Sparse MoE Qwen model with 3B active parameters for efficient chat and reasoning
8 providers
Model catalog
Models
Every model in the catalog with source-linked pricing, context limits, provider availability, and published benchmark results.
Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads
5 providers
Cohere's RAG workhorse for long-context enterprise search and tool use
9 providers
Efficient Mistral-NVIDIA open model for multilingual chat and local deployment
11 providers
| Model | Creator | Inputs | Context | Input | Output | Released | Compare |
|---|---|---|---|---|---|---|---|
| Qwen3 30B A3Balibaba/qwen3-30b-a3b | Alibaba Qwen |
131.072K | $0.08 | $0.29 | 2025-04-28 | ||
| Ministral 3Bmistral/ministral-3b | Mistral AI |
128K | $0.04 | $0.04 | 2024-10-16 | ||
| Command R+cohere/command-r-plus-08-2024 | Cohere |
128K | $2.5 | $10 | 2024-08-30 | ||
| Mistral Nemomistral/mistral-nemo | Mistral AI |
128K | $0.15 | $0.15 | 2024-07-01 |