Best LLMs for Coding
Language models suited to code generation, refactoring and agentic tool use: Claude Opus and Sonnet, GPT-6.1 and GPT-6 Sol, Kimi K3, GLM 5, Qwen3.8 Max, DeepSeek V4 Pro and MiniMax M3.
All Best LLMs for Coding
Preview the output style, compare capabilities, then open any model for full specs, pricing, and a live Playground.
Claude Opus 5.5
Claude Opus 5.5 is the most powerful model in the Claude 5 family from Anthropic. It excels at complex reasoning, analysis, and creative tasks with superior accuracy and nuance. It supports text, imag...
Claude Opus 5
Claude Opus 5 is the most powerful model in the Claude 5 family from Anthropic. It excels at complex reasoning, analysis, and creative tasks with superior accuracy and nuance. It supports text, image,...
Claude Opus 4.8
Claude Opus 4.8 is Anthropic's most capable generally available model in the Opus family. It supports text, image, and file inputs with text output, with reasoning support and a 1M-token context windo...
Claude Sonnet 5.5
Claude Sonnet 5.5 is Anthropic's Sonnet-class model for well-scoped everyday work, succeeding Claude Sonnet 5 as a direct upgrade. It is especially strong at building features and fixing bugs, with a ...
Claude Sonnet 5
Claude Sonnet 5 is a Sonnet-class model for high-quality coding, agentic workflows, reasoning, vision, structured outputs, and tool use.
GPT-6.1 Sol
GPT-6.1 Sol is OpenAI's upgrade to GPT-6 Sol, introduced at DevDay 2026 and positioned between GPT-6 Astra and GPT-6 Luna, with text and image input. OpenAI says it delivers near-Astra performance for...
GPT-6 Sol
GPT-6 Sol is the middle tier of OpenAI's GPT-6 reasoning family, released in September 2026 alongside GPT-6 Luna and built, according to OpenAI, for complex coding and agentic workflows, with text and...
GPT-5.6 Sol
GPT-5.6 Sol is the flagship tier of OpenAI's GPT-5.6 reasoning family, accepting text and image input; OpenAI says it roughly corresponds to the unsuffixed tier of earlier GPT-5 families, and the plai...
Kimi K3.1 Pro
Kimi K3.1 Pro is Moonshot AI's flagship open-weight multimodal reasoning model, a post-trained successor to Kimi K3 with a 1M-token context window. It accepts text, image and video input and is built ...
Kimi K3
Kimi K3 is Moonshot AI's flagship model, a 2.8-trillion-parameter open-weight mixture-of-experts model with native visual understanding and a 1M-token context. It is built on Kimi Delta Attention, a h...
GLM 5.3
GLM-5.3 is Z.ai's flagship text model for complex software engineering and long-horizon agent work, built on the same base model as GLM-5.2 with all gains coming from expanded post-training. Z.ai high...
GLM 5.2
GLM-5.2 is Z.ai's open-weight flagship text model released in June 2026 for long-horizon tasks, and the first GLM model to deliver that capability on a usable 1M-token context. Z.ai positions it for p...
Qwen3.8 Max
Qwen3.8 Max is Alibaba's flagship Qwen3.8 model, a 2.4-trillion-parameter Mixture-of-Experts reasoning model with native vision understanding, released in August 2026. Alibaba positions it for long-ho...
DeepSeek V4 Pro
DeepSeek V4 Pro is the large tier of DeepSeek's V4 family, a 1.6T-parameter mixture-of-experts model with 49B active parameters, introduced as an open-weight preview in April 2026 with a 1M-token cont...
MiniMax M3
MiniMax-M3 is MiniMax's flagship multimodal foundation model, which MiniMax describes as open-weight. It is built on MiniMax Sparse Attention, which selects key-value blocks to cut long-context comput...
Model lineup
Context window and positioning from each provider.
| Model | Context | Positioning |
|---|---|---|
| Claude Opus 4.8 | 1000K | Claude Opus 4.8 is Anthropic's most capable generally available model in the Opus family |
| GPT-5.6 Sol | 1050K | GPT-5.6 Sol is the flagship tier of OpenAI's GPT-5.6 reasoning family, accepting text and image input; OpenAI says it roughly corresponds to the… |
| DeepSeek V4 Pro | 1049K | DeepSeek V4 Pro is the large tier of DeepSeek's V4 family, a 1.6T-parameter mixture-of-experts model with 49B active parameters, introduced as an… |
| Kimi K3 | 1049K | Kimi K3 is Moonshot AI's flagship model, a 2.8-trillion-parameter open-weight mixture-of-experts model with native visual understanding and a… |
| Claude Opus 5 | 1000K | Claude Opus 5 is the most powerful model in the Claude 5 family from Anthropic |
| GPT-6.1 Sol | 1050K | GPT-6.1 Sol is OpenAI's upgrade to GPT-6 Sol, introduced at DevDay 2026 and positioned between GPT-6 Astra and GPT-6 Luna, with text and image input |
| GLM 5.2 | 1049K | GLM-5.2 is Z.ai's open-weight flagship text model released in June 2026 for long-horizon tasks, and the first GLM model to deliver that capability… |
| GLM 5.3 | 1049K | GLM-5.3 is Z.ai's flagship text model for complex software engineering and long-horizon agent work, built on the same base model as GLM-5.2 with all… |
| MiniMax M3 | 1000K | MiniMax-M3 is MiniMax's flagship multimodal foundation model, which MiniMax describes as open-weight |
| Claude Sonnet 5 | 1000K | Claude Sonnet 5 is a Sonnet-class model for high-quality coding, agentic workflows, reasoning, vision, structured outputs, and tool use |
| Qwen3.8 Max | 1000K | Qwen3.8 Max is Alibaba's flagship Qwen3.8 model, a 2.4-trillion-parameter Mixture-of-Experts reasoning model with native vision understanding,… |
| Claude Opus 5.5 | 1000K | Claude Opus 5.5 is the most powerful model in the Claude 5 family from Anthropic |
Models for code and agents
These models are positioned by their providers for coding, tool use and long agentic workflows. All support function calling and structured output on SandBase.
Picking one
- Hardest tasks: Claude Opus 5.5, GPT-6.1 Sol.
- Everyday coding: Claude Sonnet 5.5 and 5, GPT-6 Sol.
- Strong value: Kimi K3.1 Pro and K3, GLM 5.3, DeepSeek V4 Pro, Qwen3.8 Max, MiniMax M3.
Use them in your tools
Connect Claude Code, Codex, Cursor and other clients with one SandBase key; see Use in AI tools. Claude also works on the native Messages API; see Claude API.
Start using Best LLMs for Coding on SandBase
Switch models by changing one field.
- 01
Create an API key
Sign in to the SandBase Console and create a key on the API Keys page. Keep it in an environment variable and never commit it to source control.
TERMINALexport SANDBASE_API_KEY="YOUR_SANDBASE_API_KEY" - 02
Send a chat request
Call the OpenAI-compatible Chat Completions API with model anthropic/claude-sonnet-5.5. Any OpenAI SDK works with base URL https://api.sandbase.ai/v1.
TERMINALcurl https://api.sandbase.ai/v1/chat/completions \ -H "Authorization: Bearer $SANDBASE_API_KEY" \ -H "Content-Type: application/json" \ -d '{"model": "anthropic/claude-sonnet-5.5", "messages": [{"role": "user", "content": "Explain vector databases in two sentences."}]}' - 03
Or use the Messages API
Claude models are also served on the native Anthropic Messages API.
TERMINALcurl https://api.sandbase.ai/v1/messages \ -H "Authorization: Bearer $SANDBASE_API_KEY" \ -H "Content-Type: application/json" \ -d '{"model": "anthropic/claude-sonnet-5.5", "max_tokens": 1024, "messages": [{"role": "user", "content": "Explain vector databases in two sentences."}]}' - 04
Connect your AI tools
Use the same key in Claude Code, Codex, Cursor and other clients. See Use in AI tools for setup.
Questions, answered
Can I use these models in Claude Code or Cursor?
Yes. See Use in AI tools for setup. Claude models work over the Messages API; others over OpenAI-compatible chat completions.
Do these models support tool calling?
Yes. All models on this page are tagged for function calling and structured output.
Which is the best value for coding?
Kimi, GLM, DeepSeek V4 and Qwen3.8 Max have lower token prices than Claude Opus or GPT-6.1 Sol. Compare current prices on the cards.
How big a codebase can they read?
Most models here have a context window of about 1M tokens. Check each model page.
Build with Best LLMs for Coding.
One key, consistent APIs, and usage-based pricing across every model on this page.