Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 0 additions & 1 deletion Argcfile.sh
Original file line number Diff line number Diff line change
Expand Up @@ -92,7 +92,6 @@ OPENAI_COMPATIBLE_PLATFORMS=( \
mistral,open-mistral-nemo,https://api.mistral.ai/v1 \
moonshot,moonshot-v1-8k,https://api.moonshot.cn/v1 \
openrouter,openai/gpt-4o-mini,https://openrouter.ai/api/v1 \
octoai,meta-llama-3.1-8b-instruct,https://text.octoai.run/v1 \
ollama,llama3.1:latest,http://localhost:11434/v1 \
perplexity,llama-3.1-8b-instruct,https://api.perplexity.ai \
qianwen,qwen-turbo,https://dashscope.aliyuncs.com/compatible-mode/v1 \
Expand Down
6 changes: 0 additions & 6 deletions config.example.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -296,12 +296,6 @@ clients:
api_base: https://openrouter.ai/api/v1
api_key: xxx

# See https://octo.ai/docs/getting-started/quickstart
- type: openai-compatible
name: octoai
api_base: https://text.octoai.run/v1
api_key: xxx

# See https://docs.siliconflow.cn/docs/getting-started
- type: openai-compatible
name: siliconflow
Expand Down
31 changes: 0 additions & 31 deletions models.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -1355,37 +1355,6 @@
input_price: 0.4
output_price: 0.4

# Links:
# - https://octo.ai/docs/getting-started/inference-models
# - https://octo.ai/docs/getting-started/pricing-and-billing
- platform: octoai
models:
- name: meta-llama-3.1-405b-instruct
max_input_tokens: 131072
input_price: 3
output_price: 9
supports_function_calling: true
- name: meta-llama-3.1-70b-instruct
max_input_tokens: 131072
input_price: 0.9
output_price: 0.9
supports_function_calling: true
- name: meta-llama-3.1-8b-instruct
max_input_tokens: 131072
input_price: 0.15
output_price: 0.15
supports_function_calling: true
- name: mistral-nemo-instruct
max_input_tokens: 65536
input_price: 0.2
output_price: 0.2
- name: thenlper/gte-large
type: embedding
input_price: 0.05
max_tokens_per_chunk: 512
default_chunk_size: 1000
max_batch_size: 100

# Links
# - https://siliconflow.cn/zh-cn/pricing#siliconcloud-1417
# - https://docs.siliconflow.cn/api-reference/chat-completions/chat-completions
Expand Down
3 changes: 1 addition & 2 deletions src/client/mod.rs
Original file line number Diff line number Diff line change
Expand Up @@ -35,7 +35,7 @@ register_client!(
(ernie, "ernie", ErnieConfig, ErnieClient),
);

pub const OPENAI_COMPATIBLE_PLATFORMS: [(&str, &str); 21] = [
pub const OPENAI_COMPATIBLE_PLATFORMS: [(&str, &str); 20] = [
("ai21", "https://api.ai21.com/studio/v1"),
("cloudflare", ""),
("deepinfra", "https://api.deepinfra.com/v1/openai"),
Expand All @@ -48,7 +48,6 @@ pub const OPENAI_COMPATIBLE_PLATFORMS: [(&str, &str); 21] = [
("mistral", "https://api.mistral.ai/v1"),
("moonshot", "https://api.moonshot.cn/v1"),
("openrouter", "https://openrouter.ai/api/v1"),
("octoai", "https://text.octoai.run/v1"),
("ollama", ""),
("perplexity", "https://api.perplexity.ai"),
(
Expand Down