summaryrefslogtreecommitdiffstats
path: root/models.yaml
diff options
context:
space:
mode:
authorsigoden <sigoden@gmail.com>2025-02-06 08:49:17 +0800
committerGitHub <noreply@github.com>2025-02-06 08:49:17 +0800
commit4812e446ee30467bd3ecce983a826f7649de7110 (patch)
treea44bf9ad94db9008199a619af8398b1a62b0ac25 /models.yaml
parent470eeb2efc8b5c9f20ec275d3b2ced1d92e1642d (diff)
downloadaichat-4812e446ee30467bd3ecce983a826f7649de7110.tar.gz
refactor: several improvements (#1149)
Diffstat (limited to 'models.yaml')
-rw-r--r--models.yaml62
1 files changed, 53 insertions, 9 deletions
diff --git a/models.yaml b/models.yaml
index 3618dcf..2b6b62e 100644
--- a/models.yaml
+++ b/models.yaml
@@ -53,7 +53,6 @@
supports_vision: true
supports_function_calling: true
supports_reasoning: true
- no_system_message: true
- name: o1
max_input_tokens: 200000
input_price: 15
@@ -61,7 +60,6 @@
supports_vision: true
supports_function_calling: true
supports_reasoning: true
- no_system_message: true
- name: o1-preview
max_input_tokens: 128000
max_output_tokens: 32768
@@ -122,6 +120,20 @@
output_price: 0
supports_vision: true
supports_function_calling: true
+ - name: gemini-2.0-flash
+ max_input_tokens: 1048576
+ max_output_tokens: 8192
+ input_price: 0
+ output_price: 0
+ supports_vision: true
+ supports_function_calling: true
+ - name: gemini-2.0-flash-lite-preview
+ max_input_tokens: 1048576
+ max_output_tokens: 8192
+ input_price: 0
+ output_price: 0
+ supports_vision: true
+ supports_function_calling: true
- name: gemini-2.0-flash-exp
max_input_tokens: 1048576
max_output_tokens: 8192
@@ -136,7 +148,7 @@
output_price: 0
supports_vision: true
supports_reasoning: true
- - name: gemini-exp-1206
+ - name: gemini-2.0-pro-exp
max_input_tokens: 2097152
max_output_tokens: 8192
input_price: 0
@@ -468,10 +480,24 @@
- name: gemini-1.5-flash-002
max_input_tokens: 1048576
max_output_tokens: 8192
- input_price: 0.01875
+ input_price: 0.019
output_price: 0.075
supports_vision: true
supports_function_calling: true
+ - name: gemini-2.0-flash-001
+ max_input_tokens: 1048576
+ max_output_tokens: 8192
+ input_price: 0.15
+ output_price: 0.6
+ supports_vision: true
+ supports_function_calling: true
+ - name: gemini-2.0-flash-lite-preview-02-05
+ max_input_tokens: 1048576
+ max_output_tokens: 8192
+ input_price: 0.075
+ output_price: 0.3
+ supports_vision: true
+ supports_function_calling: true
- name: gemini-2.0-flash-exp
max_input_tokens: 1048576
max_output_tokens: 8192
@@ -482,6 +508,11 @@
max_output_tokens: 8192
supports_vision: true
supports_reasoning: true
+ - name: gemini-2.0-pro-exp-02-05
+ max_input_tokens: 2097152
+ max_output_tokens: 8192
+ supports_vision: true
+ supports_function_calling: true
- name: claude-3-5-sonnet-v2@20241022
max_input_tokens: 200000
max_output_tokens: 8192
@@ -757,7 +788,7 @@
max_batch_size: 100
# Links:
-# - https://cloud.baidu.com/doc/WENXINWORKSHOP/s/Nlks5zkzu
+# - https://cloud.baidu.com/doc/WENXINWORKSHOP/s/Fm2vrveyu
# - https://cloud.baidu.com/doc/WENXINWORKSHOP/s/hlrk4akp7
- provider: ernie
models:
@@ -1141,7 +1172,6 @@
supports_vision: true
supports_function_calling: true
supports_reasoning: true
- no_system_message: true
- name: openai/o1
max_input_tokens: 128000
input_price: 15
@@ -1149,7 +1179,6 @@
supports_vision: true
supports_function_calling: true
supports_reasoning: true
- no_system_message: true
- name: openai/o1-preview
max_input_tokens: 128000
input_price: 15
@@ -1185,6 +1214,12 @@
output_price: 0.15
supports_vision: true
supports_function_calling: true
+ - name: google/gemini-2.0-flash-001
+ max_input_tokens: 1000000
+ input_price: 0.1
+ output_price: 0.4
+ supports_vision: true
+ supports_function_calling: true
- name: anthropic/claude-3.5-sonnet
max_input_tokens: 200000
max_output_tokens: 8192
@@ -1442,13 +1477,11 @@
supports_function_calling: true
supports_vision: true
supports_reasoning: true
- no_system_message: true
- name: o1
max_input_tokens: 200000
supports_function_calling: true
supports_vision: true
supports_reasoning: true
- no_system_message: true
- name: o1-preview
max_input_tokens: 128000
supports_reasoning: true
@@ -1729,6 +1762,7 @@
max_tokens_per_chunk: 512
default_chunk_size: 1000
max_batch_size: 100
+
# Links
# - https://cloud.siliconflow.cn/models
# - https://docs.siliconflow.cn/api-reference/chat-completions/chat-completions
@@ -1798,6 +1832,16 @@
input_price: 2.24
output_price: 2.24
supports_reasoning: true
+ - name: deepseek-ai/DeepSeek-R1-Distill-Llama-70B
+ max_input_tokens: 32768
+ input_price: 0.578
+ output_price: 0.578
+ supports_reasoning: true
+ - name: deepseek-ai/DeepSeek-R1-Distill-Qwen-32B
+ max_input_tokens: 32768
+ input_price: 0.176
+ output_price: 0.176
+ supports_reasoning: true
- name: deepseek-ai/DeepSeek-V2.5
max_input_tokens: 32768
input_price: 0.7