diff --git a/api/core/model_runtime/model_providers/minimax/llm/abab5-chat.yaml b/api/core/model_runtime/model_providers/minimax/llm/abab5-chat.yaml index f946848c13..e0d81e76cc 100644 --- a/api/core/model_runtime/model_providers/minimax/llm/abab5-chat.yaml +++ b/api/core/model_runtime/model_providers/minimax/llm/abab5-chat.yaml @@ -23,7 +23,7 @@ parameter_rules: - name: frequency_penalty use_template: frequency_penalty pricing: - input: '0.00' + input: '0.015' output: '0.015' unit: '0.001' currency: RMB diff --git a/api/core/model_runtime/model_providers/minimax/llm/abab5.5-chat.yaml b/api/core/model_runtime/model_providers/minimax/llm/abab5.5-chat.yaml index 5840c2faba..cacccdb669 100644 --- a/api/core/model_runtime/model_providers/minimax/llm/abab5.5-chat.yaml +++ b/api/core/model_runtime/model_providers/minimax/llm/abab5.5-chat.yaml @@ -36,7 +36,7 @@ parameter_rules: en_US: Enable Web Search zh_Hans: 开启网页搜索 pricing: - input: '0.00' + input: '0.015' output: '0.015' unit: '0.001' currency: RMB diff --git a/api/core/model_runtime/model_providers/minimax/llm/abab5.5s-chat.yaml b/api/core/model_runtime/model_providers/minimax/llm/abab5.5s-chat.yaml index 710c5c8914..1ef7046459 100644 --- a/api/core/model_runtime/model_providers/minimax/llm/abab5.5s-chat.yaml +++ b/api/core/model_runtime/model_providers/minimax/llm/abab5.5s-chat.yaml @@ -29,7 +29,7 @@ parameter_rules: - name: frequency_penalty use_template: frequency_penalty pricing: - input: '0.00' + input: '0.005' output: '0.005' unit: '0.001' currency: RMB diff --git a/api/core/model_runtime/model_providers/minimax/llm/abab6-chat.yaml b/api/core/model_runtime/model_providers/minimax/llm/abab6-chat.yaml new file mode 100644 index 0000000000..258f2a9188 --- /dev/null +++ b/api/core/model_runtime/model_providers/minimax/llm/abab6-chat.yaml @@ -0,0 +1,35 @@ +model: abab6-chat +label: + en_US: Abab6-Chat +model_type: llm +features: + - agent-thought +model_properties: + mode: chat + context_size: 32768 +parameter_rules: + - name: temperature + use_template: temperature + min: 0.01 + max: 1 + default: 0.1 + - name: top_p + use_template: top_p + min: 0.01 + max: 1 + default: 0.9 + - name: max_tokens + use_template: max_tokens + required: true + default: 2048 + min: 1 + max: 32768 + - name: presence_penalty + use_template: presence_penalty + - name: frequency_penalty + use_template: frequency_penalty +pricing: + input: '0.1' + output: '0.1' + unit: '0.001' + currency: RMB diff --git a/api/core/model_runtime/model_providers/minimax/llm/chat_completion_pro.py b/api/core/model_runtime/model_providers/minimax/llm/chat_completion_pro.py index d75b734eb3..51b1a4da27 100644 --- a/api/core/model_runtime/model_providers/minimax/llm/chat_completion_pro.py +++ b/api/core/model_runtime/model_providers/minimax/llm/chat_completion_pro.py @@ -22,9 +22,6 @@ class MinimaxChatCompletionPro(object): """ generate chat completion """ - if model not in ['abab5.5-chat', 'abab5.5s-chat']: - raise BadRequestError(f'Invalid model: {model}') - if not api_key or not group_id: raise InvalidAPIKeyError('Invalid API key or group ID') diff --git a/api/core/model_runtime/model_providers/minimax/llm/llm.py b/api/core/model_runtime/model_providers/minimax/llm/llm.py index 429c75c537..7d8ae22317 100644 --- a/api/core/model_runtime/model_providers/minimax/llm/llm.py +++ b/api/core/model_runtime/model_providers/minimax/llm/llm.py @@ -1,9 +1,8 @@ -from typing import Generator, List, Optional, Union +from typing import Generator, List -from core.model_runtime.entities.llm_entities import LLMMode, LLMResult, LLMResultChunk, LLMResultChunkDelta, LLMUsage +from core.model_runtime.entities.llm_entities import LLMResult, LLMResultChunk, LLMResultChunkDelta from core.model_runtime.entities.message_entities import (AssistantPromptMessage, PromptMessage, PromptMessageTool, SystemPromptMessage, UserPromptMessage) -from core.model_runtime.entities.model_entities import AIModelEntity, FetchFrom, ModelType, ParameterRule, ParameterType from core.model_runtime.errors.invoke import (InvokeAuthorizationError, InvokeBadRequestError, InvokeConnectionError, InvokeError, InvokeRateLimitError, InvokeServerUnavailableError) from core.model_runtime.errors.validate import CredentialsValidateFailedError @@ -18,6 +17,7 @@ from core.model_runtime.model_providers.minimax.llm.types import MinimaxMessage class MinimaxLargeLanguageModel(LargeLanguageModel): model_apis = { + 'abab6-chat': MinimaxChatCompletionPro, 'abab5.5s-chat': MinimaxChatCompletionPro, 'abab5.5-chat': MinimaxChatCompletionPro, 'abab5-chat': MinimaxChatCompletion