From a1a76f82e1728b67c2c7f563a74dcb2f80852c69 Mon Sep 17 00:00:00 2001 From: sigoden Date: Fri, 14 Feb 2025 22:29:37 +0800 Subject: feat: remove supports for hyperbolic and novita (#1176) --- Argcfile.sh | 2 - config.example.yaml | 12 ------ models.yaml | 104 ---------------------------------------------------- src/client/mod.rs | 4 +- 4 files changed, 1 insertion(+), 121 deletions(-) diff --git a/Argcfile.sh b/Argcfile.sh index 52101b0..47ec38b 100755 --- a/Argcfile.sh +++ b/Argcfile.sh @@ -306,12 +306,10 @@ _argc_before() { github,gpt-4o-mini,https://models.inference.ai.azure.com \ groq,llama-3.1-8b-instant,https://api.groq.com/openai/v1 \ hunyuan,hunyuan-large,https://api.hunyuan.cloud.tencent.com/v1 \ - hyperbolic,meta-llama/Meta-Llama-3.1-8B-Instruct,https://api.hyperbolic.xyz/v1 \ lingyiwanwu,yi-lightning,https://api.lingyiwanwu.com/v1 \ minimax,MiniMax-Text-01,https://api.minimax.chat/v1 \ mistral,mistral-small-latest,https://api.mistral.ai/v1 \ moonshot,moonshot-v1-8k,https://api.moonshot.cn/v1 \ - novita,meta-llama/llama-3.1-8b-instruct,https://api.novita.ai/v3/openai \ openrouter,openai/gpt-4o-mini,https://openrouter.ai/api/v1 \ perplexity,llama-3.1-8b-instruct,https://api.perplexity.ai \ qianwen,qwen-turbo-latest,https://dashscope.aliyuncs.com/compatible-mode/v1 \ diff --git a/config.example.yaml b/config.example.yaml index 2a9168c..d0b6111 100644 --- a/config.example.yaml +++ b/config.example.yaml @@ -324,18 +324,6 @@ clients: api_base: https://api.together.xyz/v1 api_key: xxx - # See https://docs.hyperbolic.xyz/docs/getting-started - - type: openai-compatible - name: hyperbolic - api_base: https://api.hyperbolic.xyz/v1 - api_key: xxx - - # See https://novita.ai/docs/guides/introduction - - type: openai-compatible - name: novita - api_base: https://api.novita.ai/v3/openai - api_key: xxx - # ----- RAG dedicated ----- # See https://jina.ai diff --git a/models.yaml b/models.yaml index fce774a..b32a0ec 100644 --- a/models.yaml +++ b/models.yaml @@ -1984,110 +1984,6 @@ max_input_tokens: 8192 input_price: 0.1 -# Links: -# - https://app.hyperbolic.xyz/models -# - https://docs.hyperbolic.xyz/docs/hyperbolic-ai-inference-pricing -- provider: hyperbolic - models: - - name: meta-llama/Llama-3.3-70B-Instruct - max_input_tokens: 131072 - input_price: 0.4 - output_price: 0.4 - - name: meta-llama/Meta-Llama-3.1-405B-Instruct - max_input_tokens: 32768 - input_price: 4 - output_price: 4 - - name: meta-llama/Meta-Llama-3.1-70B-Instruct - max_input_tokens: 32768 - input_price: 0.4 - output_price: 0.4 - - name: meta-llama/Meta-Llama-3.1-8B-Instruct - max_input_tokens: 32768 - input_price: 0.1 - output_price: 0.1 - - name: Qwen/Qwen2.5-72B-Instruct - max_input_tokens: 32768 - input_price: 0.4 - output_price: 0.4 - - name: Qwen/Qwen2.5-Coder-32B-Instruct - max_input_tokens: 131072 - input_price: 0.2 - output_price: 0.2 - - name: Qwen/QwQ-32B-Preview - max_input_tokens: 32768 - input_price: 0.2 - output_price: 0.2 - - name: Qwen/Qwen2-VL-72B-Instruct - max_input_tokens: 32768 - input_price: 0.4 - output_price: 0.4 - supports_vision: true - - name: deepseek-ai/DeepSeek-V3 - max_input_tokens: 131072 - input_price: 0.25 - output_price: 0.25 - - name: deepseek-ai/DeepSeek-R1 - max_input_tokens: 163840 - input_price: 2 - output_price: 2 - - name: mistralai/Pixtral-12B-2409 - max_input_tokens: 128000 - input_price: 0.1 - output_price: 0.1 - supports_vision: true - -# Links: -# - https://novita.ai/models -# - https://novita.ai/docs/guides/llm-api -- provider: novita - models: - - name: meta-llama/llama-3.3-70b-instruct - max_input_tokens: 131072 - input_price: 0.39 - output_price: 0.39 - - name: meta-llama/llama-3.1-70b-instruct - max_input_tokens: 32768 - input_price: 0.34 - output_price: 0.39 - - name: meta-llama/llama-3.1-8b-instruct - max_input_tokens: 16384 - input_price: 0.05 - output_price: 0.05 - - name: meta-llama/llama-3.2-11b-vision-instruct - max_input_tokens: 32768 - input_price: 0.06 - output_price: 0.06 - supports_vision: true - - name: qwen/qwen-2.5-72b-instruct - max_input_tokens: 32000 - input_price: 0.38 - output_price: 0.4 - - name: qwen/qwen-2-vl-72b-instruct - max_input_tokens: 32768 - input_price: 0.45 - output_price: 0.45 - supports_vision: true - - name: deepseek/deepseek_v3 - max_input_tokens: 64000 - input_price: 0.89 - output_price: 0.89 - - name: deepseek/deepseek-r1 - max_input_tokens: 64000 - input_price: 4 - output_price: 4 - - name: deepseek/deepseek-r1-distill-llama-70b - max_input_tokens: 32000 - input_price: 0.8 - output_price: 0.8 - - name: deepseek/deepseek-r1-distill-qwen-32b - max_input_tokens: 128000 - input_price: 0.3 - output_price: 0.3 - - name: mistralai/mistral-nemo - max_input_tokens: 131072 - input_price: 0.17 - output_price: 0.17 - # Links: # - https://jina.ai/models # - https://api.jina.ai/redoc diff --git a/src/client/mod.rs b/src/client/mod.rs index af0ace1..92fd31f 100644 --- a/src/client/mod.rs +++ b/src/client/mod.rs @@ -33,7 +33,7 @@ register_client!( (bedrock, "bedrock", BedrockConfig, BedrockClient), ); -pub const OPENAI_COMPATIBLE_PROVIDERS: [(&str, &str); 24] = [ +pub const OPENAI_COMPATIBLE_PROVIDERS: [(&str, &str); 22] = [ ("ai21", "https://api.ai21.com/studio/v1"), ( "cloudflare", @@ -46,12 +46,10 @@ pub const OPENAI_COMPATIBLE_PROVIDERS: [(&str, &str); 24] = [ ("github", "https://models.inference.ai.azure.com"), ("groq", "https://api.groq.com/openai/v1"), ("hunyuan", "https://api.hunyuan.cloud.tencent.com/v1"), - ("hyperbolic", "https://api.hyperbolic.xyz/v1"), ("lingyiwanwu", "https://api.lingyiwanwu.com/v1"), ("minimax", "https://api.minimax.chat/v1"), ("mistral", "https://api.mistral.ai/v1"), ("moonshot", "https://api.moonshot.cn/v1"), - ("novita", "https://api.novita.ai/v3/openai"), ("openrouter", "https://openrouter.ai/api/v1"), ("perplexity", "https://api.perplexity.ai"), ( -- cgit v1.2.3