OpenChat 3 Models by Alignment Lab AI
About
The OpenChat 3 family consists of open-source large language models (LLMs) that are fine-tuned using a novel approach called C-RLFT, inspired by offline reinforcement learning. These models are trained on a diverse dataset without needing explicit preference labels, enabling them to achieve comparable performance to models like ChatGPT, even with smaller sizes such as 7 billion parameters. The family includes versions like OpenChat 3.5 and 3.6, featuring improved coding capabilities and overall performance enhancements. These models are designed for tasks like chat, conversation, text generation, and coding, and are licensed under Apache 2.0. They are highly optimized for efficiency and speed, often utilizing quantization methods, and are compatible with a wide range of clients and libraries, making them accessible to many users 27.
Current Variants
Use-when guidance is derived from seed capabilities, context, release, and replacement fields.
Use when the workload needs 8k context, 8B parameters, and structured outputs.
Use when the workload needs 4k context and 13B parameters.
Use when the workload needs 4k context and 13B parameters.
Use when the workload needs 4k context and 13B parameters.
Use when the workload needs 8k context, 7B parameters, and structured outputs.
Use when the workload needs 8k context and 7B parameters.
Use when the workload needs 8k context and 7B parameters.
| Model | Use when | Released | Signals | Status |
|---|---|---|---|---|
| OpenChat 3.6 8B | Use when the workload needs 8k context, 8B parameters, and structured outputs. | 2024-05 | 8k context8B parametersstructured outputs | Current |
| OpenChat 3.1 | Use when the workload needs 4k context and 13B parameters. | 2024-01 | 4k context13B parameters | Current |
| OpenChat 3.2 | Use when the workload needs 4k context and 13B parameters. | 2024-01 | 4k context13B parameters | Current |
| OpenChat 3.2 Super | Use when the workload needs 4k context and 13B parameters. | 2024-01 | 4k context13B parameters | Current |
| OpenChat 3.5 (0106) | Use when the workload needs 8k context, 7B parameters, and structured outputs. | 2024-01 | 8k context7B parametersstructured outputs | Current |
| OpenChat 3.5 Gemma | Use when the workload needs 8k context and 7B parameters. | 2024-01 | 8k context7B parameters | Current |
| OpenChat 3.5 (1210) | Use when the workload needs 8k context and 7B parameters. | 2023-12 | 8k context7B parameters | Current |
Release Timeline
3 release groupsSpecifications(7 models)
| Model | Released | Context | Parameters | Structured Outputs |
|---|---|---|---|---|
| OpenChat 3.6 8B | 2024-05 | 8k | 8B | Yes |
| OpenChat 3.1 | 2024-01 | 4k | 13B | No |
| OpenChat 3.2 | 2024-01 | 4k | 13B | No |
| OpenChat 3.2 Super | 2024-01 | 4k | 13B | No |
| OpenChat 3.5 (0106) | 2024-01 | 8k | 7B | Yes |
| OpenChat 3.5 Gemma | 2024-01 | 8k | 7B | No |
| OpenChat 3.5 (1210) | 2023-12 | 8k | 7B | No |
Available From(4 providers)
Pricing
| Model | Provider | Input / 1M | Output / 1M | Type |
|---|---|---|---|---|
| OpenChat 3.6 8B | DeepInfra | $0.05 | $0.15 | Serverless |
| OpenChat 3.5 (0106) | Lepton AI API | $0.07 | $0.07 | Serverless |
| OpenChat 3.5 (0106) | Together AI | $0.2 | $0.2 | Serverless |
| OpenChat 3.5 (0106) | Fireworks AI | $0.2 | $0.2 | Provisioned |
Frequently Asked Questions
- What is OpenChat 3 used for?
- OpenChat 3 is used for structured outputs, coding, and math-heavy prompts. The family description and listed model capabilities point to those workloads as the best fit.
- How does OpenChat 3 compare to MOSS-Audio?
- OpenChat 3 by Alignment Lab AI is strongest where you need structured outputs, while MOSS-Audio by MOSI Intelligence is the closest related family to check for multimodal. OpenChat 3 has 7 listed variants and reaches up to 8k context, so compare the specs and pricing tables before choosing a production model.
- Which OpenChat 3 model should I use?
- For the lowest listed input price, start with OpenChat 3.6 8B through DeepInfra at $0.05/1M input tokens. For the most capable/latest local choice, evaluate OpenChat 3.6 8B with 8k context and structured outputs.
