diff --git a/providers/commandcode/logo.svg b/providers/commandcode/logo.svg new file mode 100644 index 00000000000..fd1d6b13565 --- /dev/null +++ b/providers/commandcode/logo.svg @@ -0,0 +1,3 @@ + + + diff --git a/providers/commandcode/models/MiniMaxAI/MiniMax-M2.5.toml b/providers/commandcode/models/MiniMaxAI/MiniMax-M2.5.toml new file mode 100644 index 00000000000..6b25079282e --- /dev/null +++ b/providers/commandcode/models/MiniMaxAI/MiniMax-M2.5.toml @@ -0,0 +1,7 @@ +# https://commandcode.ai/models/minimax-m2-5 +base_model = "minimax/MiniMax-M2.5" +reasoning_options = [] + +[cost] +input = 0.5 +output = 2 diff --git a/providers/commandcode/models/MiniMaxAI/MiniMax-M2.7.toml b/providers/commandcode/models/MiniMaxAI/MiniMax-M2.7.toml new file mode 100644 index 00000000000..746138a9987 --- /dev/null +++ b/providers/commandcode/models/MiniMaxAI/MiniMax-M2.7.toml @@ -0,0 +1,8 @@ +# https://commandcode.ai/models/minimax-m2-7 +base_model = "minimax/MiniMax-M2.7" +reasoning_options = [] + +[cost] +cache_read = 0.06 +input = 0.3 +output = 1.2 diff --git a/providers/commandcode/models/MiniMaxAI/MiniMax-M3.toml b/providers/commandcode/models/MiniMaxAI/MiniMax-M3.toml new file mode 100644 index 00000000000..25aa1ccc334 --- /dev/null +++ b/providers/commandcode/models/MiniMaxAI/MiniMax-M3.toml @@ -0,0 +1,11 @@ +# https://commandcode.ai/models/minimax-m3 +# Toggle: chat_template_kwargs.thinking_mode = enabled|disabled +base_model = "minimax/MiniMax-M3" + +[[reasoning_options]] +type = "toggle" + +[cost] +cache_read = 0.06 +input = 0.3 +output = 1.2 diff --git a/providers/commandcode/models/Qwen/Qwen3.6-Max-Preview.toml b/providers/commandcode/models/Qwen/Qwen3.6-Max-Preview.toml new file mode 100644 index 00000000000..d1c4b26f26e --- /dev/null +++ b/providers/commandcode/models/Qwen/Qwen3.6-Max-Preview.toml @@ -0,0 +1,16 @@ +# https://commandcode.ai/models/qwen3-6-max-preview +# Toggle: enable_thinking true|false +# Budget: thinking_budget +base_model = "alibaba/qwen3.6-max-preview" + +[[reasoning_options]] +type = "toggle" + +[[reasoning_options]] +type = "budget_tokens" + +[cost] +cache_read = 0.26 +cache_write = 1.63 +input = 1.3 +output = 7.8 diff --git a/providers/commandcode/models/Qwen/Qwen3.6-Plus.toml b/providers/commandcode/models/Qwen/Qwen3.6-Plus.toml new file mode 100644 index 00000000000..6e8e055be78 --- /dev/null +++ b/providers/commandcode/models/Qwen/Qwen3.6-Plus.toml @@ -0,0 +1,15 @@ +# https://commandcode.ai/models/qwen3-6-plus +# Toggle: enable_thinking true|false +# Budget: thinking_budget +base_model = "alibaba/qwen3.6-plus" + +[[reasoning_options]] +type = "toggle" + +[[reasoning_options]] +type = "budget_tokens" + +[cost] +cache_read = 0.1 +input = 0.5 +output = 3 diff --git a/providers/commandcode/models/Qwen/Qwen3.7-Flash.toml b/providers/commandcode/models/Qwen/Qwen3.7-Flash.toml new file mode 100644 index 00000000000..9b53b191598 --- /dev/null +++ b/providers/commandcode/models/Qwen/Qwen3.7-Flash.toml @@ -0,0 +1,16 @@ +# https://commandcode.ai/models/qwen3-7-flash +# Toggle: enable_thinking true|false +# Budget: thinking_budget +base_model = "alibaba/qwen3.7-flash" + +[[reasoning_options]] +type = "toggle" + +[[reasoning_options]] +type = "budget_tokens" + +[cost] +cache_read = 0.006 +cache_write = 0.038 +input = 0.03 +output = 0.13 diff --git a/providers/commandcode/models/Qwen/Qwen3.7-Max.toml b/providers/commandcode/models/Qwen/Qwen3.7-Max.toml new file mode 100644 index 00000000000..43bb735f445 --- /dev/null +++ b/providers/commandcode/models/Qwen/Qwen3.7-Max.toml @@ -0,0 +1,16 @@ +# https://commandcode.ai/models/qwen3-7-max +# Toggle: enable_thinking true|false +# Budget: thinking_budget +base_model = "alibaba/qwen3.7-max" + +[[reasoning_options]] +type = "toggle" + +[[reasoning_options]] +type = "budget_tokens" + +[cost] +cache_read = 0.5 +cache_write = 3.13 +input = 2.5 +output = 7.5 diff --git a/providers/commandcode/models/Qwen/Qwen3.7-Plus.toml b/providers/commandcode/models/Qwen/Qwen3.7-Plus.toml new file mode 100644 index 00000000000..2bc15dc2d9c --- /dev/null +++ b/providers/commandcode/models/Qwen/Qwen3.7-Plus.toml @@ -0,0 +1,16 @@ +# https://commandcode.ai/models/qwen3-7-plus +# Toggle: enable_thinking true|false +# Budget: thinking_budget +base_model = "alibaba/qwen3.7-plus" + +[[reasoning_options]] +type = "toggle" + +[[reasoning_options]] +type = "budget_tokens" + +[cost] +cache_read = 0.08 +cache_write = 0.5 +input = 0.4 +output = 1.6 diff --git a/providers/commandcode/models/Qwen/Qwen3.8-27B.toml b/providers/commandcode/models/Qwen/Qwen3.8-27B.toml new file mode 100644 index 00000000000..97a1658897c --- /dev/null +++ b/providers/commandcode/models/Qwen/Qwen3.8-27B.toml @@ -0,0 +1,25 @@ +# https://commandcode.ai/models/qwen3-8-27b +# Toggle: enable_thinking true|false +# Effort: reasoning_effort = low|medium|xhigh +# Budget: thinking_budget (0..262144) +base_model = "alibaba/qwen3.8-27b" + +[[reasoning_options]] +type = "toggle" + +[[reasoning_options]] +type = "effort" +values = ["low", "medium", "xhigh"] + +[[reasoning_options]] +max = 262144 +min = 0 +type = "budget_tokens" + +[cost] +cache_read = 0.04 +input = 0.4 +output = 3 + +[interleaved] +field = "reasoning_content" diff --git a/providers/commandcode/models/Qwen/Qwen3.8-Flash.toml b/providers/commandcode/models/Qwen/Qwen3.8-Flash.toml new file mode 100644 index 00000000000..f9ec5d2af84 --- /dev/null +++ b/providers/commandcode/models/Qwen/Qwen3.8-Flash.toml @@ -0,0 +1,25 @@ +# https://commandcode.ai/models/qwen3-8-flash +# Toggle: enable_thinking true|false +# Effort: reasoning_effort = low|medium|xhigh +# Budget: thinking_budget (0..262144) +base_model = "alibaba/qwen3.8-flash" + +[[reasoning_options]] +type = "toggle" + +[[reasoning_options]] +type = "effort" +values = ["low", "medium", "xhigh"] + +[[reasoning_options]] +max = 262144 +min = 0 +type = "budget_tokens" + +[cost] +cache_read = 0.016 +input = 0.16 +output = 0.47 + +[interleaved] +field = "reasoning_content" diff --git a/providers/commandcode/models/Qwen/Qwen3.8-Max-0902.toml b/providers/commandcode/models/Qwen/Qwen3.8-Max-0902.toml new file mode 100644 index 00000000000..fb658eed9cf --- /dev/null +++ b/providers/commandcode/models/Qwen/Qwen3.8-Max-0902.toml @@ -0,0 +1,25 @@ +# https://commandcode.ai/models/qwen3-8-max-0902 +# Toggle: enable_thinking true|false +# Effort: reasoning_effort = low|medium|xhigh +# Budget: thinking_budget (0..262144) +base_model = "alibaba/qwen3.8-max-0902" + +[[reasoning_options]] +type = "toggle" + +[[reasoning_options]] +type = "effort" +values = ["low", "medium", "xhigh"] + +[[reasoning_options]] +max = 262144 +min = 0 +type = "budget_tokens" + +[interleaved] +field = "reasoning_content" + +[cost] +cache_read = 0.25 +input = 2 +output = 6 diff --git a/providers/commandcode/models/Qwen/Qwen3.8-Max.toml b/providers/commandcode/models/Qwen/Qwen3.8-Max.toml new file mode 100644 index 00000000000..6c2e6b82df3 --- /dev/null +++ b/providers/commandcode/models/Qwen/Qwen3.8-Max.toml @@ -0,0 +1,26 @@ +# https://commandcode.ai/models/qwen3-8-max +# Toggle: enable_thinking true|false +# Effort: reasoning_effort = low|medium|xhigh +# Budget: thinking_budget (0..262144) +base_model = "alibaba/qwen3.8-max" + +[[reasoning_options]] +type = "toggle" + +[[reasoning_options]] +type = "effort" +values = ["low", "medium", "xhigh"] + +[[reasoning_options]] +max = 262144 +min = 0 +type = "budget_tokens" + +[interleaved] +field = "reasoning_content" + +[cost] +cache_read = 0.25 +cache_write = 2.5 +input = 2 +output = 6 diff --git a/providers/commandcode/models/claude-fable-5-1.toml b/providers/commandcode/models/claude-fable-5-1.toml new file mode 100644 index 00000000000..97d20be09bc --- /dev/null +++ b/providers/commandcode/models/claude-fable-5-1.toml @@ -0,0 +1,12 @@ +# https://commandcode.ai/models/claude-fable-5-1 +base_model = "anthropic/claude-fable-5-1" + +[[reasoning_options]] +type = "effort" +values = ["low", "medium", "high", "xhigh", "max"] + +[cost] +cache_read = 0.25 +cache_write = 12.50 +input = 10.00 +output = 50.00 diff --git a/providers/commandcode/models/claude-fable-5.toml b/providers/commandcode/models/claude-fable-5.toml new file mode 100644 index 00000000000..a7dee706a12 --- /dev/null +++ b/providers/commandcode/models/claude-fable-5.toml @@ -0,0 +1,12 @@ +# https://commandcode.ai/models/claude-fable-5 +base_model = "anthropic/claude-fable-5" + +[[reasoning_options]] +type = "effort" +values = ["low", "medium", "high", "xhigh", "max"] + +[cost] +cache_read = 1.00 +cache_write = 12.50 +input = 10.00 +output = 50.00 diff --git a/providers/commandcode/models/claude-haiku-4-5-20251001.toml b/providers/commandcode/models/claude-haiku-4-5-20251001.toml new file mode 100644 index 00000000000..4e595e6f4a8 --- /dev/null +++ b/providers/commandcode/models/claude-haiku-4-5-20251001.toml @@ -0,0 +1,12 @@ +# https://commandcode.ai/models/claude-haiku-4-5-20251001 +# Toggle: thinking.type = enabled|disabled +base_model = "anthropic/claude-haiku-4-5-20251001" + +[[reasoning_options]] +type = "toggle" + +[cost] +cache_read = 0.1 +cache_write = 1.25 +input = 1 +output = 5 diff --git a/providers/commandcode/models/claude-opus-4-7.toml b/providers/commandcode/models/claude-opus-4-7.toml new file mode 100644 index 00000000000..7a19f7b915b --- /dev/null +++ b/providers/commandcode/models/claude-opus-4-7.toml @@ -0,0 +1,12 @@ +# https://commandcode.ai/models/claude-opus-4-7 +base_model = "anthropic/claude-opus-4-7" + +[[reasoning_options]] +type = "effort" +values = ["low", "medium", "high", "xhigh", "max"] + +[cost] +cache_read = 0.5 +cache_write = 6.25 +input = 5 +output = 25 diff --git a/providers/commandcode/models/claude-opus-4-8.toml b/providers/commandcode/models/claude-opus-4-8.toml new file mode 100644 index 00000000000..0da2d0590f6 --- /dev/null +++ b/providers/commandcode/models/claude-opus-4-8.toml @@ -0,0 +1,12 @@ +# https://commandcode.ai/models/claude-opus-4-8 +base_model = "anthropic/claude-opus-4-8" + +[[reasoning_options]] +type = "effort" +values = ["low", "medium", "high", "xhigh", "max"] + +[cost] +cache_read = 0.5 +cache_write = 6.25 +input = 5 +output = 25 diff --git a/providers/commandcode/models/claude-opus-5.toml b/providers/commandcode/models/claude-opus-5.toml new file mode 100644 index 00000000000..15ef299e158 --- /dev/null +++ b/providers/commandcode/models/claude-opus-5.toml @@ -0,0 +1,12 @@ +# https://commandcode.ai/models/claude-opus-5 +base_model = "anthropic/claude-opus-5" + +[[reasoning_options]] +type = "effort" +values = ["low", "medium", "high", "xhigh", "max"] + +[cost] +cache_read = 0.5 +cache_write = 6.25 +input = 5 +output = 25 diff --git a/providers/commandcode/models/claude-sonnet-4-6.toml b/providers/commandcode/models/claude-sonnet-4-6.toml new file mode 100644 index 00000000000..6d2edeb31ea --- /dev/null +++ b/providers/commandcode/models/claude-sonnet-4-6.toml @@ -0,0 +1,17 @@ +# https://commandcode.ai/models/claude-sonnet-4-6 +# Toggle: thinking.type = enabled|disabled +# Effort: reasoning_effort = low|medium|high|max +base_model = "anthropic/claude-sonnet-4-6" + +[[reasoning_options]] +type = "toggle" + +[[reasoning_options]] +type = "effort" +values = ["low", "medium", "high", "max"] + +[cost] +cache_read = 0.3 +cache_write = 3.75 +input = 3 +output = 15 diff --git a/providers/commandcode/models/claude-sonnet-5.toml b/providers/commandcode/models/claude-sonnet-5.toml new file mode 100644 index 00000000000..d3407390ad1 --- /dev/null +++ b/providers/commandcode/models/claude-sonnet-5.toml @@ -0,0 +1,17 @@ +# https://commandcode.ai/models/claude-sonnet-5 +# Toggle: thinking.type = enabled|disabled +# Effort: reasoning_effort = low|medium|high|xhigh|max +base_model = "anthropic/claude-sonnet-5" + +[[reasoning_options]] +type = "toggle" + +[[reasoning_options]] +type = "effort" +values = ["low", "medium", "high", "xhigh", "max"] + +[cost] +cache_read = 0.2 +cache_write = 2.5 +input = 2 +output = 10 diff --git a/providers/commandcode/models/deepseek/deepseek-v4-flash-fast.toml b/providers/commandcode/models/deepseek/deepseek-v4-flash-fast.toml new file mode 100644 index 00000000000..48f8e9b851d --- /dev/null +++ b/providers/commandcode/models/deepseek/deepseek-v4-flash-fast.toml @@ -0,0 +1,22 @@ +# https://commandcode.ai/models/deepseek-v4-flash-fast +# Low-latency deployment tier of DeepSeek V4 Flash, not a distinct model: +# https://commandcode.ai/models/deepseek-v4-flash-fast +# Toggle: thinking.type = enabled|disabled +# Effort: reasoning_effort = low|high|max +base_model = "deepseek/deepseek-v4-flash-0731" +name = "DeepSeek V4 Flash Fast" + +[[reasoning_options]] +type = "toggle" + +[[reasoning_options]] +type = "effort" +values = ["low", "high", "max"] + +[interleaved] +field = "reasoning_content" + +[cost] +cache_read = 0.07 +input = 0.28 +output = 0.56 diff --git a/providers/commandcode/models/deepseek/deepseek-v4-flash-vision-exp.toml b/providers/commandcode/models/deepseek/deepseek-v4-flash-vision-exp.toml new file mode 100644 index 00000000000..841caaa256b --- /dev/null +++ b/providers/commandcode/models/deepseek/deepseek-v4-flash-vision-exp.toml @@ -0,0 +1,21 @@ +# https://commandcode.ai/models/deepseek-v4-flash-vision-exp +# Time-of-day pricing since 2026-08-16, peak UTC 01:00-04:00 and 06:00-10:00: +# peak input 0.44 / output 1.32 / cache_read 0.014; [cost] below is the off-peak rate. +# Toggle: thinking.type = enabled|disabled +# Effort: reasoning_effort = low|high|max +base_model = "deepseek/deepseek-v4-flash-vision-exp" + +[[reasoning_options]] +type = "toggle" + +[[reasoning_options]] +type = "effort" +values = ["low", "high", "max"] + +[interleaved] +field = "reasoning_content" + +[cost] +cache_read = 0.007 +input = 0.22 +output = 0.66 diff --git a/providers/commandcode/models/deepseek/deepseek-v4-flash.toml b/providers/commandcode/models/deepseek/deepseek-v4-flash.toml new file mode 100644 index 00000000000..a2c389667ed --- /dev/null +++ b/providers/commandcode/models/deepseek/deepseek-v4-flash.toml @@ -0,0 +1,21 @@ +# https://commandcode.ai/models/deepseek-v4-flash +# Time-of-day pricing since 2026-08-16, peak UTC 01:00-04:00 and 06:00-10:00: +# peak input 0.44 / output 1.32 / cache_read 0.014; [cost] below is the off-peak rate. +# Toggle: thinking.type = enabled|disabled +# Effort: reasoning_effort = low|high|max +base_model = "deepseek/deepseek-v4-flash-0731" + +[[reasoning_options]] +type = "toggle" + +[[reasoning_options]] +type = "effort" +values = ["low", "high", "max"] + +[interleaved] +field = "reasoning_content" + +[cost] +cache_read = 0.007 +input = 0.22 +output = 0.66 diff --git a/providers/commandcode/models/deepseek/deepseek-v4-pro.toml b/providers/commandcode/models/deepseek/deepseek-v4-pro.toml new file mode 100644 index 00000000000..7dfe5a65224 --- /dev/null +++ b/providers/commandcode/models/deepseek/deepseek-v4-pro.toml @@ -0,0 +1,21 @@ +# https://commandcode.ai/models/deepseek-v4-pro +# Time-of-day pricing since 2026-08-16, peak UTC 01:00-04:00 and 06:00-10:00: +# peak input 1.32 / output 3.96 / cache_read 0.044; [cost] below is the off-peak rate. +# Toggle: thinking.type = enabled|disabled +# Effort: reasoning_effort = high|max +base_model = "deepseek/deepseek-v4-pro-0813" + +[[reasoning_options]] +type = "toggle" + +[[reasoning_options]] +type = "effort" +values = ["high", "max"] + +[interleaved] +field = "reasoning_content" + +[cost] +cache_read = 0.022 +input = 0.66 +output = 1.98 diff --git a/providers/commandcode/models/google/gemini-3.1-flash-lite.toml b/providers/commandcode/models/google/gemini-3.1-flash-lite.toml new file mode 100644 index 00000000000..a5618b8e1bb --- /dev/null +++ b/providers/commandcode/models/google/gemini-3.1-flash-lite.toml @@ -0,0 +1,11 @@ +# https://commandcode.ai/models/gemini-3-1-flash-lite +base_model = "google/gemini-3.1-flash-lite" + +[[reasoning_options]] +type = "effort" +values = ["minimal", "low", "medium", "high"] + +[cost] +cache_read = 0.03 +input = 0.25 +output = 1.5 diff --git a/providers/commandcode/models/google/gemini-3.5-flash-lite.toml b/providers/commandcode/models/google/gemini-3.5-flash-lite.toml new file mode 100644 index 00000000000..7f82bf1d7d5 --- /dev/null +++ b/providers/commandcode/models/google/gemini-3.5-flash-lite.toml @@ -0,0 +1,11 @@ +# https://commandcode.ai/models/gemini-3-5-flash-lite +base_model = "google/gemini-3.5-flash-lite" + +[[reasoning_options]] +type = "effort" +values = ["minimal", "low", "medium", "high"] + +[cost] +cache_read = 0.03 +input = 0.3 +output = 2.5 diff --git a/providers/commandcode/models/google/gemini-3.5-flash.toml b/providers/commandcode/models/google/gemini-3.5-flash.toml new file mode 100644 index 00000000000..d72d475c720 --- /dev/null +++ b/providers/commandcode/models/google/gemini-3.5-flash.toml @@ -0,0 +1,11 @@ +# https://commandcode.ai/models/gemini-3-5-flash +base_model = "google/gemini-3.5-flash" + +[[reasoning_options]] +type = "effort" +values = ["minimal", "low", "medium", "high"] + +[cost] +cache_read = 0.15 +input = 1.5 +output = 9 diff --git a/providers/commandcode/models/google/gemini-3.6-flash.toml b/providers/commandcode/models/google/gemini-3.6-flash.toml new file mode 100644 index 00000000000..6247447bc96 --- /dev/null +++ b/providers/commandcode/models/google/gemini-3.6-flash.toml @@ -0,0 +1,11 @@ +# https://commandcode.ai/models/gemini-3-6-flash +base_model = "google/gemini-3.6-flash" + +[[reasoning_options]] +type = "effort" +values = ["minimal", "low", "medium", "high"] + +[cost] +cache_read = 0.15 +input = 1.5 +output = 7.5 diff --git a/providers/commandcode/models/google/gemini-3.7-flash.toml b/providers/commandcode/models/google/gemini-3.7-flash.toml new file mode 100644 index 00000000000..56c527545ca --- /dev/null +++ b/providers/commandcode/models/google/gemini-3.7-flash.toml @@ -0,0 +1,14 @@ +# https://commandcode.ai/models/gemini-3-7-flash +# CommandCode bills cache writes only on this Gemini Flash model; the host's +# sibling Flash pages publish no cache-write rate, so the other entries omit it. +base_model = "google/gemini-3.7-flash" + +[[reasoning_options]] +type = "effort" +values = ["low", "medium", "high"] + +[cost] +cache_read = 0.15 +cache_write = 0.08334 +input = 1.5 +output = 7.5 diff --git a/providers/commandcode/models/google/gemini-3.8-flash.toml b/providers/commandcode/models/google/gemini-3.8-flash.toml new file mode 100644 index 00000000000..6c6908e38be --- /dev/null +++ b/providers/commandcode/models/google/gemini-3.8-flash.toml @@ -0,0 +1,11 @@ +# https://commandcode.ai/models/gemini-3-8-flash +base_model = "google/gemini-3.8-flash" + +[[reasoning_options]] +type = "effort" +values = ["low", "medium", "high"] + +[cost] +cache_read = 0.15 +input = 1.5 +output = 7.5 diff --git a/providers/commandcode/models/gpt-5.3-codex.toml b/providers/commandcode/models/gpt-5.3-codex.toml new file mode 100644 index 00000000000..da9f713b03e --- /dev/null +++ b/providers/commandcode/models/gpt-5.3-codex.toml @@ -0,0 +1,11 @@ +# https://commandcode.ai/models/gpt-5-3-codex +base_model = "openai/gpt-5.3-codex" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "xhigh"] + +[cost] +cache_read = 0.5 +input = 2 +output = 8 diff --git a/providers/commandcode/models/gpt-5.4-mini.toml b/providers/commandcode/models/gpt-5.4-mini.toml new file mode 100644 index 00000000000..e5ac9f888f1 --- /dev/null +++ b/providers/commandcode/models/gpt-5.4-mini.toml @@ -0,0 +1,11 @@ +# https://commandcode.ai/models/gpt-5-4-mini +base_model = "openai/gpt-5.4-mini" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "xhigh"] + +[cost] +cache_read = 0.075 +input = 0.75 +output = 4.5 diff --git a/providers/commandcode/models/gpt-5.4.toml b/providers/commandcode/models/gpt-5.4.toml new file mode 100644 index 00000000000..21889e2ae04 --- /dev/null +++ b/providers/commandcode/models/gpt-5.4.toml @@ -0,0 +1,17 @@ +# https://commandcode.ai/models/gpt-5-4 +# Gateway caps context at 400K vs lab 1_050_000. +# CommandCode flat-prices through the 400K cap; no 272K long-context tier applies on this host. +base_model = "openai/gpt-5.4" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "xhigh"] + +[cost] +cache_read = 0.25 +input = 2.5 +output = 15 + +[limit] +context = 400_000 +input = 400_000 diff --git a/providers/commandcode/models/gpt-5.5.toml b/providers/commandcode/models/gpt-5.5.toml new file mode 100644 index 00000000000..dc8f0d0a621 --- /dev/null +++ b/providers/commandcode/models/gpt-5.5.toml @@ -0,0 +1,17 @@ +# https://commandcode.ai/models/gpt-5-5 +# Gateway caps context at 400K vs lab 1_050_000. +# CommandCode flat-prices through the 400K cap; no 272K long-context tier applies on this host. +base_model = "openai/gpt-5.5" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "xhigh"] + +[cost] +cache_read = 0.5 +input = 5 +output = 30 + +[limit] +context = 400_000 +input = 400_000 diff --git a/providers/commandcode/models/gpt-5.6-luna.toml b/providers/commandcode/models/gpt-5.6-luna.toml new file mode 100644 index 00000000000..c01e1468ae1 --- /dev/null +++ b/providers/commandcode/models/gpt-5.6-luna.toml @@ -0,0 +1,20 @@ +# https://commandcode.ai/models/gpt-5-6-luna +# Price bands: standard ≤272K context, long >272K. +base_model = "openai/gpt-5.6-luna" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "xhigh", "max"] + +[cost] +cache_read = 0.02 +cache_write = 0.25 +input = 0.2 +output = 1.2 + +[[cost.tiers]] +cache_read = 0.04 +cache_write = 0.50 +input = 0.40 +output = 1.80 +tier = { size = 272_000 } diff --git a/providers/commandcode/models/gpt-5.6-sol.toml b/providers/commandcode/models/gpt-5.6-sol.toml new file mode 100644 index 00000000000..4bdf26e85e1 --- /dev/null +++ b/providers/commandcode/models/gpt-5.6-sol.toml @@ -0,0 +1,20 @@ +# https://commandcode.ai/models/gpt-5-6-sol +# Price bands: standard ≤272K context, long >272K. +base_model = "openai/gpt-5.6-sol" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "xhigh", "max"] + +[cost] +cache_read = 0.5 +cache_write = 6.25 +input = 5 +output = 30 + +[[cost.tiers]] +cache_read = 1.0 +cache_write = 12.50 +input = 10.00 +output = 45.00 +tier = { size = 272_000 } diff --git a/providers/commandcode/models/gpt-5.6-terra.toml b/providers/commandcode/models/gpt-5.6-terra.toml new file mode 100644 index 00000000000..4e9e600a787 --- /dev/null +++ b/providers/commandcode/models/gpt-5.6-terra.toml @@ -0,0 +1,20 @@ +# https://commandcode.ai/models/gpt-5-6-terra +# Price bands: standard ≤272K context, long >272K. +base_model = "openai/gpt-5.6-terra" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "medium", "high", "xhigh", "max"] + +[cost] +cache_read = 0.2 +cache_write = 2.50 +input = 2 +output = 12 + +[[cost.tiers]] +cache_read = 0.40 +cache_write = 5.00 +input = 4.00 +output = 18.00 +tier = { size = 272_000 } diff --git a/providers/commandcode/models/meituan/LongCat-2.0:free.toml b/providers/commandcode/models/meituan/LongCat-2.0:free.toml new file mode 100644 index 00000000000..dfeb817f05a --- /dev/null +++ b/providers/commandcode/models/meituan/LongCat-2.0:free.toml @@ -0,0 +1,15 @@ +# https://commandcode.ai/models/longcat-2-0-free +# Toggle: reasoning.enabled = true|false +# Id "meituan/LongCat-2.0:free" is verbatim from https://api.commandcode.ai/provider/v1/models. +# The colon is part of the upstream id and must stay in the filename; there's precedent for that. +base_model = "meituan/longcat-2.0" +name = "LongCat 2.0 Free" +reasoning_options = [{ type = "toggle" }] + +[cost] +cache_read = 0 +input = 0 +output = 0 + +[interleaved] +field = "reasoning_content" diff --git a/providers/commandcode/models/meta/muse-spark-1.1.toml b/providers/commandcode/models/meta/muse-spark-1.1.toml new file mode 100644 index 00000000000..45e9525e961 --- /dev/null +++ b/providers/commandcode/models/meta/muse-spark-1.1.toml @@ -0,0 +1,11 @@ +# https://commandcode.ai/models/muse-spark-1-1 +base_model = "meta/muse-spark-1.1" + +[[reasoning_options]] +type = "effort" +values = ["minimal", "low", "medium", "high", "xhigh"] + +[cost] +cache_read = 0.15 +input = 1.25 +output = 4.25 diff --git a/providers/commandcode/models/meta/muse-spark-1.2-contributor.toml b/providers/commandcode/models/meta/muse-spark-1.2-contributor.toml new file mode 100644 index 00000000000..40035877987 --- /dev/null +++ b/providers/commandcode/models/meta/muse-spark-1.2-contributor.toml @@ -0,0 +1,12 @@ +# https://commandcode.ai/models/muse-spark-1-2-contributor +base_model = "meta/muse-spark-1.2" +name = "Muse Spark 1.2 Contributor" + +[[reasoning_options]] +type = "effort" +values = ["minimal", "low", "medium", "high", "xhigh"] + +[cost] +cache_read = 0.002 +input = 0.1 +output = 0.2 diff --git a/providers/commandcode/models/meta/muse-spark-1.2.toml b/providers/commandcode/models/meta/muse-spark-1.2.toml new file mode 100644 index 00000000000..ddaa164e0f4 --- /dev/null +++ b/providers/commandcode/models/meta/muse-spark-1.2.toml @@ -0,0 +1,11 @@ +# https://commandcode.ai/models/muse-spark-1-2 +base_model = "meta/muse-spark-1.2" + +[[reasoning_options]] +type = "effort" +values = ["minimal", "low", "medium", "high", "xhigh"] + +[cost] +cache_read = 0.15 +input = 1.25 +output = 4.25 diff --git a/providers/commandcode/models/meta/muse-spark-1.3-contributor.toml b/providers/commandcode/models/meta/muse-spark-1.3-contributor.toml new file mode 100644 index 00000000000..302f9e2e812 --- /dev/null +++ b/providers/commandcode/models/meta/muse-spark-1.3-contributor.toml @@ -0,0 +1,15 @@ +# https://commandcode.ai/models/muse-spark-1-3-contributor +# Reasoning beyond "xhigh" is not available on Contributor-tier models. +# https://dev.meta.ai/docs/reasoning#how-it-works + +base_model = "meta/muse-spark-1.3" +name = "Muse Spark 1.3 Contributor" + +[[reasoning_options]] +type = "effort" +values = ["minimal", "low", "medium", "high", "xhigh"] + +[cost] +cache_read = 0.002 +input = 0.1 +output = 0.2 diff --git a/providers/commandcode/models/meta/muse-spark-1.3.toml b/providers/commandcode/models/meta/muse-spark-1.3.toml new file mode 100644 index 00000000000..eba0d6697f0 --- /dev/null +++ b/providers/commandcode/models/meta/muse-spark-1.3.toml @@ -0,0 +1,11 @@ +# https://commandcode.ai/models/muse-spark-1-3 +base_model = "meta/muse-spark-1.3" + +[[reasoning_options]] +type = "effort" +values = ["minimal", "low", "medium", "high", "xhigh", "max"] + +[cost] +cache_read = 0.15 +input = 1.25 +output = 4.25 diff --git a/providers/commandcode/models/moonshotai/Kimi-K2.5.toml b/providers/commandcode/models/moonshotai/Kimi-K2.5.toml new file mode 100644 index 00000000000..4f83d7588d1 --- /dev/null +++ b/providers/commandcode/models/moonshotai/Kimi-K2.5.toml @@ -0,0 +1,13 @@ +# https://commandcode.ai/models/kimi-k2-5 +# Toggle: thinking.type = enabled|disabled +base_model = "moonshotai/kimi-k2.5" + +[cost] +input = 0.6 +output = 3 + +[interleaved] +field = "reasoning_content" + +[[reasoning_options]] +type = "toggle" diff --git a/providers/commandcode/models/moonshotai/Kimi-K2.6.toml b/providers/commandcode/models/moonshotai/Kimi-K2.6.toml new file mode 100644 index 00000000000..55e494b6906 --- /dev/null +++ b/providers/commandcode/models/moonshotai/Kimi-K2.6.toml @@ -0,0 +1,14 @@ +# https://commandcode.ai/models/kimi-k2-6 +# Toggle: thinking.type = enabled|disabled +base_model = "moonshotai/kimi-k2.6" + +[cost] +cache_read = 0.16 +input = 0.95 +output = 4 + +[interleaved] +field = "reasoning_content" + +[[reasoning_options]] +type = "toggle" diff --git a/providers/commandcode/models/moonshotai/Kimi-K2.7-Code-Highspeed.toml b/providers/commandcode/models/moonshotai/Kimi-K2.7-Code-Highspeed.toml new file mode 100644 index 00000000000..d65dceb1347 --- /dev/null +++ b/providers/commandcode/models/moonshotai/Kimi-K2.7-Code-Highspeed.toml @@ -0,0 +1,11 @@ +# https://commandcode.ai/models/kimi-k2-7-code-highspeed +base_model = "moonshotai/kimi-k2.7-code-highspeed" +reasoning_options = [] + +[interleaved] +field = "reasoning_content" + +[cost] +cache_read = 0.38 +input = 1.9 +output = 8 diff --git a/providers/commandcode/models/moonshotai/Kimi-K2.7-Code.toml b/providers/commandcode/models/moonshotai/Kimi-K2.7-Code.toml new file mode 100644 index 00000000000..e794af81bdb --- /dev/null +++ b/providers/commandcode/models/moonshotai/Kimi-K2.7-Code.toml @@ -0,0 +1,11 @@ +# https://commandcode.ai/models/kimi-k2-7-code +base_model = "moonshotai/kimi-k2.7-code" +reasoning_options = [] + +[interleaved] +field = "reasoning_content" + +[cost] +cache_read = 0.19 +input = 0.95 +output = 4 diff --git a/providers/commandcode/models/moonshotai/Kimi-K3.toml b/providers/commandcode/models/moonshotai/Kimi-K3.toml new file mode 100644 index 00000000000..7d0bb1e6a77 --- /dev/null +++ b/providers/commandcode/models/moonshotai/Kimi-K3.toml @@ -0,0 +1,19 @@ +# https://commandcode.ai/models/kimi-k3 +# Toggle: thinking.type = enabled|disabled +# Effort: output_config.effort = low|high|max +base_model = "moonshotai/kimi-k3" + +[[reasoning_options]] +type = "toggle" + +[[reasoning_options]] +type = "effort" +values = ["low", "high", "max"] + +[interleaved] +field = "reasoning_content" + +[cost] +cache_read = 0.3 +input = 3 +output = 15 diff --git a/providers/commandcode/models/nvidia/nemotron-3-ultra-550b-a55b.toml b/providers/commandcode/models/nvidia/nemotron-3-ultra-550b-a55b.toml new file mode 100644 index 00000000000..69e72fdec7f --- /dev/null +++ b/providers/commandcode/models/nvidia/nemotron-3-ultra-550b-a55b.toml @@ -0,0 +1,11 @@ +# https://commandcode.ai/models/nemotron-3-ultra-550b-a55b +# Toggle: reasoning.enabled = true|false +base_model = "nvidia/nemotron-3-ultra-550b-a55b" + +[[reasoning_options]] +type = "toggle" + +[cost] +cache_read = 0.12 +input = 0.6 +output = 2.4 diff --git a/providers/commandcode/models/poolside/laguna-s-2.1-free.toml b/providers/commandcode/models/poolside/laguna-s-2.1-free.toml new file mode 100644 index 00000000000..fa474a036b8 --- /dev/null +++ b/providers/commandcode/models/poolside/laguna-s-2.1-free.toml @@ -0,0 +1,14 @@ +# https://commandcode.ai/models/laguna-s-2-1-free +# Toggle: chat_template_kwargs.enable_thinking = true|false +base_model = "poolside/laguna-s-2.1" +name = "Laguna S 2.1 Free" + +[[reasoning_options]] +type = "toggle" + +[interleaved] +field = "reasoning_content" + +[cost] +input = 0 +output = 0 diff --git a/providers/commandcode/models/sakana/fugu-ultra.toml b/providers/commandcode/models/sakana/fugu-ultra.toml new file mode 100644 index 00000000000..6751d500613 --- /dev/null +++ b/providers/commandcode/models/sakana/fugu-ultra.toml @@ -0,0 +1,14 @@ +# https://commandcode.ai/models/fugu-ultra +base_model = "sakana/fugu-ultra" + +[[reasoning_options]] +type = "effort" +values = ["high", "xhigh"] + +[cost] +cache_read = 0.5 +input = 5 +output = 30 + +[limit] +output = 128_000 diff --git a/providers/commandcode/models/stepfun/Step-3.5-Flash.toml b/providers/commandcode/models/stepfun/Step-3.5-Flash.toml new file mode 100644 index 00000000000..519915eb75c --- /dev/null +++ b/providers/commandcode/models/stepfun/Step-3.5-Flash.toml @@ -0,0 +1,15 @@ +# https://commandcode.ai/models/step-3-5-flash +# Effort: reasoning_effort (Chat) / output_config.effort (Messages) = low|high +base_model = "stepfun/step-3.5-flash" + +[[reasoning_options]] +type = "effort" +values = ["low", "high"] + +[interleaved] +field = "reasoning_content" + +[cost] +cache_read = 0.02 +input = 0.1 +output = 0.3 diff --git a/providers/commandcode/models/stepfun/Step-3.7-Flash.toml b/providers/commandcode/models/stepfun/Step-3.7-Flash.toml new file mode 100644 index 00000000000..ba6e28f1391 --- /dev/null +++ b/providers/commandcode/models/stepfun/Step-3.7-Flash.toml @@ -0,0 +1,15 @@ +# https://commandcode.ai/models/step-3-7-flash +# Effort: reasoning_effort (Chat) / output_config.effort (Messages) = low|medium|high +base_model = "stepfun/step-3.7-flash" + +[[reasoning_options]] +type = "effort" +values = ["low", "medium", "high"] + +[interleaved] +field = "reasoning_content" + +[cost] +cache_read = 0.04 +input = 0.2 +output = 1.15 diff --git a/providers/commandcode/models/tencent/Hy3.toml b/providers/commandcode/models/tencent/Hy3.toml new file mode 100644 index 00000000000..22285d983f9 --- /dev/null +++ b/providers/commandcode/models/tencent/Hy3.toml @@ -0,0 +1,12 @@ +# https://commandcode.ai/models/hy3 +# Effort: reasoning_effort = none|low|high (off is effort=none) +base_model = "tencent/hy3" +name = "Hy3 Free" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "high"] + +[cost] +input = 0 +output = 0 diff --git a/providers/commandcode/models/tencent/hy3-paid.toml b/providers/commandcode/models/tencent/hy3-paid.toml new file mode 100644 index 00000000000..a0c46a69339 --- /dev/null +++ b/providers/commandcode/models/tencent/hy3-paid.toml @@ -0,0 +1,12 @@ +# https://commandcode.ai/models/hy3-paid +# Effort: reasoning_effort = none|low|high (off is effort=none) +base_model = "tencent/hy3" + +[[reasoning_options]] +type = "effort" +values = ["none", "low", "high"] + +[cost] +cache_read = 0.035 +input = 0.14 +output = 0.58 diff --git a/providers/commandcode/models/tencent/hy4-preview.toml b/providers/commandcode/models/tencent/hy4-preview.toml new file mode 100644 index 00000000000..ac1dd7b2d02 --- /dev/null +++ b/providers/commandcode/models/tencent/hy4-preview.toml @@ -0,0 +1,12 @@ +# https://commandcode.ai/models/hy4-preview +# Effort: reasoning_effort = none|high (off is effort=none) +base_model = "tencent/hy4-preview" + +[[reasoning_options]] +type = "effort" +values = ["none", "high"] + +[cost] +cache_read = 0.042 +input = 0.834 +output = 2.501 diff --git a/providers/commandcode/models/thinkingmachines/inkling-small.toml b/providers/commandcode/models/thinkingmachines/inkling-small.toml new file mode 100644 index 00000000000..243938c4d5b --- /dev/null +++ b/providers/commandcode/models/thinkingmachines/inkling-small.toml @@ -0,0 +1,12 @@ +# https://commandcode.ai/models/inkling-small +# Effort: reasoning_effort = none|minimal|low|medium|high|max (off is effort=none) +base_model = "thinkingmachines/inkling-small" + +[[reasoning_options]] +type = "effort" +values = ["none", "minimal", "low", "medium", "high", "max"] + +[cost] +cache_read = 0.1 +input = 0.5 +output = 1.2 diff --git a/providers/commandcode/models/thinkingmachines/inkling.toml b/providers/commandcode/models/thinkingmachines/inkling.toml new file mode 100644 index 00000000000..e7684600cc3 --- /dev/null +++ b/providers/commandcode/models/thinkingmachines/inkling.toml @@ -0,0 +1,12 @@ +# https://commandcode.ai/models/inkling +# Effort: reasoning_effort = none|minimal|low|medium|high|xhigh|max (off is effort=none) +base_model = "thinkingmachines/inkling" + +[[reasoning_options]] +type = "effort" +values = ["none", "minimal", "low", "medium", "high", "xhigh", "max"] + +[cost] +cache_read = 0.17 +input = 1 +output = 4.05 diff --git a/providers/commandcode/models/xai/grok-4.5.toml b/providers/commandcode/models/xai/grok-4.5.toml new file mode 100644 index 00000000000..cb934f0a703 --- /dev/null +++ b/providers/commandcode/models/xai/grok-4.5.toml @@ -0,0 +1,11 @@ +# https://commandcode.ai/models/grok-4-5 +base_model = "xai/grok-4.5" + +[[reasoning_options]] +type = "effort" +values = ["low", "medium", "high"] + +[cost] +cache_read = 0.5 +input = 2 +output = 6 diff --git a/providers/commandcode/models/xai/grok-4.6.toml b/providers/commandcode/models/xai/grok-4.6.toml new file mode 100644 index 00000000000..b44a1db26f4 --- /dev/null +++ b/providers/commandcode/models/xai/grok-4.6.toml @@ -0,0 +1,11 @@ +# https://commandcode.ai/models/grok-4-6 +base_model = "xai/grok-4.6" + +[[reasoning_options]] +type = "effort" +values = ["low", "medium", "high", "xhigh"] + +[cost] +cache_read = 0.5 +input = 2 +output = 6 diff --git a/providers/commandcode/models/xiaomi/mimo-v2.5-pro.toml b/providers/commandcode/models/xiaomi/mimo-v2.5-pro.toml new file mode 100644 index 00000000000..73d9b18b401 --- /dev/null +++ b/providers/commandcode/models/xiaomi/mimo-v2.5-pro.toml @@ -0,0 +1,14 @@ +# https://commandcode.ai/models/mimo-v2-5-pro +# Toggle: thinking.type = enabled|disabled +base_model = "xiaomi/mimo-v2.5-pro" + +[[reasoning_options]] +type = "toggle" + +[interleaved] +field = "reasoning_content" + +[cost] +cache_read = 0.0036 +input = 0.435 +output = 0.87 diff --git a/providers/commandcode/models/xiaomi/mimo-v2.5.toml b/providers/commandcode/models/xiaomi/mimo-v2.5.toml new file mode 100644 index 00000000000..f3e94bd75ec --- /dev/null +++ b/providers/commandcode/models/xiaomi/mimo-v2.5.toml @@ -0,0 +1,14 @@ +# https://commandcode.ai/models/mimo-v2-5 +# Toggle: thinking.type = enabled|disabled +base_model = "xiaomi/mimo-v2.5" + +[[reasoning_options]] +type = "toggle" + +[interleaved] +field = "reasoning_content" + +[cost] +cache_read = 0.0028 +input = 0.14 +output = 0.28 diff --git a/providers/commandcode/models/z-ai/glm-5.3-flash.toml b/providers/commandcode/models/z-ai/glm-5.3-flash.toml new file mode 100644 index 00000000000..4cc70e6a64c --- /dev/null +++ b/providers/commandcode/models/z-ai/glm-5.3-flash.toml @@ -0,0 +1,14 @@ +# https://commandcode.ai/models/glm-5-3-flash +base_model = "zhipuai/glm-5.3-flash" + +[[reasoning_options]] +type = "effort" +values = ["low", "high", "max"] + +[interleaved] +field = "reasoning_content" + +[cost] +cache_read = 0.03 +input = 0.15 +output = 0.5 diff --git a/providers/commandcode/models/zai-org/GLM-5.1.toml b/providers/commandcode/models/zai-org/GLM-5.1.toml new file mode 100644 index 00000000000..bfc63bb4045 --- /dev/null +++ b/providers/commandcode/models/zai-org/GLM-5.1.toml @@ -0,0 +1,14 @@ +# https://commandcode.ai/models/glm-5-1 +# Toggle: thinking.type = enabled|disabled +base_model = "zhipuai/glm-5.1" + +[[reasoning_options]] +type = "toggle" + +[interleaved] +field = "reasoning_content" + +[cost] +cache_read = 0.26 +input = 1.4 +output = 4.4 diff --git a/providers/commandcode/models/zai-org/GLM-5.2-Fast.toml b/providers/commandcode/models/zai-org/GLM-5.2-Fast.toml new file mode 100644 index 00000000000..0013ae5257d --- /dev/null +++ b/providers/commandcode/models/zai-org/GLM-5.2-Fast.toml @@ -0,0 +1,19 @@ +# https://commandcode.ai/models/glm-5-2-fast +base_model = "zhipuai/glm-5.2" +description = "High-throughput GLM-5.2 with 1M context." +name = "GLM-5.2 Fast" + +[[reasoning_options]] +type = "effort" +values = ["high", "max"] + +[interleaved] +field = "reasoning_content" + +[limit] +output = 128_000 + +[cost] +cache_read = 0.5 +input = 3 +output = 10.25 diff --git a/providers/commandcode/models/zai-org/GLM-5.2.toml b/providers/commandcode/models/zai-org/GLM-5.2.toml new file mode 100644 index 00000000000..a61b7a7c0f3 --- /dev/null +++ b/providers/commandcode/models/zai-org/GLM-5.2.toml @@ -0,0 +1,14 @@ +# https://commandcode.ai/models/glm-5-2 +base_model = "zhipuai/glm-5.2" + +[[reasoning_options]] +type = "effort" +values = ["high", "max"] + +[interleaved] +field = "reasoning_content" + +[cost] +cache_read = 0.26 +input = 1.4 +output = 4.4 diff --git a/providers/commandcode/models/zai-org/GLM-5.3.toml b/providers/commandcode/models/zai-org/GLM-5.3.toml new file mode 100644 index 00000000000..96938771af1 --- /dev/null +++ b/providers/commandcode/models/zai-org/GLM-5.3.toml @@ -0,0 +1,14 @@ +# https://commandcode.ai/models/glm-5-3 +base_model = "zhipuai/glm-5.3" + +[[reasoning_options]] +type = "effort" +values = ["low", "high", "max"] + +[interleaved] +field = "reasoning_content" + +[cost] +cache_read = 0.26 +input = 1.4 +output = 4.4 diff --git a/providers/commandcode/models/zai-org/GLM-5.toml b/providers/commandcode/models/zai-org/GLM-5.toml new file mode 100644 index 00000000000..75351e545bb --- /dev/null +++ b/providers/commandcode/models/zai-org/GLM-5.toml @@ -0,0 +1,13 @@ +# https://commandcode.ai/models/glm-5 +# Toggle: thinking.type = enabled|disabled +base_model = "zhipuai/glm-5" + +[[reasoning_options]] +type = "toggle" + +[interleaved] +field = "reasoning_content" + +[cost] +input = 0.95 +output = 3.15 diff --git a/providers/commandcode/provider.toml b/providers/commandcode/provider.toml new file mode 100644 index 00000000000..98da32a1b83 --- /dev/null +++ b/providers/commandcode/provider.toml @@ -0,0 +1,5 @@ +name = "CommandCode" +env = ["COMMANDCODE_API_KEY"] +npm = "@ai-sdk/openai-compatible" +api = "https://api.commandcode.ai/provider/v1" +doc = "https://commandcode.ai/models"