Show me AI coding models

7 AI coding models from 5 labs. 4 have weights you can download. Input prices run from $0.20 to $1.40 per 1M tokens. The largest context window is 1M tokens (Gemini 3.8 Flash Cyber). Newest check: 24 Oct 2026.

94 of 197 models were checked against the vendor's own page in the last 30 days.

ModelLabContextIn / out per 1MReads and writesStatusChecked
Mellum2.1Mellum2.1 is JetBrains' open mixture-of-experts model, post-trained with reinforcement learning to work inside code repositories as an agent.JetBrains131K--text → textAvailable20 Oct
Gemini 3.8 Flash CyberGemini 3.8 Flash Cyber (Google DeepMind, Sept 2026) reports 86.2% on CyberGym and is limited to vetted Fairwind Program defenders; Gemini 4 Argon now sits above it.Google1M--text, code → text, codePreview2 Oct
GLM-5.3GLM-5.3 is Z.ai's text-only flagship for agentic coding and security work, with a 1M-token context, a live API and open weights.Z.ai1M$1.40 / $4.40text → textAvailable19 Oct
MAI-Code-1.1-FlashMicrosoft released MAI-Code-1.1-Flash in August 2026 as a small-tier coding model for GitHub Copilot, adding native vision input and a large context window.Microsoft256K$0.20 / $1.20text, image → text, codeAvailable14 Oct
Gemini 3.5 Flash CyberGemini 3.5 Flash Cyber (Google DeepMind, 2026) is a gated fine-tune of Gemini 3.5 Flash for finding and patching vulnerabilities inside CodeMender.Google1M--text, code → text, codePreview24 Oct
Kimi K2.7 Code HighSpeedOpen-weight 1T-parameter MoE coding model from Moonshot AI (June 2026) with a 256K context window and a HighSpeed mode hitting ~180-260 tokens/sec.Moonshot AI262K$0.95 / $4text, image, video, code → text, codeBeta31 Aug
Kimi K2.7-CodeOpen-weight 1T/32B-active MoE coding model from Moonshot AI, released June 2026 under a Modified MIT license and built for long-horizon agentic coding.Moonshot AI262K$0.95 / $4text, image, video, code → text, codeAvailable29 Sep

A person checks every record against the vendor's own page. Rankings cannot be bought. How Hokai checks records. Not sure what you need? Describe the job to Smart Match and get three picks with reasons.