Integrations
Use Cline with any model
Cline has an OpenAI Compatible provider with its own Base URL field. Connect to Hopscotch to use any model in the catalog.
Set it up
- 01
The configuration surface
In Cline's settings, choose the provider named OpenAI Compatible. It then shows a Base URL field, an API Key field and a Model ID field.
Cline does not append /v1. Its model-refresh handler appends only /models to whatever you type, so the value you paste has to carry the version segment itself:
Base URLhttps://api.hopscotchlabs.ai/v1Paste the key into API Key. Cline reads no environment variable for this provider: configuration is through the extension, and the settings it writes live under your home directory rather than in the repository.
- 02
The model id
Model ID is the field, and it takes an arbitrary string, so a pinned id goes in as it is:
Model IDopenai/gpt-4o-miniThe field is a dropdown when Cline has fetched a model list and a plain text box when it has not, and it always offers a Use custom model ID option, so you are never blocked by the list.
- 03
The model metadata Cline asks you for
The OpenAI Compatible provider has a Model Configuration section, and the fields in it are ones Cline cannot discover for a model it does not recognise: Supports Images, Context Window Size, Max Output Tokens, Input Price and Output Price per million tokens, and Temperature.
Take the context window and maximum output for a model from GET /v1/models, which publishes both per model, rather than guessing.
Models that fit an agent
These models support tool calling and take at least 128K tokens of context. Prices are per million tokens.
| Model | Context | Max output | Input /1M | Output /1M | Cached input /1M | Providers | Released |
|---|---|---|---|---|---|---|---|
| Gemma 4 E4B ITGoogledeepinfra/gemma-4-E4B-it | 131K | 8K | $0.02 | $0.10 | n/a | Deepinfra | 2 Apr 2026 |
| GPT OSS 20BOpenAIdeepinfra/gpt-oss-20b | 131K | 16K | $0.03 | $0.14 | n/a | Deepinfra | 5 Aug 2025 |
| GPT OSS 120BOpenAIdeepinfra/gpt-oss-120b | 131K | 16K | $0.04 | $0.17 | n/a | Deepinfra | 5 Aug 2025 |
| Command R7BCoherecohere/command-r7b-12-2024 | 128K | 4K | $0.04 | $0.15 | $0.04 | Cohere | 2 Dec 2024 |
| Nemotron 3 Nano 30B A3BNVIDIAdeepinfra/Nemotron-3-Nano-30B-A3B | 262K | 262K | $0.05 | $0.20 | n/a | Deepinfra | 15 Dec 2025 |
| DeepSeek V4 Flash 0731DeepSeekdeepinfra/DeepSeek-V4-Flash-0731 | 1M | 384K | $0.06 | $0.18 | n/a | Deepinfra | 31 Jul 2026 |
What changes when Cline runs through Hopscotch
- One key for every model
- Switch models in Cline by changing the model name.
- A budget for this tool
- Give Cline its own key with a daily limit. A long session stops at the limit.
- Every call in Activity
- Each request Cline sends shows up with its model, provider, tokens and cost.
- List price
- You pay each provider's list price per token, with no markup.
Cline questions
Do I need an account with each provider?
No. One Hopscotch key covers every model in the catalog, and you buy credit once.
Which model name goes in Cline?
The ID from the models page, such as deepinfra/gemma-4-E4B-it. The provider comes first, then the model.
Will Cline get a different model than the one I picked?
No. Hopscotch runs the model you name. To add a backup, set up a routing profile.
Can I use my own provider key with Cline?
Yes. Add the key in your dashboard. Requests to that provider run on it.