DeepSeek reasoning model for multi-step analysis, math, coding, and tools
6 providers
Every model in the catalog with source-linked pricing, context limits, provider availability, and published benchmark results.
DeepSeek reasoning model for multi-step analysis, math, coding, and tools
DeepSeek chat model for instruction following, coding, and analysis
Large open Qwen MoE for multilingual reasoning, coding, and tool use
Classic open reasoning model for transparent math, coding, and deliberate problem solving
Dense open Qwen model for self-hosted chat, reasoning, and coding
Open multimodal Llama for strong reasoning with efficient everyday serving
Cohere command model for multilingual enterprise agents, tools, and chat
Mistral code model for completions, refactors, and developer IDE workflows
| Model | Creator | Score | Inputs | Context | Input | Output | Released | Compare |
|---|---|---|---|---|---|---|---|---|
| DeepSeek Reasonerdeepseek/deepseek-reasoner | 74.2 | 1M | $0.147 | $0.295 | 2025-12-01 | |||
| DeepSeek Chatdeepseek/deepseek-chat | 70.2 | 1M | $0.147 | $0.295 | 2025-12-01 | |||
| Qwen3 235B-A22Balibaba/qwen3-235b-a22b | 59.6 | 131.072K | $0.7 | $2.8 | 2025-04 | |||
| DeepSeek-R1deepseek/deepseek-r1 | 56.9 | 128K | $0.7 | $2.5 | 2025-01-20 | |||
| Qwen3 32Balibaba/qwen3-32b | 40.0 | 131.072K | $0.7 | $2.8 | 2025-04 | |||
| Llama 4 Maverick 17B Instructmeta/llama-4-maverick-17b-instruct | 15.6 | 1M | $0.14 | $0.59 | 2025-04-05 | |||
| Command Acohere/command-a-03-2025 | 12.0 | 256K | $2.5 | $10 | 2025-03-13 | |||
| Codestral (latest)mistral/codestral-latest | 11.1 | 256K | $0.3 | $0.9 | 2024-05-29 |