Skip to content

AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.

feat(backend): Add new LLM models (#10512)

Bently054c20abdc9f
diff --git a/autogpt_platform/backend/backend/blocks/llm.py b/autogpt_platform/backend/backend/blocks/llm.py
index 66e3f475f6..eb857ee990 100644
--- a/autogpt_platform/backend/backend/blocks/llm.py
+++ b/autogpt_platform/backend/backend/blocks/llm.py
@@ -82,6 +82,7 @@ class LlmModel(str, Enum, metaclass=LlmModelMeta):
O1 = "o1"
O1_MINI = "o1-mini"
GPT41 = "gpt-4.1-2025-04-14"
+ GPT41_MINI = "gpt-4.1-mini-2025-04-14"
GPT4O_MINI = "gpt-4o-mini"
GPT4O = "gpt-4o"
GPT4_TURBO = "gpt-4-turbo"
@@ -116,10 +117,15 @@ class LlmModel(str, Enum, metaclass=LlmModelMeta):
# OpenRouter models
GEMINI_FLASH_1_5 = "google/gemini-flash-1.5"
GEMINI_2_5_PRO = "google/gemini-2.5-pro-preview-03-25"
+ GEMINI_2_5_FLASH = "google/gemini-2.5-flash"
+ GEMINI_2_0_FLASH = "google/gemini-2.0-flash-001"
+ GEMINI_2_5_FLASH_LITE_PREVIEW = "google/gemini-2.5-flash-lite-preview-06-17"
+ GEMINI_2_0_FLASH_LITE = "google/gemini-2.0-flash-lite-001"
MISTRAL_NEMO = "mistralai/mistral-nemo"
COHERE_COMMAND_R_08_2024 = "cohere/command-r-08-2024"
COHERE_COMMAND_R_PLUS_08_2024 = "cohere/command-r-plus-08-2024"
DEEPSEEK_CHAT = "deepseek/deepseek-chat" # Actually: DeepSeek V3
+ DEEPSEEK_R1_0528 = "deepseek/deepseek-r1-0528"
PERPLEXITY_SONAR = "perplexity/sonar"
PERPLEXITY_SONAR_PRO = "perplexity/sonar-pro"
PERPLEXITY_SONAR_DEEP_RESEARCH = "perplexity/sonar-deep-research"
@@ -132,6 +138,10 @@ class LlmModel(str, Enum, metaclass=LlmModelMeta):
GRYPHE_MYTHOMAX_L2_13B = "gryphe/mythomax-l2-13b"
META_LLAMA_4_SCOUT = "meta-llama/llama-4-scout"
META_LLAMA_4_MAVERICK = "meta-llama/llama-4-maverick"
+ GROK_4 = "x-ai/grok-4"
+ KIMI_K2 = "moonshotai/kimi-k2"
+ QWEN3_235B_A22B_THINKING = "qwen/qwen3-235b-a22b-thinking-2507"
+ QWEN3_CODER = "qwen/qwen3-coder"
# Llama API models
LLAMA_API_LLAMA_4_SCOUT = "Llama-4-Scout-17B-16E-Instruct-FP8"
LLAMA_API_LLAMA4_MAVERICK = "Llama-4-Maverick-17B-128E-Instruct-FP8"
@@ -162,6 +172,7 @@ MODEL_METADATA = {
LlmModel.O1: ModelMetadata("openai", 200000, 100000), # o1-2024-12-17
LlmModel.O1_MINI: ModelMetadata("openai", 128000, 65536), # o1-mini-2024-09-12
LlmModel.GPT41: ModelMetadata("openai", 1047576, 32768),
+ LlmModel.GPT41_MINI: ModelMetadata("openai", 1047576, 32768),
LlmModel.GPT4O_MINI: ModelMetadata(
"openai", 128000, 16384
), # gpt-4o-mini-2024-07-18
@@ -211,10 +222,17 @@ MODEL_METADATA = {
# https://openrouter.ai/models
LlmModel.GEMINI_FLASH_1_5: ModelMetadata("open_router", 1000000, 8192),
LlmModel.GEMINI_2_5_PRO: ModelMetadata("open_router", 1050000, 8192),
+ LlmModel.GEMINI_2_5_FLASH: ModelMetadata("open_router", 1048576, 65535),
+ LlmModel.GEMINI_2_0_FLASH: ModelMetadata("open_router", 1048576, 8192),
+ LlmModel.GEMINI_2_5_FLASH_LITE_PREVIEW: ModelMetadata(
+ "open_router", 1048576, 65535
+ ),
+ LlmModel.GEMINI_2_0_FLASH_LITE: ModelMetadata("open_router", 1048576, 8192),
LlmModel.MISTRAL_NEMO: ModelMetadata("open_router", 128000, 4096),
LlmModel.COHERE_COMMAND_R_08_2024: ModelMetadata("open_router", 128000, 4096),
LlmModel.COHERE_COMMAND_R_PLUS_08_2024: ModelMetadata("open_router", 128000, 4096),
LlmModel.DEEPSEEK_CHAT: ModelMetadata("open_router", 64000, 2048),
+ LlmModel.DEEPSEEK_R1_0528: ModelMetadata("open_router", 163840, 163840),
LlmModel.PERPLEXITY_SONAR: ModelMetadata("open_router", 127000, 127000),
LlmModel.PERPLEXITY_SONAR_PRO: ModelMetadata("open_router", 200000, 8000),
LlmModel.PERPLEXITY_SONAR_DEEP_RESEARCH: ModelMetadata(
@@ -235,6 +253,10 @@ MODEL_METADATA = {
LlmModel.GRYPHE_MYTHOMAX_L2_13B: ModelMetadata("open_router", 4096, 4096),
LlmModel.META_LLAMA_4_SCOUT: ModelMetadata("open_router", 131072, 131072),
LlmModel.META_LLAMA_4_MAVERICK: ModelMetadata("open_router", 1048576, 1000000),
+ LlmModel.GROK_4: ModelMetadata("open_router", 256000, 256000),
+ LlmModel.KIMI_K2: ModelMetadata("open_router", 131000, 131000),
+ LlmModel.QWEN3_235B_A22B_THINKING: ModelMetadata("open_router", 262144, 262144),
+ LlmModel.QWEN3_CODER: ModelMetadata("open_router", 262144, 262144),
# Llama API models
LlmModel.LLAMA_API_LLAMA_4_SCOUT: ModelMetadata("llama_api", 128000, 4028),
LlmModel.LLAMA_API_LLAMA4_MAVERICK: ModelMetadata("llama_api", 128000, 4028),
diff --git a/autogpt_platform/backend/backend/data/block_cost_config.py b/autogpt_platform/backend/backend/data/block_cost_config.py
index 6bc07b6ed9..e73f103b7e 100644
--- a/autogpt_platform/backend/backend/data/block_cost_config.py
+++ b/autogpt_platform/backend/backend/data/block_cost_config.py
@@ -49,6 +49,7 @@ MODEL_COST: dict[LlmModel, int] = {
LlmModel.O1: 16, # $15 / $60
LlmModel.O1_MINI: 4,
LlmModel.GPT41: 2,
+ LlmModel.GPT41_MINI: 1,
LlmModel.GPT4O_MINI: 1,
LlmModel.GPT4O: 3,
LlmModel.GPT4_TURBO: 10,
@@ -97,6 +98,15 @@ MODEL_COST: dict[LlmModel, int] = {
LlmModel.LLAMA_API_LLAMA4_MAVERICK: 1,
LlmModel.LLAMA_API_LLAMA3_3_8B: 1,
LlmModel.LLAMA_API_LLAMA3_3_70B: 1,
+ LlmModel.GROK_4: 9,
+ LlmModel.KIMI_K2: 1,
+ LlmModel.QWEN3_235B_A22B_THINKING: 1,
+ LlmModel.QWEN3_CODER: 9,
+ LlmModel.GEMINI_2_5_FLASH: 1,
+ LlmModel.GEMINI_2_0_FLASH: 1,
+ LlmModel.GEMINI_2_5_FLASH_LITE_PREVIEW: 1,
+ LlmModel.GEMINI_2_0_FLASH_LITE: 1,
+ LlmModel.DEEPSEEK_R1_0528: 1,
}
for model in LlmModel: