List models - Case.dev

Visual Model Browser: Prefer a visual interface? Browse all models with filtering, search, and comparison.

Endpoint

GET /llm/v1/models

curl https://api.case.dev/llm/v1/models \
  -H "Authorization: Bearer sk_case_YOUR_API_KEY"

casedev llm:v1 list-models

import Casedev from 'casedev';

const client = new Casedev({ apiKey: 'sk_case_YOUR_API_KEY' });

const { data: models } = await client.llm.v1.listModels();

for (const model of models) {
  console.log(`${model.id}: $${model.pricing.input}/input, $${model.pricing.output}/output`);
}

import casedev

client = casedev.Casedev(api_key='sk_case_YOUR_API_KEY')

result = client.llm.v1.list_models()

for model in result.data:
    print(f'{model.id}: ${model.pricing.input}/input, ${model.pricing.output}/output')

result, _ := client.Llm.V1.ListModels(ctx)
for _, model := range result.Data {
	fmt.Printf("%s: $%s/input, $%s/output\n", model.ID, model.Pricing.Input, model.Pricing.Output)
}

Response

{
  "object": "list",
  "data": [
    {
      "id": "casemark/core-large",
      "name": "CaseMark Core Large",
      "description": "CaseMark's flagship legal reasoning model powered by Kimi K2.6",
      "owned_by": "casemark",
      "context_window": 200000,
      "max_tokens": 128000,
      "tags": ["reasoning", "legal", "tool-use"],
      "pricing": {
        "input": "0.0000015",
        "output": "0.0000035"
      }
    },
    {
      "id": "openai/gpt-6-sol",
      "name": "GPT-6 Sol",
      "description": "OpenAI's current frontier model with vision, reasoning, and tool use",
      "owned_by": "openai",
      "context_window": 1050000,
      "max_tokens": 128000,
      "tags": ["vision", "reasoning", "tool-use"],
      "pricing": {
        "input": "0.000002",
        "output": "0.00001"
      }
    }
  ]
}

Popular models

Model	Context	Best for	Input $/MTok
`casemark/core-large`	200K	Legal reasoning, workflows	$1.50
`openai/gpt-6.1-sol`	1M	Newest frontier model, agents	$2.00
`openai/gpt-6-sol`	1M	Complex analysis, vision, tool use	$2.00
`openai/gpt-6-astra`	1M	Hardest tasks	$10.00
`openai/gpt-6-luna`	1M	Fast, cheap	$0.10
`anthropic/claude-opus-5.5`	1M	Deepest reasoning, long agent runs	$4.00
`anthropic/claude-sonnet-5.5`	1M	Balanced analysis, drafting, tool use	$2.00
`anthropic/claude-haiku-5.5`	1M	Fast, cheap	$0.10
`google/gemini-3.8-flash`	1M	Long documents, multimodal	$0.75
`google/gemini-3.1-flash-lite`	1M	Very long documents at lowest cost	$0.25

Model capabilities

Tag	Meaning
`vision`	Can process images
`tool-use`	Supports function calling
`reasoning`	Enhanced reasoning
`fast`	Optimized for low latency
`legal`	Fine-tuned for legal tasks

Prices are per token. Multiply by 1,000,000 for price per million tokens (MTok).