100% official direct connections. Real-time pricing. Zero quantization.
ai21/jamba-large-1.7 from Ai21, optimized for chat completions workloads and available through Yi-AI.
Input
$2.20/M tokens
aion-labs/aion-1.0 from Aion Labs, optimized for chat completions workloads and available through Yi-AI.
Input
$4.40/M tokens
aion-labs/aion-1.0-mini from Aion Labs, optimized for chat completions workloads and available through Yi-AI.
Input
$0.770/M tokens
aion-labs/aion-2.0 from Aion Labs, optimized for chat completions workloads and available through Yi-AI.
Input
$0.880/M tokens
aion-labs/aion-rp-llama-3.1-8b from Aion Labs, optimized for chat completions workloads and available through Yi-AI.
Input
$0.880/M tokens
allenai/olmo-3-32b-think from Allenai, optimized for chat completions workloads and available through Yi-AI.
Input
$0.165/M tokens
amazon/nova-2-lite-v1 from Amazon, optimized for multimodal understanding workloads and available through Yi-AI.
Input
$0.330/M tokens
amazon/nova-lite-v1 from Amazon, optimized for multimodal understanding workloads and available through Yi-AI.
Input
$0.066/M tokens
amazon/nova-micro-v1 from Amazon, optimized for chat completions workloads and available through Yi-AI.
Input
$0.038/M tokens
amazon/nova-premier-v1 from Amazon, optimized for multimodal understanding workloads and available through Yi-AI.
Input
$2.75/M tokens
amazon/nova-pro-v1 from Amazon, optimized for multimodal understanding workloads and available through Yi-AI.
Input
$0.880/M tokens
anthracite-org/magnum-v4-72b from Anthracite Org, optimized for chat completions workloads and available through Yi-AI.
Input
$3.30/M tokens
~anthropic/claude-haiku-latest from Anthropic, optimized for multimodal understanding workloads and available through Yi-AI.
Input
$1.10/M tokens
~anthropic/claude-sonnet-latest from Anthropic, optimized for multimodal understanding workloads and available through Yi-AI.
Input
$3.30/M tokens
anthropic/claude-3-haiku from Anthropic, optimized for multimodal understanding workloads and available through Yi-AI.
Input
$0.275/M tokens
anthropic/claude-fable-5 from Anthropic, optimized for multimodal understanding workloads and available through Yi-AI.
Input
$11.00/M tokens
~anthropic/claude-fable-latest from Anthropic, optimized for multimodal understanding workloads and available through Yi-AI.
Input
$11.00/M tokens
anthropic/claude-haiku-4.5 from Anthropic, optimized for multimodal understanding workloads and available through Yi-AI.
Input
$1.10/M tokens
anthropic/claude-opus-4 from Anthropic, optimized for multimodal understanding workloads and available through Yi-AI.
Input
$16.50/M tokens
anthropic/claude-opus-4.1 from Anthropic, optimized for multimodal understanding workloads and available through Yi-AI.
Input
$16.50/M tokens
anthropic/claude-opus-4.5 from Anthropic, optimized for multimodal understanding workloads and available through Yi-AI.
Input
$5.50/M tokens
anthropic/claude-opus-4.6 from Anthropic, optimized for multimodal understanding workloads and available through Yi-AI.
Input
$5.50/M tokens
anthropic/claude-opus-4.7 from Anthropic, optimized for multimodal understanding workloads and available through Yi-AI.
Input
$5.50/M tokens
anthropic/claude-opus-4.7-fast from Anthropic, optimized for multimodal understanding workloads and available through Yi-AI.
Input
$33.00/M tokens
anthropic/claude-opus-4.8 from Anthropic, optimized for multimodal understanding workloads and available through Yi-AI.
Input
$5.50/M tokens
anthropic/claude-opus-4.8-fast from Anthropic, optimized for multimodal understanding workloads and available through Yi-AI.
Input
$11.00/M tokens
~anthropic/claude-opus-latest from Anthropic, optimized for multimodal understanding workloads and available through Yi-AI.
Input
$5.50/M tokens
anthropic/claude-sonnet-4 from Anthropic, optimized for multimodal understanding workloads and available through Yi-AI.
Input
$3.30/M tokens
anthropic/claude-sonnet-4.5 from Anthropic, optimized for multimodal understanding workloads and available through Yi-AI.
Input
$3.30/M tokens
anthropic/claude-sonnet-4.6 from Anthropic, optimized for multimodal understanding workloads and available through Yi-AI.
Input
$3.30/M tokens
claude-3-5-haiku-20241022 from Anthropic, optimized for chat completions workloads and available through Yi-AI.
Input
$0.880/M tokens
claude-3-5-haiku-latest from Anthropic, optimized for chat completions workloads and available through Yi-AI.
Input
$1.10/M tokens
claude-3-5-sonnet-20240620 from Anthropic, optimized for chat completions workloads and available through Yi-AI.
Input
$3.30/M tokens
claude-3-5-sonnet-20241022 from Anthropic, optimized for chat completions workloads and available through Yi-AI.
Input
$3.30/M tokens
claude-3-5-sonnet-latest from Anthropic, optimized for chat completions workloads and available through Yi-AI.
Input
$3.30/M tokens
claude-3-haiku-20240307 from Anthropic, optimized for chat completions workloads and available through Yi-AI.
Input
$0.275/M tokens
claude-3-opus-20240229 from Anthropic, optimized for chat completions workloads and available through Yi-AI.
Input
$5.50/M tokens
claude-3-sonnet-20240229 from Anthropic, optimized for chat completions workloads and available through Yi-AI.
Input
$3.30/M tokens
claude-haiku-4-5 from Anthropic, optimized for chat completions workloads and available through Yi-AI.
Input
$1.10/M tokens
claude-haiku-latest from Anthropic, optimized for chat completions workloads and available through Yi-AI.
Input
$1.10/M tokens
claude-opus-4 from Anthropic, optimized for chat completions workloads and available through Yi-AI.
Input
$16.50/M tokens
claude-opus-4-1 from Anthropic, optimized for chat completions workloads and available through Yi-AI.
Input
$16.50/M tokens
claude-opus-4-5 from Anthropic, optimized for chat completions workloads and available through Yi-AI.
Input
$5.50/M tokens
claude-opus-4-6 from Anthropic, optimized for chat completions workloads and available through Yi-AI.
Input
$5.50/M tokens
claude-opus-4-6-fast from Anthropic, optimized for chat completions workloads and available through Yi-AI.
Input
$33.00/M tokens
claude-opus-4-7 from Anthropic, optimized for chat completions workloads and available through Yi-AI.
Input
$5.50/M tokens
claude-opus-4-7-fast from Anthropic, optimized for chat completions workloads and available through Yi-AI.
Input
$33.00/M tokens
claude-opus-latest from Anthropic, optimized for chat completions workloads and available through Yi-AI.
Input
$5.50/M tokens
claude-sonnet-4 from Anthropic, optimized for chat completions workloads and available through Yi-AI.
Input
$3.30/M tokens
claude-sonnet-4-20250514 from Anthropic, optimized for chat completions workloads and available through Yi-AI.
Input
$3.30/M tokens
claude-sonnet-4-5 from Anthropic, optimized for chat completions workloads and available through Yi-AI.
Input
$3.30/M tokens
claude-sonnet-4-6 from Anthropic, optimized for chat completions workloads and available through Yi-AI.
Input
$3.30/M tokens
claude-sonnet-latest from Anthropic, optimized for chat completions workloads and available through Yi-AI.
Input
$3.30/M tokens
arcee-ai/coder-large from Arcee Ai, optimized for chat completions workloads and available through Yi-AI.
Input
$0.550/M tokens
arcee-ai/trinity-large-thinking from Arcee Ai, optimized for chat completions workloads and available through Yi-AI.
Input
$0.275/M tokens
arcee-ai/trinity-mini from Arcee Ai, optimized for chat completions workloads and available through Yi-AI.
Input
$0.050/M tokens
arcee-ai/virtuoso-large from Arcee Ai, optimized for chat completions workloads and available through Yi-AI.
Input
$0.825/M tokens
baai/bge-base-en-v1.5 from Baai, optimized for embedding generation workloads and available through Yi-AI.
Input
$0.0055/M tokens
baai/bge-large-en-v1.5 from Baai, optimized for embedding generation workloads and available through Yi-AI.
Input
$0.011/M tokens
baai/bge-m3 from Baai, optimized for embedding generation workloads and available through Yi-AI.
Input
$0.011/M tokens
baidu/ernie-4.5-vl-424b-a47b from Baidu, optimized for multimodal understanding workloads and available through Yi-AI.
Input
$0.462/M tokens
bytedance/ui-tars-1.5-7b from Bytedance, optimized for multimodal understanding workloads and available through Yi-AI.
Input
$0.110/M tokens
bytedance-seed/seed-1.6 from Bytedance Seed, optimized for multimodal understanding workloads and available through Yi-AI.
Input
$0.275/M tokens
bytedance-seed/seed-1.6-flash from Bytedance Seed, optimized for multimodal understanding workloads and available through Yi-AI.
Input
$0.083/M tokens
bytedance-seed/seed-2.0-lite from Bytedance Seed, optimized for multimodal understanding workloads and available through Yi-AI.
Input
$0.275/M tokens
bytedance-seed/seed-2.0-mini from Bytedance Seed, optimized for multimodal understanding workloads and available through Yi-AI.
Input
$0.110/M tokens
canopylabs/orpheus-3b-0.1-ft from Canopylabs, optimized for multimodal understanding workloads and available through Yi-AI.
Input
$7.70/M tokens
cohere/command-a from Cohere, optimized for chat completions workloads and available through Yi-AI.
Input
$2.75/M tokens
cohere/command-r-08-2024 from Cohere, optimized for chat completions workloads and available through Yi-AI.
Input
$0.165/M tokens
cohere/command-r-plus-08-2024 from Cohere, optimized for chat completions workloads and available through Yi-AI.
Input
$2.75/M tokens
cohere/command-r7b-12-2024 from Cohere, optimized for chat completions workloads and available through Yi-AI.
Input
$0.041/M tokens
deepcogito/cogito-v2.1-671b from Deepcogito, optimized for chat completions workloads and available through Yi-AI.
Input
$1.38/M tokens
deepseek/deepseek-chat from DeepSeek, optimized for chat completions workloads and available through Yi-AI.
Input
$0.220/M tokens
deepseek/deepseek-chat-v3-0324 from DeepSeek, optimized for chat completions workloads and available through Yi-AI.
Input
$0.220/M tokens
deepseek/deepseek-chat-v3.1 from DeepSeek, optimized for chat completions workloads and available through Yi-AI.
Input
$0.231/M tokens
deepseek/deepseek-v3.1-terminus from DeepSeek, optimized for chat completions workloads and available through Yi-AI.
Input
$0.297/M tokens
deepseek/deepseek-v3.2 from DeepSeek, optimized for chat completions workloads and available through Yi-AI.
Input
$0.252/M tokens
deepseek/deepseek-v3.2-exp from DeepSeek, optimized for chat completions workloads and available through Yi-AI.
Input
$0.297/M tokens
deepseek/deepseek-v4-flash from DeepSeek, optimized for chat completions workloads and available through Yi-AI.
Input
$0.099/M tokens
deepseek/deepseek-v4-pro from DeepSeek, optimized for chat completions workloads and available through Yi-AI.
Input
$0.478/M tokens