DeepSeek V4.1 Flash model for reasoning and agentic coding
Models
Every model in the catalog with source-linked pricing, context limits, provider availability, and published benchmark results.
Flagship GLM model for long-horizon coding, agents, and complex project delivery
Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work
Open flagship GLM for long-horizon coding agents and million-token context work
Open MoE flagship with million-token context for coding and long agent runs
Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work
Strong GLM coding model for agentic engineering, terminals, and repository generation
Open MiniMax flagship for coding agents, office automation, and complex environments
Large open Qwen multimodal MoE for visual agents and long technical tasks
General GLM flagship for coding, analysis, and tool-heavy engineering workflows
Prior MiniMax coding model for agent workflows, office edits, and automation
Qwen instruction model for multilingual chat, reasoning, and tool use
Efficient Qwen thinking model for local reasoning, math, and coding agents
DeepSeek chat model for instruction following, coding, and analysis
Smaller Qwen coder for efficient local agents and repo-level fixes
Open Qwen coding heavyweight for repository reasoning and agentic engineering
May 2025 DeepSeek R1 update with improved mathematics, coding, and reasoning
Dense open Qwen model for self-hosted chat, reasoning, and coding
Large open Qwen MoE for multilingual reasoning, coding, and tool use
Open reasoning model from the Qwen team for math, coding, and step-by-step problem solving
Qwen vision-language model for visual reasoning, documents, and agent tasks
Small open Qwen2.5 instruction model for chat, structured output, and tool use
| Model | Creator | Inputs | Context | Input | Output | Released | Compare |
|---|---|---|---|---|---|---|---|
| DeepSeek V4.1 Flashdeepseek/deepseek-v4.1-flash | 1M | $0.02 | $1 | 2026-09-10 | |||
| GLM-5.3zhipuai/glm-5.3 | 1M | $1.195 | $4.183 | 2026-08-14 | |||
| Kimi K3moonshotai/kimi-k3 | 1.04858M | $3 | $15 | 2026-07-16 | |||
| GLM-5.2zhipuai/glm-5.2 | 1M | $1.195 | $4.183 | 2026-06-13 | |||
| DeepSeek V4 Prodeepseek/deepseek-v4-pro | 1M | $0.66 | $1.98 | 2026-04-24 | |||
| DeepSeek V4 Flashdeepseek/deepseek-v4-flash | 1M | $0.15 | $0.6 | 2026-04-24 | |||
| GLM-5.1zhipuai/glm-5.1 | 200K | $0.896 | $3.585 | 2026-04-07 | |||
| MiniMax-M2.7minimax/MiniMax-M2.7 | 204.8K | $0.3 | $1.2 | 2026-03-18 | |||
| Qwen3.5 397B-A17Balibaba/qwen3.5-397b-a17b | 262.144K | $0.6 | $3.6 | 2026-02-15 | |||
| GLM-5zhipuai/glm-5 | 204.8K | $0.598 | $2.689 | 2026-02-12 | |||
| MiniMax-M2.5minimax/MiniMax-M2.5 | 204.8K | $0.3 | $1.2 | 2026-02-12 | |||
| Qwen3-Next 80B-A3B Instructalibaba/qwen3-next-80b-a3b-instruct | 262.144K | $0.5 | $2 | 2025-09 | |||
| Qwen3-Next 80B-A3B (Thinking)alibaba/qwen3-next-80b-a3b-thinking | 262.144K | $0.5 | $6 | 2025-09 | |||
| DeepSeek V3.1deepseek/deepseek-chat-v3.1 | 163.84K | $0.19 | $0.79 | 2025-08-21 | |||
| Qwen3-Coder 30B-A3B Instructalibaba/qwen3-coder-30b-a3b-instruct | 262.144K | $0.45 | $2.25 | 2025-07-31 | |||
| Qwen3-Coder 480B-A35B Instructalibaba/qwen3-coder-480b-a35b-instruct | 262.144K | $1.5 | $7.5 | 2025-07-22 | |||
| DeepSeek R1 0528deepseek/deepseek-r1-0528 | 163.84K | $0.2 | $0.8 | 2025-05-28 | |||
| Qwen3 32Balibaba/qwen3-32b | 131.072K | $0.7 | $2.8 | 2025-04-28 | |||
| Qwen3 235B-A22Balibaba/qwen3-235b-a22b | 131.072K | $0.7 | $2.8 | 2025-04-28 | |||
| QwQ 32Balibaba/qwq-32b | 131.072K | $0.4 | $0.4 | 2025-03-05 | |||
| Qwen2.5-VL 72B Instructalibaba/qwen2-5-vl-72b-instruct | 131.072K | $0.8 | $1 | 2025-01-26 | |||
| Qwen2.5 7B Instructalibaba/qwen2.5-7b-instruct | 131.072K | $0.1 | $0.2 | 2024-09-19 |