diff options
| -rw-r--r-- | models.yaml | 203 |
1 files changed, 102 insertions, 101 deletions
diff --git a/models.yaml b/models.yaml index a62bb37..1a426ed 100644 --- a/models.yaml +++ b/models.yaml @@ -31,12 +31,6 @@ output_price: 10 supports_vision: true supports_function_calling: true - - name: gpt-4o-search-preview - max_input_tokens: 128000 - max_output_tokens: 16384 - input_price: 2.5 - output_price: 10 - supports_vision: true - name: gpt-4o-mini max_input_tokens: 128000 max_output_tokens: 16384 @@ -44,19 +38,6 @@ output_price: 0.6 supports_vision: true supports_function_calling: true - - name: gpt-4o-mini-search-preview - max_input_tokens: 128000 - max_output_tokens: 16384 - input_price: 0.15 - output_price: 0.6 - supports_vision: true - - name: chatgpt-4o-latest - max_input_tokens: 128000 - max_output_tokens: 16384 - input_price: 5 - output_price: 15 - supports_vision: true - supports_function_calling: true - name: o4-mini max_input_tokens: 200000 input_price: 1.1 @@ -85,8 +66,8 @@ top_p: null - name: o3 max_input_tokens: 200000 - input_price: 10 - output_price: 40 + input_price: 2 + output_price: 8 supports_vision: true supports_function_calling: true system_prompt_prefix: Formatting re-enabled @@ -95,6 +76,20 @@ max_tokens: null temperature: null top_p: null + - name: o3-high + real_name: o3 + max_input_tokens: 200000 + input_price: 2 + output_price: 8 + supports_vision: true + supports_function_calling: true + system_prompt_prefix: Formatting re-enabled + patch: + body: + reasoning_effort: high + max_tokens: null + temperature: null + top_p: null - name: o3-mini max_input_tokens: 200000 input_price: 1.1 @@ -365,13 +360,19 @@ - provider: cohere models: - name: command-a-03-2025 - max_input_tokens: 256000 + max_input_tokens: 262144 max_output_tokens: 8192 input_price: 2.5 output_price: 10 supports_function_calling: true + - name: command-a-vision-07-2025 + max_input_tokens: 131072 + max_output_tokens: 8192 + input_price: 2.5 + output_price: 10 + supports_vision: true - name: command-r7b-12-2024 - max_input_tokens: 128000 + max_input_tokens: 131072 max_output_tokens: 4096 input_price: 0.0375 output_price: 0.15 @@ -408,6 +409,11 @@ # - https://docs.x.ai/docs/api-reference#chat-completions - provider: xai models: + - name: grok-4 + max_input_tokens: 256000 + input_price: 3 + output_price: 15 + supports_function_calling: true - name: grok-3 max_input_tokens: 131072 input_price: 3 @@ -422,18 +428,15 @@ max_input_tokens: 131072 input_price: 0.3 output_price: 0.5 + supports_function_calling: true - name: grok-3-mini-fast max_input_tokens: 131072 input_price: 0.6 output_price: 4 - - name: grok-4 - max_input_tokens: 256000 - input_price: 3 - output_price: 15 + supports_function_calling: true # Links: -# - https://docs.perplexity.ai/models/model-cards -# - https://docs.perplexity.ai/guides/pricing +# - https://docs.perplexity.ai/getting-started/models # - https://docs.perplexity.ai/api-reference/chat-completions - provider: perplexity models: @@ -457,10 +460,6 @@ max_input_tokens: 128000 input_price: 2 output_price: 8 - - name: r1-1776 - max_input_tokens: 128000 - input_price: 2 - output_price: 8 # Links: # - https://console.groq.com/docs/models @@ -511,8 +510,8 @@ - name: gemini-2.5-flash max_input_tokens: 1048576 max_output_tokens: 65536 - input_price: 0.15 - output_price: 0.6 + input_price: 0.3 + output_price: 2.5 supports_vision: true supports_function_calling: true - name: gemini-2.5-pro @@ -525,7 +524,7 @@ - name: gemini-2.5-flash-lite max_input_tokens: 1048576 max_output_tokens: 65536 - input_price: 0.1 + input_price: 0.3 output_price: 0.4 supports_vision: true supports_function_calling: true @@ -830,12 +829,6 @@ require_max_tokens: true input_price: 0 output_price: 0 - - name: '@cf/qwen/qwq-32b' - max_input_tokens: 131072 - max_output_tokens: 2048 - require_max_tokens: true - input_price: 0 - output_price: 0 - name: '@cf/qwen/qwen2.5-coder-32b-instruct' max_input_tokens: 131072 max_output_tokens: 2048 @@ -928,11 +921,6 @@ max_input_tokens: 32768 max_output_tokens: 2048 supports_vision: true - - name: qwq-plus-latest - max_input_tokens: 131072 - max_output_tokens: 8192 - input_price: 0.224 - output_price: 0.56 - name: qwen-coder-plus-latest max_input_tokens: 131072 max_output_tokens: 8192 @@ -964,6 +952,15 @@ max_input_tokens: 131072 input_price: 0.28 output_price: 2.8 + - name: qwen3-30b-a3b-instruct-2507 + max_input_tokens: 131072 + input_price: 0.105 + output_price: 0.42 + supports_function_calling: true + - name: qwen3-30b-a3b-thinking-2507 + max_input_tokens: 131072 + input_price: 0.105 + output_price: 1.05 - name: qwen3-235b-a22b max_input_tokens: 131072 max_output_tokens: 8192 @@ -979,11 +976,6 @@ max_output_tokens: 8192 input_price: 0.28 output_price: 1.12 - - name: qwq-32b - max_input_tokens: 131072 - max_output_tokens: 8192 - input_price: 0.28 - output_price: 0.84 - name: qwen2.5-72b-instruct max_input_tokens: 129024 max_output_tokens: 8192 @@ -1075,6 +1067,12 @@ output_price: 2.24 supports_vision: true supports_function_calling: true + - name: kimi-k2-turbo-preview + max_input_tokens: 131072 + input_price: 1.12 + output_price: 4.48 + supports_vision: true + supports_function_calling: true - name: kimi-thinking-preview max_input_tokens: 131072 input_price: 28 @@ -1214,30 +1212,12 @@ output_price: 10 supports_vision: true supports_function_calling: true - - name: openai/gpt-4o-search-preview - max_input_tokens: 128000 - max_output_tokens: 16384 - input_price: 2.5 - output_price: 10 - supports_vision: true - name: openai/gpt-4o-mini max_input_tokens: 128000 input_price: 0.15 output_price: 0.6 supports_vision: true supports_function_calling: true - - name: openai/gpt-4o-mini-search-preview - max_input_tokens: 128000 - max_output_tokens: 16384 - input_price: 0.15 - output_price: 0.6 - supports_vision: true - - name: openai/chatgpt-4o-latest - max_input_tokens: 128000 - input_price: 5 - output_price: 15 - supports_vision: true - supports_function_calling: true - name: openai/o4-mini max_input_tokens: 200000 input_price: 1.1 @@ -1263,10 +1243,10 @@ max_tokens: null temperature: null top_p: null - - name: openai/o3-pro + - name: openai/o3 max_input_tokens: 200000 - input_price: 20 - output_price: 80 + input_price: 2 + output_price: 8 supports_vision: true supports_function_calling: true system_prompt_prefix: Formatting re-enabled @@ -1275,16 +1255,17 @@ max_tokens: null temperature: null top_p: null - - name: openai/o3 + - name: openai/o3-high + real_name: openai/o3 max_input_tokens: 200000 - input_price: 10 - output_price: 40 + input_price: 2 + output_price: 8 supports_vision: true supports_function_calling: true system_prompt_prefix: Formatting re-enabled patch: body: - max_tokens: null + reasoning_effort: high temperature: null top_p: null - name: openai/o3-mini @@ -1311,8 +1292,8 @@ top_p: null - name: google/gemini-2.5-flash max_input_tokens: 1048576 - input_price: 0.15 - output_price: 0.6 + input_price: 0.3 + output_price: 2.5 supports_vision: true supports_function_calling: true - name: google/gemini-2.5-pro @@ -1323,13 +1304,13 @@ supports_function_calling: true - name: google/gemini-2.5-flash-lite max_input_tokens: 1048576 - input_price: 0.1 + input_price: 0.3 output_price: 0.4 supports_vision: true - name: google/gemini-2.0-flash-001 max_input_tokens: 1000000 - input_price: 0.1 - output_price: 0.4 + input_price: 0.15 + output_price: 0.6 supports_vision: true supports_function_calling: true - name: google/gemini-2.0-flash-lite-001 @@ -1436,12 +1417,12 @@ input_price: 0.4 output_price: 2 supports_function_calling: true - - name: mistralai/devstral-small-2505 + - name: mistralai/devstral-small max_input_tokens: 131072 - input_price: 0.06 - output_price: 0.12 + input_price: 0.07 + output_price: 0.28 supports_function_calling: true - - name: mistralai/codestral-2501 + - name: mistralai/codestral-2508 max_input_tokens: 256000 input_price: 0.3 output_price: 0.9 @@ -1510,6 +1491,10 @@ max_input_tokens: 262144 input_price: 0.118 output_price: 0.118 + - name: qwen/qwen3-30b-a3b-instruct-2507 + max_input_tokens: 131072 + input_price: 0.2 + output_price: 0.8 - name: qwen/qwen3-coder max_input_tokens: 262144 input_price: 0.3 @@ -1527,10 +1512,6 @@ max_input_tokens: 40960 input_price: 0.1 output_price: 0.3 - - name: qwen/qwq-32b - max_input_tokens: 128000 - input_price: 0.29 - output_price: 0.39 - name: qwen/qwen-2.5-72b-instruct max_input_tokens: 131072 input_price: 0.35 @@ -1610,17 +1591,19 @@ patch: body: include_reasoning: true - - name: perplexity/r1-1776 - max_input_tokens: 127000 - input_price: 2 - output_price: 8 - patch: - body: - include_reasoning: true - name: minimax/minimax-01 max_input_tokens: 1000192 input_price: 0.2 output_price: 1.1 + - 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 # Links: # - https://github.com/marketplace?type=models @@ -1681,6 +1664,18 @@ max_tokens: null temperature: null top_p: null + - name: o3-high + real_name: o3 + max_input_tokens: 200000 + supports_vision: true + supports_function_calling: true + system_prompt_prefix: Formatting re-enabled + patch: + body: + reasoning_effort: high + max_tokens: null + temperature: null + top_p: null - name: o3-mini max_input_tokens: 200000 supports_vision: true @@ -1804,10 +1799,6 @@ max_input_tokens: 40960 input_price: 0.1 output_price: 0.3 - - name: Qwen/QwQ-32B - max_input_tokens: 131072 - input_price: 0.12 - output_price: 0.18 - name: Qwen/Qwen2.5-72B-Instruct max_input_tokens: 32768 input_price: 0.23 @@ -1842,6 +1833,16 @@ input_price: 0.55 output_price: 2.2 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: BAAI/bge-large-en-v1.5 type: embedding input_price: 0.01 |