What is the best LLM for coding?

Claude Sonnet 5 and Claude Opus 4.8 lead most real-world coding evaluations, with OpenAI's GPT-5.3 Codex and Google's Gemini 3.1 Pro close behind. Among open-weight models, Qwen3 Coder, Kimi K2.7 Code, GLM-5.2, and DeepSeek V4 deliver strong results at a fraction of the price.

What is the cheapest model that is still good at coding?

Qwen3 Coder 30B (about $0.07 per million input tokens), GLM-4.7 Flash, and DeepSeek V4 Flash are the standouts for budget coding. They handle everyday completion, refactoring, and code review well and are cheap enough to run on every commit.

Can I use these models with coding agents like Cline or Aider?

Yes. Any agent that supports an OpenAI-compatible endpoint or custom base URL can route through OffRail with one API key — that includes Cline, Aider, and Roo Code — so you can mix models per task and see per-agent cost analytics.

Do coding models need tool calling?

For agentic workflows, yes. Editing files, running tests, and searching a repo all happen through function calls, so pick a model with reliable tool calling — the capability icons in the list above show which provider mappings support tools. For plain autocomplete or one-shot generation, tool calling is optional.

Best Models for Coding

Frontier and open-weight models for code generation, review, and agentic coding — compared by price and context window

Compare

37/351

Models

36/51

Providers

Vision Models (filtered)

Tool-enabled (filtered)

Free Models (filtered)


ByteDance	glm-5.2	$1.40	$4.40	$0.26
Runware	glm-5.2	$0.80	$2.55	$0.16
CanopyWave	glm-5.2	$1.40	$4.40	$0.26
SCX.ai(au)	glm-5.2	$0.55	$1.78	$0.11
Alibaba Cloud(us-virginia)	qwen3-coder-flash	$0.14	$0.57	$0.03
Alibaba Cloud(cn-beijing)	qwen3-coder-flash	$0.14	$0.57	$0.03
Alibaba Cloud	qwen3-coder-flash	$0.30	$1.50	$0.06
Alibaba Cloud(eu-frankfurt)	qwen3-coder-flash	$0.30	$1.50	$0.06
Alibaba Cloud	qwen3-coder-flash	$0.30	$1.50	$0.06
Alibaba Cloud(singapore)	qwen3-coder-flash	$0.30	$1.50	$0.06
EmberCloud	qwen3-coder-next	$0.11	$0.68	$0.06
EmberCloud	qwen3-coder-next	$0.11	$0.68	$0.06
NovitaAI	qwen3-coder-30b-a3b-instruct	$0.07	$0.27	—
Nebius AI	qwen3-coder-30b-a3b-instruct	$0.10	$0.30	—
NovitaAI	qwen3-coder-30b-a3b-instruct	$0.07	$0.27	—
NovitaAI	qwen3-coder-480b-a35b-instruct	$0.38	$1.55	—
Nebius AI	qwen3-coder-480b-a35b-instruct	$0.40	$1.80	—
Vertex AI (OpenAI-compatible)	qwen3-coder-480b-a35b-instruct	$0.22	$1.80	$0.02
Vertex AI (OpenAI-compatible)	qwen3-coder-480b-a35b-instruct	$0.22	$1.80	$0.02
NovitaAI	qwen3-coder-480b-a35b-instruct	$0.38	$1.55	—
Alibaba Cloud	qwen3-coder-plus	$6.00	$60.00	$1.20
Alibaba Cloud	qwen3-coder-plus	$6.00	$60.00	$1.20
Permafrost	kimi-k3	$3.00	$15.00	$0.60
Fireworks AI	kimi-k3	$3.00	$15.00	$0.30
Fireworks AI	kimi-k3	$3.00	$15.00	$0.30
Moonshot AI	kimi-k3	$3.00	$15.00	$0.30
Nebius AI	kimi-k3	$3.00	$15.00	—
Together AI	kimi-k3	$3.00	$15.00	$0.30
CanopyWave	kimi-k3	$3.00	$15.00	$0.30
Moonshot AI	kimi-k3	$3.00	$15.00	$0.30
Permafrost	kimi-k3	$3.00	$15.00	$0.60
Together AI	kimi-k3	$3.00	$15.00	$0.30
NovitaAI	kimi-k3	$3.00	$15.00	$0.30
NovitaAI	kimi-k3	$3.00	$15.00	$0.30
Nebius AI	kimi-k3	$3.00	$15.00	—
CanopyWave	kimi-k3	$3.00	$15.00	$0.30
Moonshot AI	kimi-k2.7-code-highspeed	$1.90	$8.00	$0.38
Moonshot AI	kimi-k2.7-code-highspeed	$1.90	$8.00	$0.38
NovitaAI	kimi-k2.7-code	$0.95	$4.00	$0.19
NovitaAI	kimi-k2.7-code	$0.95	$4.00	$0.19
Nebius AI	kimi-k2.7-code	$0.95	$4.00	—
Moonshot AI	kimi-k2.7-code	$0.95	$4.00	$0.19
Nebius AI	kimi-k2.7-code	$0.95	$4.00	—
Moonshot AI	kimi-k2.7-code	$0.95	$4.00	$0.19
NovitaAI	kimi-k2.6	$0.80	$3.40	$0.16
Baidu	kimi-k2.6	$0.95	$4.00	$0.16
Moonshot AI	kimi-k2.6	$0.95	$4.00	$0.16
Gonka24	kimi-k2.6	$0.22	$1.14	$0.05
CanopyWave	kimi-k2.6	$0.95	$4.00	$0.16
Tundra	kimi-k2.6	$0.40	$2.20	$0.08

Support

Welcome!

Best Models for Coding

Stay ahead of the curve

Frequently asked questions

What is the best LLM for coding?

What is the cheapest model that is still good at coding?

Can I use these models with coding agents like Cline or Aider?

Do coding models need tool calling?