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 LLM Gateway with one API key — that includes Cline, Aider, Roo Code, and devpass-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

36/258

Models

35/55

Providers

Vision Models (filtered)

Tool-enabled (filtered)

Free Models (filtered)


NovitaAI	kimi-k3	$3.00	$15.00	$0.30
Together AI	kimi-k3	$3.00	$15.00	$0.30
CanopyWave	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
Permafrost	kimi-k3	$3.00$2.10 -30% off	$15.00$10.50 -30% off	$0.60$0.42 -30% off
Nebius AI	kimi-k3	$3.00	$15.00	—
OpenAI	gpt-5.6-terra	$2.00	$12.00	$0.20
AWS Mantle(us-east-1)	gpt-5.6-terra	$2.20	$13.20	$0.22
Azure	gpt-5.6-terra	$2.00	$12.00	$0.20
AWS Mantle	gpt-5.6-terra	$2.20	$13.20	$0.22
AWS Mantle(us-east-2)	gpt-5.6-terra	$2.20	$13.20	$0.22
AWS Mantle(us-west-2)	gpt-5.6-terra	$2.20	$13.20	$0.22
AWS Mantle(us-east-1)	gpt-5.6-sol	$5.50	$33.00	$0.55
AWS Mantle	gpt-5.6-sol	$5.50	$33.00	$0.55
Azure	gpt-5.6-sol	$5.00	$30.00	$0.50
AWS Mantle(us-east-2)	gpt-5.6-sol	$5.50	$33.00	$0.55
OpenAI	gpt-5.6-sol	$5.00	$30.00	$0.50
AWS Bedrock(global)	claude-sonnet-5	$2.00	$10.00	$0.20
AWS Bedrock	claude-sonnet-5	$2.00	$10.00	$0.20
AWS Bedrock(us)	claude-sonnet-5	$2.20	$11.00	$0.22
Vertex AI (Anthropic)	claude-sonnet-5	$2.00	$10.00	$0.20
Anthropic	claude-sonnet-5	$2.00	$10.00	$0.20
Alibaba Cloud(singapore)	glm-5.2	$1.40	$4.40	$0.28
CanopyWave	glm-5.2	$1.40	$4.40	$0.26
NovitaAI	glm-5.2	$1.40	$4.40	$0.26
Alibaba Cloud(us-virginia)	glm-5.2	$1.40	$4.40	$0.28
EmberCloud	glm-5.2	$1.26	$3.96	$0.23
Z AI	glm-5.2	$1.40	$4.40	$0.26
Alibaba Cloud	glm-5.2	$1.40	$4.40	$0.28
Baidu	glm-5.2	$1.40	$4.40	$0.26
Alibaba Cloud(cn-beijing)	glm-5.2	$1.40	$4.40	$0.28
Runware	glm-5.2	$0.80$0.56 -30% off	$2.55$1.79 -30% off	$0.16$0.11 -30% off
Alibaba Cloud(eu-frankfurt)	glm-5.2	$1.40	$4.40	$0.28
ByteDance	glm-5.2	$1.40	$4.40	$0.26
SCX.ai	glm-5.2	$0.55	$1.78	$0.11
Nebius AI	glm-5.2	$1.40	$4.40	—
Moonshot AI	kimi-k2.7-code-highspeed	$1.90	$8.00	$0.38
Nebius AI	kimi-k2.7-code	$0.95	$4.00	—
NovitaAI	kimi-k2.7-code	$0.95	$4.00	$0.19
Moonshot AI	kimi-k2.7-code	$0.95	$4.00	$0.19
Anthropic	claude-fable-5	$10.00	$50.00	$1.00
AWS Bedrock(us)	claude-fable-5	$11.00	$55.00	$1.10
AWS Bedrock(global)	claude-fable-5	$10.00	$50.00	$1.00
AWS Bedrock	claude-fable-5	$10.00	$50.00	$1.00
Nebius AI	minimax-m3	$0.30	$1.20	—
Together AI	minimax-m3	$0.30	$1.20	$0.06
MiniMax	minimax-m3	$0.60	$2.40	$0.12
AWS Bedrock(au)	claude-opus-4-8	$5.50	$27.50	$0.55
Anthropic	claude-opus-4-8	$5.00	$25.00	$0.50

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?