diff --git a/providers/zro/logo.svg b/providers/zro/logo.svg new file mode 100644 index 00000000000..440252733ac --- /dev/null +++ b/providers/zro/logo.svg @@ -0,0 +1,17 @@ + + + + + + + + + + + + + + + + + diff --git a/providers/zro/models/deepseek-v4-flash-0731.toml b/providers/zro/models/deepseek-v4-flash-0731.toml new file mode 100644 index 00000000000..1e929fddb08 --- /dev/null +++ b/providers/zro/models/deepseek-v4-flash-0731.toml @@ -0,0 +1,16 @@ +# Wire: only OpenAI-style `reasoning_effort` is forwarded. +# Off is effort=none (no separate toggle field). Graded levels: low|high|max. +# Pricing: https://zro.moonmath.ai/pricing (USD / 1M tokens) +base_model = "deepseek/deepseek-v4-flash-0731" +reasoning_options = [{ type = "effort", values = ["none", "low", "high", "max"] }] + +[interleaved] +field = "reasoning_content" + +[cost] +input = 0.14 +output = 0.28 +cache_read = 0.0028 + +[limit] +context = 1_048_576 diff --git a/providers/zro/models/glm-5.2.toml b/providers/zro/models/glm-5.2.toml new file mode 100644 index 00000000000..4c7303a2538 --- /dev/null +++ b/providers/zro/models/glm-5.2.toml @@ -0,0 +1,15 @@ +# Pricing: https://zro.moonmath.ai/pricing (USD / 1M tokens) +base_model = "zhipuai/glm-5.2" +reasoning_options = [{ type = "effort", values = ["high", "max"] }] + +[interleaved] +field = "reasoning_content" + +[cost] +input = 1.10 +output = 4.00 +cache_read = 0.20 + +[limit] +context = 524_288 +output = 64_000 diff --git a/providers/zro/models/glm-5.3-flash.toml b/providers/zro/models/glm-5.3-flash.toml new file mode 100644 index 00000000000..0c9c3c5b757 --- /dev/null +++ b/providers/zro/models/glm-5.3-flash.toml @@ -0,0 +1,15 @@ +# Pricing: https://zro.moonmath.ai/pricing (USD / 1M tokens) +base_model = "zhipuai/glm-5.3-flash" +reasoning_options = [{ type = "effort", values = ["low", "high", "max"] }] + +[interleaved] +field = "reasoning_content" + +[cost] +input = 0.15 +output = 0.50 +cache_read = 0.03 + +[limit] +context = 1_048_576 +output = 64_000 diff --git a/providers/zro/models/glm-5.3.toml b/providers/zro/models/glm-5.3.toml new file mode 100644 index 00000000000..39a0322f16d --- /dev/null +++ b/providers/zro/models/glm-5.3.toml @@ -0,0 +1,14 @@ +# Pricing: https://zro.moonmath.ai/pricing (USD / 1M tokens) +base_model = "zhipuai/glm-5.3" +reasoning_options = [{ type = "effort", values = ["low", "high", "max"] }] + +[interleaved] +field = "reasoning_content" + +[cost] +input = 1.40 +output = 4.40 +cache_read = 0.26 + +[limit] +context = 1_048_576 diff --git a/providers/zro/models/kimi-k3.toml b/providers/zro/models/kimi-k3.toml new file mode 100644 index 00000000000..d2e53afcc65 --- /dev/null +++ b/providers/zro/models/kimi-k3.toml @@ -0,0 +1,21 @@ +# Wire: only OpenAI-style `reasoning_effort` is forwarded. +# No on/off toggle field is forwarded on this surface, so there is no toggle option to expose. +# Effort: reasoning_effort = low|high|max +# Pricing: https://zro.moonmath.ai/pricing (USD / 1M tokens) +base_model = "moonshotai/kimi-k3" +temperature = true +reasoning_options = [{ type = "effort", values = ["low", "high", "max"] }] + +[interleaved] +field = "reasoning_content" + +[cost] +input = 2.50 +output = 12.00 +cache_read = 0.45 + +[limit] +output = 1_048_576 + +[modalities] +input = ["text", "image"] diff --git a/providers/zro/provider.toml b/providers/zro/provider.toml new file mode 100644 index 00000000000..3b6d9ee77d0 --- /dev/null +++ b/providers/zro/provider.toml @@ -0,0 +1,5 @@ +name = "Zro" +env = ["ZRO_API_KEY"] +npm = "@ai-sdk/openai-compatible" +api = "https://zro.moonmath.ai/v1" +doc = "https://zro.moonmath.ai/"