Hybrid-reasoning DeepSeek model with thinking and non-thinking modes, sparse attention, and tool-use
24 providers
Model catalog
Models
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
6 providers
DeepSeek chat model for instruction following, coding, and analysis
8 providers
Thinking Kimi model for slower research passes, planning, and hard technical questions
22 providers
Efficient open MiniMax model built for coding agents and tool-heavy workflows
14 providers
Late GLM-4 workhorse for coding agents, reasoning, and structured tasks
18 providers
GLM vision model for visual reasoning, documents, and multimodal agents
7 providers
Open GPT reasoning model for self-hosted agents and controllable deployments
53 providers
Open GPT reasoning model for self-hosted agents and controllable deployments
32 providers
Hybrid-reasoning GLM release that made the 4.5 line broadly useful
14 providers
Lighter GLM-4.5 variant for fast coding assistance and cheaper agents
11 providers
Mistral coding agent model for repository tasks and software engineering workflows
3 providers
Open multimodal Llama for strong reasoning with efficient everyday serving
6 providers
Large open Qwen MoE for multilingual reasoning, coding, and tool use
5 providers
Smaller Qwen coder for efficient local agents and repo-level fixes
13 providers
Open Qwen coding heavyweight for repository reasoning and agentic engineering
8 providers
Dense open Qwen model for self-hosted chat, reasoning, and coding
15 providers
Cohere command model for multilingual enterprise agents, tools, and chat
6 providers
Largest open Gemma 3 instruction model for multilingual text generation and visual understanding
10 providers
Open multimodal Gemma instruction model for efficient text generation and image understanding
7 providers
Open multimodal Gemma instruction model for multilingual text generation and image understanding
8 providers
Classic open reasoning model for transparent math, coding, and deliberate problem solving
14 providers
Compact Microsoft instruction model tuned for efficient coding assistance, reasoning, and low-latency agent tasks
2 providers
Popular open Llama workhorse for multilingual chat, coding, and self-hosting
25 providers
Flagship Mistral model for advanced reasoning, coding, and multilingual work
2 providers
Mistral's largest general model for enterprise agents, coding, and multilingual reasoning
12 providers
Mistral code model for completions, refactors, and developer IDE workflows
5 providers
Granite 4.2 8B is a dense reasoning model from IBM. It is suited for mathematics, code generation, multilingual dialogue, and agentic workflows that need multi-step reasoning. It supports full, low-effort,...
Granite 4.1 8B is a dense, decoder-only 8-billion-parameter language model from IBM, part of the Granite 4.1 family. It supports a 131K-token context window and is designed for enterprise tasks...
| Model | Creator | Inputs | Context | Input | Output | Released | Compare |
|---|---|---|---|---|---|---|---|
| DeepSeek V3.2deepseek/deepseek-v3.2 | DeepSeek |
128K | $0.18 | $0.35 | 2025-12-01 | ||
| DeepSeek Reasonerdeepseek/deepseek-reasoner | DeepSeek |
1M | $0.147 | $0.295 | 2025-12-01 | ||
| DeepSeek Chatdeepseek/deepseek-chat | DeepSeek |
1M | $0.147 | $0.295 | 2025-12-01 | ||
| Kimi K2 Thinkingmoonshotai/kimi-k2-thinking | Moonshot AI |
262.144K | $0.4 | $2.5 | 2025-11-06 | ||
| MiniMax-M2minimax/MiniMax-M2 | MiniMax |
204.8K | $0.3 | $1.2 | 2025-10-27 | ||
| GLM-4.6zhipuai/glm-4.6 | Zhipu AI |
204.8K | $0.6 | $2.2 | 2025-09-30 | ||
| GLM-4.5Vzhipuai/glm-4.5v | Zhipu AI |
64K | $0.6 | $1.8 | 2025-08-11 | ||
| GPT OSS 120Bopenai/gpt-oss-120b | OpenAI |
131.072K | $0.03 | $0.17 | 2025-08-05 | ||
| GPT OSS 20Bopenai/gpt-oss-20b | OpenAI |
131.072K | $0.02 | $0.1 | 2025-08-05 | ||
| GLM-4.5zhipuai/glm-4.5 | Zhipu AI |
131.072K | $0.6 | $2.2 | 2025-07-28 | ||
| GLM-4.5-Airzhipuai/glm-4.5-air | Zhipu AI |
131.072K | $0.2 | $1.1 | 2025-07-28 | ||
| Devstral Smallmistral/devstral-small-2507 | Mistral AI |
128K | $0.1 | $0.3 | 2025-07-10 | ||
| Llama 4 Maverick 17B Instructmeta/llama-4-maverick-17b-instruct | Meta |
1M | $0.14 | $0.59 | 2025-04-05 | ||
| Qwen3 235B-A22Balibaba/qwen3-235b-a22b | Alibaba Qwen |
131.072K | $0.7 | $2.8 | 2025-04 | ||
| Qwen3-Coder 30B-A3B Instructalibaba/qwen3-coder-30b-a3b-instruct | Alibaba Qwen |
262.144K | $0.45 | $2.25 | 2025-04 | ||
| Qwen3-Coder 480B-A35B Instructalibaba/qwen3-coder-480b-a35b-instruct | Alibaba Qwen |
262.144K | $1.5 | $7.5 | 2025-04 | ||
| Qwen3 32Balibaba/qwen3-32b | Alibaba Qwen |
131.072K | $0.7 | $2.8 | 2025-04 | ||
| Command Acohere/command-a-03-2025 | Cohere |
256K | $2.5 | $10 | 2025-03-13 | ||
| Gemma 3 27B ITgoogle/gemma-3-27b-it | Google |
131.072K | $0.08 | $0.16 | 2025-03-12 | ||
| Gemma 3 4B ITgoogle/gemma-3-4b-it | Google |
131.072K | $0.04 | $0.08 | 2025-03-12 | ||
| Gemma 3 12B ITgoogle/gemma-3-12b-it | Google |
131.072K | $0.05 | $0.1 | 2025-03-12 | ||
| DeepSeek-R1deepseek/deepseek-r1 | DeepSeek |
128K | $0.7 | $2.5 | 2025-01-20 | ||
| Phi-4-minimicrosoft/phi-4-mini | Microsoft |
128K | $0.075 | $0.3 | 2024-12-11 | ||
| Llama-3.3-70B-Instructmeta/llama-3.3-70b-instruct | Meta |
128K | $0.1 | $0.32 | 2024-12-06 | ||
| Mistral Large 2.1mistral/mistral-large-2411 | Mistral AI |
131.072K | $2 | $6 | 2024-11-18 | ||
| Mistral Large 3mistral/mistral-large-2512 | Mistral AI |
262.144K | $0.5 | $1.5 | 2024-11-01 | ||
| Codestral (latest)mistral/codestral-latest | Mistral AI |
256K | $0.3 | $0.9 | 2024-05-29 | ||
| IBM: Granite 4.2 8Bibm-granite/granite-4.2-8b | IBM |
131.072K | $0.06 | $0.25 | — | ||
| IBM: Granite 4.1 8Bibm-granite/granite-4.1-8b | IBM |
131.072K | $0.05 | $0.1 | — |