 1M tokens output
openai/o1 openrouter generation 15.7895 per 1M tokens input
openai/o1 openrouter generation 63.1579 per 1M tokens output
openai/o1-mini openrouter generation 1.1579 per 1M tokens input
openai/o1-mini openrouter generation 4.6316 per 1M tokens output
openai/o1-mini-2024-09-12 openrouter generation 1.1579 per 1M tokens input
openai/o1-mini-2024-09-12 openrouter generation 4.6316 per 1M tokens output
openai/o1-preview openrouter generation 15.7895 per 1M tokens input
openai/o1-preview openrouter generation 63.1579 per 1M tokens output
openai/o1-preview-2024-09-12 openrouter generation 15.7895 per 1M tokens input
openai/o1-preview-2024-09-12 openrouter generation 63.1579 per 1M tokens output
openai/o1-pro openrouter generation 157.8947 per 1M tokens input
openai/o1-pro openrouter generation 631.5789 per 1M tokens output
openai/o3 openrouter generation 10.5263 per 1M tokens input
openai/o3 openrouter generation 42.1053 per 1M tokens output
openai/o3-mini openrouter generation 1.1579 per 1M tokens input
openai/o3-mini openrouter generation 4.6316 per 1M tokens output
openai/o3-mini-high openrouter generation 1.1579 per 1M tokens input
openai/o3-mini-high openrouter generation 4.6316 per 1M tokens output
openai/o4-mini openrouter generation 1.1579 per 1M tokens input
openai/o4-mini openrouter generation 4.6316 per 1M tokens output
openai/o4-mini-high openrouter generation 1.1579 per 1M tokens input
openai/o4-mini-high openrouter generation 4.6316 per 1M tokens output
opengvlab/internvl3-14b openrouter generation 0.0000 per 1M tokens input
opengvlab/internvl3-14b openrouter generation 0.0000 per 1M tokens output
opengvlab/internvl3-2b openrouter generation 0.0000 per 1M tokens input
opengvlab/internvl3-2b openrouter generation 0.0000 per 1M tokens output
perplexity/llama-3.1-sonar-large-128k-online openrouter generation 1.0526 per 1M tokens input
perplexity/llama-3.1-sonar-large-128k-online openrouter generation 1.0526 per 1M tokens output
perplexity/llama-3.1-sonar-small-128k-online openrouter generation 0.2105 per 1M tokens input
perplexity/llama-3.1-sonar-small-128k-online openrouter generation 0.2105 per 1M tokens output
perplexity/r1-1776 openrouter generation 2.1053 per 1M tokens input
perplexity/r1-1776 openrouter generation 8.4211 per 1M tokens output
perplexity/sonar openrouter generation 1.0526 per 1M tokens input
perplexity/sonar openrouter generation 1.0526 per 1M tokens output
perplexity/sonar-deep-research openrouter generation 2.1053 per 1M tokens input
perplexity/sonar-deep-research openrouter generation 8.4211 per 1M tokens output
perplexity/sonar-pro openrouter generation 3.1579 per 1M tokens input
perplexity/sonar-pro openrouter generation 15.7895 per 1M tokens output
perplexity/sonar-reasoning openrouter generation 1.0526 per 1M tokens input
perplexity/sonar-reasoning openrouter generation 5.2632 per 1M tokens output
perplexity/sonar-reasoning-pro openrouter generation 2.1053 per 1M tokens input
perplexity/sonar-reasoning-pro openrouter generation 8.4211 per 1M tokens output
pygmalionai/mythalion-13b openrouter generation 0.5921 per 1M tokens input
pygmalionai/mythalion-13b openrouter generation 1.1842 per 1M tokens output
qwen/qwen-2-72b-instruct openrouter generation 0.9474 per 1M tokens input
qwen/qwen-2-72b-instruct openrouter generation 0.9474 per 1M tokens output
qwen/qwen-2.5-72b-instruct openrouter generation 0.0000 per 1M tokens input
qwen/qwen-2.5-72b-instruct openrouter generation 0.1263 per 1M tokens input
qwen/qwen-2.5-72b-instruct openrouter generation 0.0000 per 1M tokens output
qwen/qwen-2.5-72b-instruct openrouter generation 0.4105 per 1M tokens output
qwen/qwen-2.5-7b-instruct openrouter generation 0.0000 per 1M tokens input
qwen/qwen-2.5-7b-instruct openrouter generation 0.0526 per 1M tokens input
qwen/qwen-2.5-7b-instruct openrouter generation 0.0000 per 1M tokens output
qwen/qwen-2.5-7b-instruct openrouter generation 0.1053 per 1M tokens output
qwen/qwen-2.5-coder-32b-instruct openrouter generation 0.0000 per 1M tokens input
qwen/qwen-2.5-coder-32b-instruct openrouter generation 0.0632 per 1M tokens input
qwen/qwen-2.5-coder-32b-instruct openrouter generation 0.0000 per 1M tokens output
qwen/qwen-2.5-coder-32b-instruct openrouter generation 0.1895 per 1M tokens output
qwen/qwen-2.5-vl-72b-instruct openrouter generation 0.6316 per 1M tokens input
qwen/qwen-2.5-vl-72b-instruct openrouter generation 0.6316 per 1M tokens output
qwen/qwen-2.5-vl-7b-instruct openrouter generation 0.0000 per 1M tokens input
qwen/qwen-2.5-vl-7b-instruct openrouter generation 0.2105 per 1M tokens input
qwen/qwen-2.5-vl-7b-instruct openrouter generation 0.0000 per 1M tokens output
qwen/qwen-2.5-vl-7b-instruct openrouter generation 0.2105 per 1M tokens output
qwen/qwen-max openrouter generation 1.6842 per 1M tokens input
qwen/qwen-max openrouter generation 6.7368 per 1M tokens output
qwen/qwen-plus openrouter generation 0.4211 per 1M tokens input
qwen/qwen-plus openrouter generation 1.2632 per 1M tokens output
qwen/qwen-turbo openrouter generation 0.0526 per 1M tokens input
qwen/qwen-turbo openrouter generation 0.2105 per 1M tokens output
qwen/qwen-vl-max openrouter generation 0.8421 per 1M tokens input
qwen/qwen-vl-max openrouter generation 3.3684 per 1M tokens output
qwen/qwen-vl-plus openrouter generation 0.2211 per 1M tokens input
qwen/qwen-vl-plus openrouter generation 0.6632 per 1M tokens output
qwen/qwen2.5-coder-7b-instruct openrouter generation 0.0105 per 1M tokens input
qwen/qwen2.5-coder-7b-instruct openrouter generation 0.0316 per 1M tokens output
qwen/qwen2.5-vl-32b-instruct openrouter generation 0.9474 per 1M tokens input
qwen/qwen2.5-vl-32b-instruct openrouter generation 0.9474 per 1M tokens output
qwen/qwen2.5-vl-32b-instruct openrouter generation 0.0000 per 1M tokens input
qwen/qwen2.5-vl-32b-instruct openrouter generation 0.0000 per 1M tokens output
qwen/qwen2.5-vl-3b-instruct openrouter generation 0.0000 per 1M tokens input
qwen/qwen2.5-vl-3b-instruct openrouter generation 0.0000 per 1M tokens output
qwen/qwen2.5-vl-72b-instruct openrouter generation 0.2632 per 1M tokens input
qwen/qwen2.5-vl-72b-instruct openrouter generation 0.7895 per 1M tokens output
qwen/qwen2.5-vl-72b-instruct openrouter generation 0.0000 per 1M tokens input
qwen/qwen2.5-vl-72b-instruct openrouter generation 0.0000 per 1M tokens output
qwen/qwen3-0.6b-04-28 openrouter generation 0.0000 per 1M tokens input
qwen/qwen3-0.6b-04-28 openrouter generation 0.0000 per 1M tokens output
qwen/qwen3-1.7b openrouter generation 0.0000 per 1M tokens input
qwen/qwen3-1.7b openrouter generation 0.0000 per 1M tokens output
qwen/qwen3-14b openrouter generation 0.0000 per 1M tokens input
qwen/qwen3-14b openrouter generation 0.0737 per 1M tokens input
qwen/qwen3-14b openrouter generation 0.0000 per 1M tokens output
qwen/qwen3-14b openrouter generation 0.2526 per 1M tokens output
qwen/qwen3-235b-a22b openrouter generation 0.0000 per 1M tokens input
qwen/qwen3-235b-a22b openrouter generation 0.1053 per 1M tokens input
qwen/qwen3-235b-a22b openrouter generation 0.0000 per 1M tokens output
qwen/qwen3-235b-a22b openrouter generation 0.1053 per 1M tokens output
qwen/qwen3-30b-a3b openrouter generation 0.0000 per 1M tokens input
qwen/qwen3-30b-a3b openrouter generation 0.1053 per 1M tokens input
qwen/qwen3-30b-a3b openrouter generation 0.0000 per 1M tokens output
qwen/qwen3-30b-a3b openrouter generation 0.3158 per 1M tokens output
qwen/qwen3-32b openrouter generation 0.0000 per 1M tokens input
qwen/qwen3-32b openrouter generation 0.1053 per 1M tokens input
qwen/qwen3-32b openrouter generation 0.0000 per 1M tokens output
qwen/qwen3-32b openrouter generation 0.3158 per 1M tokens output
qwen/qwen3-4b openrouter generation 0.0000 per 1M tokens input
qwen/qwen3-4b openrouter generation 0.0000 per 1M tokens output
qwen/qwen3-8b openrouter generation 0.0000 per 1M tokens input
qwen/qwen3-8b openrouter generation 0.0000 per 1M tokens output
qwen/qwen3-8b openrouter generation 0.0368 per 1M tokens input
qwen/qwen3-8b openrouter generation 0.1453 per 1M tokens output
qwen/qwq-32b openrouter generation 0.0000 per 1M tokens input
qwen/qwq-32b openrouter generation 0.1579 per 1M tokens input
qwen/qwq-32b openrouter generation 0.0000 per 1M tokens output
qwen/qwq-32b openrouter generation 0.2105 per 1M tokens output
qwen/qwq-32b-preview openrouter generation 0.0000 per 1M tokens input
qwen/qwq-32b-preview openrouter generation 0.0947 per 1M tokens input
qwen/qwq-32b-preview openrouter generation 0.0000 per 1M tokens output
qwen/qwq-32b-preview openrouter generation 0.2842 per 1M tokens output
raifle/sorcererlm-8x22b openrouter generation 4.7368 per 1M tokens input
raifle/sorcererlm-8x22b openrouter generation 4.7368 per 1M tokens output
rekaai/reka-flash-3 openrouter generation 0.0000 per 1M tokens input
rekaai/reka-flash-3 openrouter generation 0.0000 per 1M tokens output
sao10k/fimbulvetr-11b-v2 openrouter generation 0.8421 per 1M tokens input
sao10k/fimbulvetr-11b-v2 openrouter generation 1.2632 per 1M tokens output
sao10k/l3-euryale-70b openrouter generation 1.5579 per 1M tokens input
sao10k/l3-euryale-70b openrouter generation 1.5579 per 1M tokens output
sao10k/l3-lunaris-8b openrouter generation 0.0211 per 1M tokens input
sao10k/l3-lunaris-8b openrouter generation 0.0526 per 1M tokens output
sao10k/l3.1-euryale-70b openrouter generation 0.7368 per 1M tokens input
sao10k/l3.1-euryale-70b openrouter generation 0.8421 per 1M tokens output
sao10k/l3.3-euryale-70b openrouter generation 0.7368 per 1M tokens input
sao10k/l3.3-euryale-70b openrouter generation 0.8421 per 1M tokens output
scb10x/llama3.1-typhoon2-70b-instruct openrouter generation 0.9263 per 1M tokens input
scb10x/llama3.1-typhoon2-70b-instruct openrouter generation 0.9263 per 1M tokens output
scb10x/llama3.1-typhoon2-8b-instruct openrouter generation 0.1895 per 1M tokens input
scb10x/llama3.1-typhoon2-8b-instruct openrouter generation 0.1895 per 1M tokens output
shisa-ai/shisa-v2-llama3.3-70b openrouter generation 0.0000 per 1M tokens input
shisa-ai/shisa-v2-llama3.3-70b openrouter generation 0.0000 per 1M tokens output
sophosympatheia/midnight-rose-70b openrouter generation 0.8421 per 1M tokens input
sophosympatheia/midnight-rose-70b openrouter generation 0.8421 per 1M tokens output
stability-ai/sdxl nebius image-generation 0.0030 per image input
text-embedding-3-large openai embeddings 0.0650 per 1M tokens total
text-embedding-3-large openai embeddings 0.1300 per 1M tokens total
text-embedding-3-large openai embeddings 0.0650 per 1M tokens total
text-embedding-3-small openai embeddings 0.0100 per 1M tokens total
text-embedding-3-small openai embeddings 0.0200 per 1M tokens total
text-embedding-3-small openai embeddings 0.0100 per 1M tokens total
text-embedding-ada-002 openai embeddings 0.0500 per 1M tokens total
text-embedding-ada-002 openai embeddings 0.1000 per 1M tokens total
text-embedding-ada-002 openai embeddings 0.0500 per 1M tokens total
thedrummer/anubis-pro-105b-v1 openrouter generation 0.8421 per 1M tokens input
thedrummer/anubis-pro-105b-v1 openrouter generation 1.0526 per 1M tokens output
thedrummer/rocinante-12b openrouter generation 0.2632 per 1M tokens input
thedrummer/rocinante-12b openrouter generation 0.5263 per 1M tokens output
thedrummer/skyfall-36b-v2 openrouter generation 0.5263 per 1M tokens input
thedrummer/skyfall-36b-v2 openrouter generation 0.8421 per 1M tokens output
thedrummer/unslopnemo-12b openrouter generation 0.4737 per 1M tokens input
thedrummer/unslopnemo-12b openrouter generation 0.4737 per 1M tokens output
thudm/glm-4-32b openrouter generation 0.0000 per 1M tokens input
thudm/glm-4-32b openrouter generation 0.0000 per 1M tokens output
thudm/glm-4-32b openrouter generation 0.2526 per 1M tokens input
thudm/glm-4-32b openrouter generation 0.2526 per 1M tokens output
thudm/glm-4-9b openrouter generation 0.0000 per 1M tokens input
thudm/glm-4-9b openrouter generation 0.0000 per 1M tokens output
thudm/glm-z1-32b openrouter generation 0.0000 per 1M tokens input
thudm/glm-z1-32b openrouter generation 0.0000 per 1M tokens output
thudm/glm-z1-32b openrouter generation 0.2526 per 1M tokens input
thudm/glm-z1-32b openrouter generation 0.2526 per 1M tokens output
thudm/glm-z1-9b openrouter generation 0.0000 per 1M tokens input
thudm/glm-z1-9b openrouter generation 0.0000 per 1M tokens output
thudm/glm-z1-rumination-32b openrouter generation 0.2526 per 1M tokens input
thudm/glm-z1-rumination-32b openrouter generation 0.2526 per 1M tokens output
tngtech/deepseek-r1t-chimera openrouter generation 0.0000 per 1M tokens input
tngtech/deepseek-r1t-chimera openrouter generation 0.0000 per 1M tokens output
undi95/remm-slerp-l2-13b openrouter generation 0.5921 per 1M tokens input
undi95/remm-slerp-l2-13b openrouter generation 1.1842 per 1M tokens output
undi95/toppy-m-7b openrouter generation 0.8421 per 1M tokens input
undi95/toppy-m-7b openrouter generation 1.2632 per 1M tokens output
wizardLM-2-8x22B deepinfra generation 0.5000 per 1M tokens input
wizardLM-2-8x22B deepinfra generation 0.5000 per 1M tokens output
x-ai/grok-2-1212 openrouter generation 2.1053 per 1M tokens input
x-ai/grok-2-1212 openrouter generation 10.5263 per 1M tokens output
x-ai/grok-2-vision-1212 openrouter generation 2.1053 per 1M tokens input
x-ai/grok-2-vision-1212 openrouter generation 10.5263 per 1M tokens output
x-ai/grok-3-beta openrouter generation 3.1579 per 1M tokens input
x-ai/grok-3-beta openrouter generation 15.7895 per 1M tokens output
x-ai/grok-3-mini-beta openrouter generation 0.3158 per 1M tokens input
x-ai/grok-3-mini-beta openrouter generation 0.5263 per 1M tokens output
x-ai/grok-beta openrouter generation 5.2632 per 1M tokens input
x-ai/grok-beta openrouter generation 15.7895 per 1M tokens output
x-ai/grok-vision-beta openrouter generation 5.2632 per 1M tokens input
x-ai/grok-vision-beta openrouter generation 15.7895 per 1M tokens output