feat: add Cohere, Perplexity, and Meta providers

models/alibaba/qwen-flash.yaml

@@ -0,0 +1,44 @@
+# yaml-language-server: $schema=https://modelparams.dev/api/v1/schema.json
+provider: alibaba
+authType: api_key
+model: qwen-flash
+params:
+  - path: max_tokens
+    type: integer
+    label: Max tokens
+    description: Maximum number of output tokens the model may generate.
+    range:
+      min: 1
+    group: generation_length
+  - path: temperature
+    type: number
+    label: Temperature
+    description: Controls randomness. Lower values make outputs more focused; higher values make them more varied.
+    range:
+      min: 0
+      max: 2
+      step: 0.1
+    group: sampling
+  - path: top_p
+    type: number
+    label: Top P
+    description: Controls nucleus sampling by limiting generation to tokens within the selected cumulative probability.
+    range:
+      min: 0
+      max: 1
+      step: 0.01
+    group: sampling
+  - path: extra_body.top_k
+    type: integer
+    label: Top K
+    description: Limits generation to the selected number of highest-probability tokens.
+    default: 20
+    range:
+      min: 1
+    group: sampling
+  - path: extra_body.chat_template_kwargs.enable_thinking
+    type: boolean
+    label: Enable thinking
+    description: Controls Qwen3 thinking mode when using OpenAI-compatible clients that pass provider-specific extra body fields.
+    default: true
+    group: reasoning

models/alibaba/qwen-plus.yaml

@@ -0,0 +1,44 @@
+# yaml-language-server: $schema=https://modelparams.dev/api/v1/schema.json
+provider: alibaba
+authType: api_key
+model: qwen-plus
+params:
+  - path: max_tokens
+    type: integer
+    label: Max tokens
+    description: Maximum number of output tokens the model may generate.
+    range:
+      min: 1
+    group: generation_length
+  - path: temperature
+    type: number
+    label: Temperature
+    description: Controls randomness. Lower values make outputs more focused; higher values make them more varied.
+    range:
+      min: 0
+      max: 2
+      step: 0.1
+    group: sampling
+  - path: top_p
+    type: number
+    label: Top P
+    description: Controls nucleus sampling by limiting generation to tokens within the selected cumulative probability.
+    range:
+      min: 0
+      max: 1
+      step: 0.01
+    group: sampling
+  - path: extra_body.top_k
+    type: integer
+    label: Top K
+    description: Limits generation to the selected number of highest-probability tokens.
+    default: 20
+    range:
+      min: 1
+    group: sampling
+  - path: extra_body.chat_template_kwargs.enable_thinking
+    type: boolean
+    label: Enable thinking
+    description: Controls Qwen3 thinking mode when using OpenAI-compatible clients that pass provider-specific extra body fields.
+    default: true
+    group: reasoning

models/alibaba/qwen3-coder-flash.yaml

@@ -0,0 +1,38 @@
+# yaml-language-server: $schema=https://modelparams.dev/api/v1/schema.json
+provider: alibaba
+authType: api_key
+model: qwen3-coder-flash
+params:
+  - path: max_tokens
+    type: integer
+    label: Max tokens
+    description: Maximum number of output tokens the model may generate.
+    range:
+      min: 1
+    group: generation_length
+  - path: temperature
+    type: number
+    label: Temperature
+    description: Controls randomness. Lower values make outputs more focused; higher values make them more varied.
+    range:
+      min: 0
+      max: 2
+      step: 0.1
+    group: sampling
+  - path: top_p
+    type: number
+    label: Top P
+    description: Controls nucleus sampling by limiting generation to tokens within the selected cumulative probability.
+    range:
+      min: 0
+      max: 1
+      step: 0.01
+    group: sampling
+  - path: extra_body.top_k
+    type: integer
+    label: Top K
+    description: Limits generation to the selected number of highest-probability tokens.
+    default: 20
+    range:
+      min: 1
+    group: sampling

models/alibaba/qwen3-coder-plus.yaml

@@ -0,0 +1,38 @@
+# yaml-language-server: $schema=https://modelparams.dev/api/v1/schema.json
+provider: alibaba
+authType: api_key
+model: qwen3-coder-plus
+params:
+  - path: max_tokens
+    type: integer
+    label: Max tokens
+    description: Maximum number of output tokens the model may generate.
+    range:
+      min: 1
+    group: generation_length
+  - path: temperature
+    type: number
+    label: Temperature
+    description: Controls randomness. Lower values make outputs more focused; higher values make them more varied.
+    range:
+      min: 0
+      max: 2
+      step: 0.1
+    group: sampling
+  - path: top_p
+    type: number
+    label: Top P
+    description: Controls nucleus sampling by limiting generation to tokens within the selected cumulative probability.
+    range:
+      min: 0
+      max: 1
+      step: 0.01
+    group: sampling
+  - path: extra_body.top_k
+    type: integer
+    label: Top K
+    description: Limits generation to the selected number of highest-probability tokens.
+    default: 20
+    range:
+      min: 1
+    group: sampling

models/alibaba/qwen3-max.yaml

@@ -0,0 +1,44 @@
+# yaml-language-server: $schema=https://modelparams.dev/api/v1/schema.json
+provider: alibaba
+authType: api_key
+model: qwen3-max
+params:
+  - path: max_tokens
+    type: integer
+    label: Max tokens
+    description: Maximum number of output tokens the model may generate.
+    range:
+      min: 1
+    group: generation_length
+  - path: temperature
+    type: number
+    label: Temperature
+    description: Controls randomness. Lower values make outputs more focused; higher values make them more varied.
+    range:
+      min: 0
+      max: 2
+      step: 0.1
+    group: sampling
+  - path: top_p
+    type: number
+    label: Top P
+    description: Controls nucleus sampling by limiting generation to tokens within the selected cumulative probability.
+    range:
+      min: 0
+      max: 1
+      step: 0.01
+    group: sampling
+  - path: extra_body.top_k
+    type: integer
+    label: Top K
+    description: Limits generation to the selected number of highest-probability tokens.
+    default: 20
+    range:
+      min: 1
+    group: sampling
+  - path: extra_body.chat_template_kwargs.enable_thinking
+    type: boolean
+    label: Enable thinking
+    description: Controls Qwen3 thinking mode when using OpenAI-compatible clients that pass provider-specific extra body fields.
+    default: false
+    group: reasoning

models/alibaba/qwen3.5-flash.yaml

@@ -0,0 +1,44 @@
+# yaml-language-server: $schema=https://modelparams.dev/api/v1/schema.json
+provider: alibaba
+authType: api_key
+model: qwen3.5-flash
+params:
+  - path: max_tokens
+    type: integer
+    label: Max tokens
+    description: Maximum number of output tokens the model may generate.
+    range:
+      min: 1
+    group: generation_length
+  - path: temperature
+    type: number
+    label: Temperature
+    description: Controls randomness. Lower values make outputs more focused; higher values make them more varied.
+    range:
+      min: 0
+      max: 2
+      step: 0.1
+    group: sampling
+  - path: top_p
+    type: number
+    label: Top P
+    description: Controls nucleus sampling by limiting generation to tokens within the selected cumulative probability.
+    range:
+      min: 0
+      max: 1
+      step: 0.01
+    group: sampling
+  - path: extra_body.top_k
+    type: integer
+    label: Top K
+    description: Limits generation to the selected number of highest-probability tokens.
+    default: 20
+    range:
+      min: 1
+    group: sampling
+  - path: extra_body.chat_template_kwargs.enable_thinking
+    type: boolean
+    label: Enable thinking
+    description: Controls Qwen3 thinking mode when using OpenAI-compatible clients that pass provider-specific extra body fields.
+    default: true
+    group: reasoning

models/alibaba/qwq-plus.yaml

@@ -0,0 +1,38 @@
+# yaml-language-server: $schema=https://modelparams.dev/api/v1/schema.json
+provider: alibaba
+authType: api_key
+model: qwq-plus
+params:
+  - path: max_tokens
+    type: integer
+    label: Max tokens
+    description: Maximum number of output tokens the model may generate.
+    range:
+      min: 1
+    group: generation_length
+  - path: temperature
+    type: number
+    label: Temperature
+    description: Controls randomness. Lower values make outputs more focused; higher values make them more varied.
+    range:
+      min: 0
+      max: 2
+      step: 0.1
+    group: sampling
+  - path: top_p
+    type: number
+    label: Top P
+    description: Controls nucleus sampling by limiting generation to tokens within the selected cumulative probability.
+    range:
+      min: 0
+      max: 1
+      step: 0.01
+    group: sampling
+  - path: extra_body.top_k
+    type: integer
+    label: Top K
+    description: Limits generation to the selected number of highest-probability tokens.
+    default: 20
+    range:
+      min: 1
+    group: sampling

models/cohere/command-a-03-2025.yaml

@@ -0,0 +1,102 @@
+# yaml-language-server: $schema=https://modelparams.dev/api/v1/schema.json
+provider: cohere
+authType: api_key
+model: command-a-03-2025
+params:
+  - path: max_tokens
+    type: integer
+    label: Max tokens
+    description: Maximum number of output tokens the model may generate.
+    range:
+      min: 1
+    group: generation_length
+  - path: stop_sequences
+    type: string
+    label: Stop sequences
+    description: Stops generation when one of these sequences is detected; up to five are allowed.
+    group: generation_length
+  - path: temperature
+    type: number
+    label: Temperature
+    description: Controls randomness. Lower values make outputs more focused; higher values make them more varied.
+    default: 0.3
+    range:
+      min: 0
+      step: 0.1
+    group: sampling
+  - path: p
+    type: number
+    label: Top P
+    description: Controls nucleus sampling by limiting generation to tokens within the selected cumulative probability.
+    default: 0.75
+    range:
+      min: 0.01
+      max: 0.99
+      step: 0.01
+    group: sampling
+  - path: k
+    type: integer
+    label: Top K
+    description: Limits sampling to the K most likely tokens; 0 disables top-k sampling.
+    default: 0
+    range:
+      min: 0
+      max: 500
+    group: sampling
+  - path: frequency_penalty
+    type: number
+    label: Frequency penalty
+    description: Penalizes tokens proportional to how often they have already appeared to reduce repetition.
+    default: 0
+    range:
+      min: 0
+      max: 1
+      step: 0.1
+    group: sampling
+  - path: presence_penalty
+    type: number
+    label: Presence penalty
+    description: Penalizes tokens that have already appeared to encourage a wider variety of content.
+    default: 0
+    range:
+      min: 0
+      max: 1
+      step: 0.1
+    group: sampling
+  - path: seed
+    type: integer
+    label: Seed
+    description: Seed used for best-effort deterministic sampling when reproducible outputs are desired.
+    group: sampling
+  - path: response_format.type
+    type: enum
+    label: Response format
+    description: Controls whether the model returns normal text or JSON object output.
+    default: text
+    values:
+      - text
+      - json_object
+    group: output_format
+  - path: logprobs
+    type: boolean
+    label: Log probabilities
+    description: Controls whether the response includes log probabilities for the generated tokens.
+    default: false
+    group: observability
+  - path: tool_choice
+    type: enum
+    label: Tool choice
+    description: Forces the model to either call a tool or skip tool calls for this request.
+    values:
+      - REQUIRED
+      - NONE
+    group: tooling
+  - path: safety_mode
+    type: enum
+    label: Safety mode
+    description: Controls Cohere's built-in safety instructions applied to the generation.
+    default: CONTEXTUAL
+    values:
+      - CONTEXTUAL
+      - STRICT
+    group: provider_metadata