summaryrefslogtreecommitdiffstats
path: root/models.yaml
diff options
context:
space:
mode:
Diffstat (limited to 'models.yaml')
-rw-r--r--models.yaml337
1 files changed, 143 insertions, 194 deletions
diff --git a/models.yaml b/models.yaml
index eda9edd..fd4cc39 100644
--- a/models.yaml
+++ b/models.yaml
@@ -31,13 +31,6 @@
output_price: 0.4
supports_vision: true
supports_function_calling: true
- - name: gpt-5-codex
- max_input_tokens: 400000
- max_output_tokens: 128000
- input_price: 1.25
- output_price: 10
- supports_vision: true
- supports_function_calling: true
- name: gpt-4.1
max_input_tokens: 1047576
max_output_tokens: 32768
@@ -259,6 +252,30 @@
thinking:
type: enabled
budget_tokens: 16000
+ - name: claude-haiku-4-5-20251001
+ max_input_tokens: 200000
+ max_output_tokens: 8192
+ require_max_tokens: true
+ input_price: 1
+ output_price: 5
+ supports_vision: true
+ supports_function_calling: true
+ - name: claude-haiku-4-5-20251001:thinking
+ real_name: claude-haiku-4-5-20251001
+ max_input_tokens: 200000
+ max_output_tokens: 24000
+ require_max_tokens: true
+ input_price: 1
+ output_price: 5
+ supports_vision: true
+ supports_function_calling: true
+ patch:
+ body:
+ temperature: null
+ top_p: null
+ thinking:
+ type: enabled
+ budget_tokens: 16000
- name: claude-opus-4-1-20250805
max_input_tokens: 200000
max_output_tokens: 8192
@@ -660,6 +677,29 @@
thinking:
type: enabled
budget_tokens: 16000
+ - name: claude-haiku-4-5@20251001
+ max_input_tokens: 200000
+ max_output_tokens: 8192
+ require_max_tokens: true
+ input_price: 1
+ output_price: 5
+ supports_vision: true
+ supports_function_calling: true
+ - name: claude-haiku-4-5@20251001:thinking
+ real_name: claude-haiku-4-5@20251001
+ max_input_tokens: 200000
+ max_output_tokens: 24000
+ require_max_tokens: true
+ input_price: 1
+ output_price: 5
+ supports_vision: true
+ patch:
+ body:
+ temperature: null
+ top_p: null
+ thinking:
+ type: enabled
+ budget_tokens: 16000
- name: claude-opus-4-1@20250805
max_input_tokens: 200000
max_output_tokens: 8192
@@ -817,6 +857,31 @@
thinking:
type: enabled
budget_tokens: 16000
+ - name: us.anthropic.claude-haiku-4-5-20251001-v1:0
+ max_input_tokens: 200000
+ max_output_tokens: 8192
+ require_max_tokens: true
+ input_price: 1
+ output_price: 5
+ supports_vision: true
+ supports_function_calling: true
+ - name: us.anthropic.claude-haiku-4-5-20251001-v1:0:thinking
+ real_name: us.anthropic.claude-haiku-4-5-20251001-v1:0
+ max_input_tokens: 200000
+ max_output_tokens: 24000
+ require_max_tokens: true
+ input_price: 1
+ output_price: 5
+ supports_vision: true
+ patch:
+ body:
+ inferenceConfig:
+ temperature: null
+ topP: null
+ additionalModelRequestFields:
+ thinking:
+ type: enabled
+ budget_tokens: 16000
- name: us.anthropic.claude-opus-4-1-20250805-v1:0
max_input_tokens: 200000
max_output_tokens: 8192
@@ -1070,70 +1135,25 @@
# - https://help.aliyun.com/zh/model-studio/developer-reference/use-qwen-by-calling-api
- provider: qianwen
models:
- - name: qwen-max-latest
- max_input_tokens: 32678
- max_output_tokens: 8192
- input_price: 1.6
- output_price: 6.4
+ - name: qwen3-max
+ max_input_tokens: 262144
supports_function_calling: true
- - name: qwen-plus-latest
+ - name: qwen-plus
max_input_tokens: 131072
- max_output_tokens: 8192
- input_price: 0.112
- output_price: 0.28
supports_function_calling: true
- - name: qwen-turbo-latest
+ - name: qwen-flash
max_input_tokens: 1000000
- max_output_tokens: 8192
- input_price: 0.042
- output_price: 0.084
- supports_function_calling: true
- - name: qwen-long
- max_input_tokens: 1000000
- input_price: 0.07
- output_price: 0.28
- - name: qwen-omni-turbo-latest
- max_input_tokens: 32768
- max_output_tokens: 2048
- supports_vision: true
- - name: qwen-coder-plus-latest
- max_input_tokens: 131072
- max_output_tokens: 8192
- input_price: 0.49
- output_price: 0.98
- - name: qwen-coder-turbo-latest
- max_input_tokens: 131072
- max_output_tokens: 8192
- input_price: 0.28
- output_price: 0.84
- - name: qwen-vl-max-latest
- max_input_tokens: 30720
- max_output_tokens: 2048
- input_price: 0.42
- output_price: 1.26
- supports_vision: true
- - name: qwen-vl-plus-latest
- max_input_tokens: 30000
- max_output_tokens: 2048
- input_price: 0.21
- output_price: 0.63
- supports_vision: true
- - name: qwen3-max
- max_input_tokens: 262144
- input_price: 2.1
- output_price: 8.4
supports_function_calling: true
- name: qwen3-vl-plus
max_input_tokens: 262144
- input_price: 0.42
- output_price: 4.2
supports_vision: true
- - name: qwen3-max-preview
+ - name: qwen3-vl-flash
max_input_tokens: 262144
- max_output_tokens: 32768
- input_price: 1.4
- output_price: 5.6
- supports_function_calling: true
+ supports_vision: true
+ - name: qwen-coder-plus
+ max_input_tokens: 1000000
+ - name: qwen-coder-flash
+ max_input_tokens: 1000000
- name: qwen3-next-80b-a3b-instruct
max_input_tokens: 131072
input_price: 0.14
@@ -1161,6 +1181,16 @@
max_input_tokens: 131072
input_price: 0.105
output_price: 1.05
+ - name: qwen3-vl-32b-instruct
+ max_input_tokens: 131072
+ input_price: 0.28
+ output_price: 1.12
+ supports_vision: true
+ - name: qwen3-vl-8b-instruct
+ max_input_tokens: 131072
+ input_price: 0.07
+ output_price: 0.28
+ supports_vision: true
- name: qwen3-coder-480b-a35b-instruct
max_input_tokens: 262144
input_price: 1.26
@@ -1169,32 +1199,10 @@
max_input_tokens: 262144
input_price: 0.315
output_price: 1.26
- - name: qwen2.5-72b-instruct
- max_input_tokens: 129024
- max_output_tokens: 8192
- input_price: 0.56
- output_price: 1.68
- supports_function_calling: true
- - name: qwen2.5-vl-72b-instruct
- max_input_tokens: 129024
- max_output_tokens: 8192
- input_price: 2.24
- output_price: 6.72
- supports_vision: true
- - name: qwen2.5-coder-32b-instruct
- max_input_tokens: 129024
- max_output_tokens: 8192
- input_price: 0.49
- output_price: 0.98
- supports_function_calling: true
- - name: deepseek-v3.1
+ - name: deepseek-v3.2-exp
max_input_tokens: 131072
input_price: 0.28
- output_price: 1.12
- - name: deepseek-r1-0528
- max_input_tokens: 65536
- input_price: 0.28
- output_price: 1.12
+ output_price: 0.42
- name: text-embedding-v4
type: embedding
input_price: 0.1
@@ -1294,7 +1302,7 @@
# - https://open.bigmodel.cn/dev/api#glm-4
- provider: zhipuai
models:
- - name: glm-4.5
+ - name: glm-4.6
max_input_tokens: 202752
input_price: 0.28
output_price: 1.12
@@ -1354,19 +1362,15 @@
input_price: 0.112
# Links:
-# - https://platform.minimaxi.com/document/pricing
+# - https://platform.minimaxi.com/docs/guides/pricing
# - https://platform.minimaxi.com/document/ChatCompletion%20v2
- provider: minimax
models:
- - name: minimax-text-01
- max_input_tokens: 1000192
- input_price: 0.14
- output_price: 1.12
- supports_vision: true
- - name: minimax-m1
- max_input_tokens: 131072
- input_price: 0.112
- output_price: 1.12
+ - name: minimax-m2
+ max_input_tokens: 204800
+ input_price: 0.294
+ output_price: 1.176
+ supports_function_calling: true
# Links:
# - https://openrouter.ai/models
@@ -1401,13 +1405,6 @@
output_price: 0.4
supports_vision: true
supports_function_calling: true
- - name: openai/gpt-5-codex
- max_input_tokens: 400000
- max_output_tokens: 128000
- input_price: 1.25
- output_price: 10
- supports_vision: true
- supports_function_calling: true
- name: openai/gpt-4.1
max_input_tokens: 1047576
max_output_tokens: 32768
@@ -1564,6 +1561,14 @@
output_price: 15
supports_vision: true
supports_function_calling: true
+ - name: anthropic/claude-haiku-4.5
+ max_input_tokens: 200000
+ max_output_tokens: 8192
+ require_max_tokens: true
+ input_price: 1
+ output_price: 5
+ supports_vision: true
+ supports_function_calling: true
- name: anthropic/claude-opus-4.1
max_input_tokens: 200000
max_output_tokens: 8192
@@ -1697,11 +1702,10 @@
patch:
body:
include_reasoning: true
- - name: qwen/qwen-max
- max_input_tokens: 32768
- max_output_tokens: 8192
- input_price: 1.6
- output_price: 6.4
+ - name: qwen/qwen3-max
+ max_input_tokens: 262144
+ input_price: 1.2
+ output_price: 6
supports_function_calling: true
- name: qwen/qwen-plus
max_input_tokens: 131072
@@ -1709,22 +1713,6 @@
input_price: 0.4
output_price: 1.2
supports_function_calling: true
- - name: qwen/qwen-turbo
- max_input_tokens: 1000000
- max_output_tokens: 8192
- input_price: 0.05
- output_price: 0.2
- supports_function_calling: true
- - name: qwen/qwen-vl-plus
- max_input_tokens: 7500
- input_price: 0.21
- output_price: 0.63
- supports_vision: true
- - name: qwen/qwen3-max
- max_input_tokens: 262144
- input_price: 1.2
- output_price: 6
- supports_function_calling: true
- name: qwen/qwen3-next-80b-a3b-instruct
max_input_tokens: 262144
input_price: 0.1
@@ -1734,7 +1722,7 @@
max_input_tokens: 262144
input_price: 0.1
output_price: 0.8
- - name: qwen/qwen3-235b-a22b-2507
+ - name: qwen/qwen5-235b-a22b-2507 # Qwen3 235B A22B Instruct 2507
max_input_tokens: 262144
input_price: 0.12
output_price: 0.59
@@ -1751,6 +1739,16 @@
max_input_tokens: 262144
input_price: 0.071
output_price: 0.285
+ - name: qwen/qwen3-vl-32b-instruct
+ max_input_tokens: 262144
+ input_price: 0.35
+ output_price: 1.1
+ supports_vision: true
+ - name: qwen/qwen3-vl-8b-instruct
+ max_input_tokens: 262144
+ input_price: 0.08
+ output_price: 0.50
+ supports_vision: true
- name: qwen/qwen3-coder-plus
max_input_tokens: 128000
input_price: 1
@@ -1761,25 +1759,16 @@
input_price: 0.3
output_price: 1.5
supports_function_calling: true
+ - name: qwen/qwen3-coder # Qwen3 Coder 480B A35B
+ max_input_tokens: 262144
+ input_price: 0.22
+ output_price: 0.95
+ supports_function_calling: true
- name: qwen/qwen3-coder-30b-a3b-instruct
max_input_tokens: 262144
input_price: 0.052
output_price: 0.207
supports_function_calling: true
- - name: qwen/qwen-2.5-72b-instruct
- max_input_tokens: 131072
- input_price: 0.35
- output_price: 0.4
- supports_function_calling: true
- - name: qwen/qwen2.5-vl-72b-instruct
- max_input_tokens: 32000
- input_price: 0.7
- output_price: 0.7
- supports_vision: true
- - name: qwen/qwen-2.5-coder-32b-instruct
- max_input_tokens: 32768
- input_price: 0.18
- output_price: 0.18
- name: moonshotai/kimi-k2-0905
max_input_tokens: 262144
input_price: 0.296
@@ -1805,6 +1794,11 @@
input_price: 0.2
output_price: 1.5
supports_function_calling: true
+ - name: amazon/nova-premier-v1
+ max_input_tokens: 1000000
+ input_price: 2.5
+ output_price: 12.5
+ supports_vision: true
- name: amazon/nova-pro-v1
max_input_tokens: 300000
max_output_tokens: 5120
@@ -1851,29 +1845,15 @@
patch:
body:
include_reasoning: true
- - name: minimax/minimax-01
- max_input_tokens: 1000192
- input_price: 0.2
- output_price: 1.1
+ - name: minimax/minimax-m2
+ max_input_tokens: 196608
+ input_price: 0.15
+ output_price: 0.45
- name: z-ai/glm-4.6
max_input_tokens: 202752
input_price: 0.5
output_price: 1.75
supports_function_calling: true
- - name: z-ai/glm-4.5
- max_input_tokens: 131072
- input_price: 0.2
- output_price: 0.2
- supports_function_calling: true
- - name: z-ai/glm-4.5-air
- max_input_tokens: 131072
- input_price: 0.2
- output_price: 1.1
- - name: z-ai/glm-4.5v
- max_input_tokens: 65536
- input_price: 0.5
- output_price: 1.7
- supports_vision: true
# Links:
# - https://github.com/marketplace?type=models
@@ -2069,10 +2049,6 @@
input_price: 0.08
output_price: 0.3
supports_vision: true
- - name: meta-llama/Llama-3.3-70B-Instruct
- max_input_tokens: 131072
- input_price: 0.23
- output_price: 0.40
- name: Qwen/Qwen3-Next-80B-A3B-Instruct
max_input_tokens: 262144
input_price: 0.14
@@ -2101,27 +2077,15 @@
input_price: 0.07
output_price: 0.27
supports_function_calling: true
- - name: Qwen/Qwen3-235B-A22B
- max_input_tokens: 40960
- input_price: 0.15
- output_price: 0.6
- name: Qwen/Qwen3-30B-A3B
max_input_tokens: 40960
input_price: 0.1
output_price: 0.3
- - name: Qwen/Qwen3-32B
- max_input_tokens: 40960
- input_price: 0.1
- output_price: 0.3
- - name: Qwen/Qwen2.5-72B-Instruct
- max_input_tokens: 32768
- input_price: 0.23
- output_price: 0.40
- supports_function_calling: true
- - name: Qwen/Qwen2.5-Coder-32B-Instruct
- max_input_tokens: 32768
- input_price: 0.07
- output_price: 0.16
+ - name: Qwen/Qwen3-VL-8B-Instruct
+ max_input_tokens: 262144
+ input_price: 0.18
+ output_price: 0.69
+ supports_vision: true
- name: deepseek-ai/DeepSeek-V3.2-Exp
max_input_tokens: 163840
input_price: 0.27
@@ -2160,21 +2124,6 @@
input_price: 0.6
output_price: 1.9
supports_function_calling: true
- - name: zai-org/GLM-4.5
- max_input_tokens: 131072
- input_price: 0.55
- output_price: 2.0
- supports_function_calling: true
- - name: zai-org/GLM-4.5-Air
- max_input_tokens: 131072
- input_price: 0.2
- output_price: 1.1
- supports_function_calling: true
- - name: zai-org/GLM-4.5V
- max_input_tokens: 65536
- input_price: 0.5
- output_price: 1.7
- supports_vision: true
- name: BAAI/bge-large-en-v1.5
type: embedding
input_price: 0.01
generated by cgit v1.2.3 (git 2.39.1) at 2026-10-02 23:43:40 +0000