diff options
| -rw-r--r-- | models.yaml | 36 |
1 files changed, 25 insertions, 11 deletions
diff --git a/models.yaml b/models.yaml index 3dee66d..10c6592 100644 --- a/models.yaml +++ b/models.yaml @@ -640,39 +640,39 @@ models: - name: ernie-4.0-turbo-8k-preview max_input_tokens: 8192 - input_price: 4.2 + input_price: 2.8 output_price: 8.4 supports_function_calling: true - name: ernie-4.0-8k-preview max_input_tokens: 8192 - input_price: 5.6 - output_price: 11.2 + input_price: 4.2 + output_price: 12.6 supports_function_calling: true - name: ernie-3.5-8k-preview max_input_tokens: 8192 - input_price: 1.68 - output_price: 1.68 + input_price: 0.112 + output_price: 0.28 supports_function_calling: true - name: ernie-speed-pro-128k max_input_tokens: 128000 - input_price: 0.056 - output_price: 0.112 + input_price: 0.042 + output_price: 0.084 - name: bge_large_zh type: embedding - input_price: 0.28 + input_price: 0.07 max_tokens_per_chunk: 512 default_chunk_size: 1000 max_batch_size: 16 - name: bge_large_en type: embedding - input_price: 0.28 + input_price: 0.07 max_tokens_per_chunk: 512 default_chunk_size: 1000 max_batch_size: 16 - name: bce_reranker_base type: reranker max_input_tokens: 1024 - input_price: 0.28 + input_price: 0.07 # Links: # - https://help.aliyun.com/zh/dashscope/developer-reference/model-introduction @@ -963,6 +963,11 @@ input_price: 0.35 output_price: 0.40 supports_function_calling: true + - name: nvidia/Llama-3.1-Nemotron-70B-Instruct + max_input_tokens: 128000 + input_price: 0.35 + output_price: 0.40 + supports_function_calling: true - name: BAAI/bge-large-en-v1.5 type: embedding input_price: 0.01 @@ -1344,7 +1349,12 @@ max_input_tokens: 32768 input_price: 0.4 output_price: 0.4 - - name: x-ai/grok-2 + - name: nvidia/llama-3.1-nemotron-70b-instruct + max_input_tokens: 131072 + input_price: 0.35 + output_price: 0.4 + supports_function_calling: true + - name: x-ai/grok-beta max_input_tokens: 32768 input_price: 5 output_price: 10 @@ -1393,6 +1403,10 @@ input_price: 0.186 output_price: 0.186 supports_function_calling: true + - name: nvidia/Llama-3.1-Nemotron-70B-Instruct + max_input_tokens: 32768 + input_price: 0.578 + output_price: 0.578 - name: BAAI/bge-large-en-v1.5 type: embedding input_price: 0 |