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 PassingRight 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

40/283

Models

34/55

Providers

Vision Models (filtered)

Tool-enabled (filtered)

Free Models (filtered)


ByteDance	deepseek-v4-pro	$1.32	$3.96	$0.04
CanopyWave	deepseek-v4-pro	$1.74	$3.48	$0.01
DeepInfra	deepseek-v4-pro	$1.30	$2.60	$0.10
Runware	deepseek-v4-pro	$0.96	$1.92	$0.08
Together AI	deepseek-v4-pro	$1.32	$3.96	$0.13
Tencent Cloud	deepseek-v4-pro	$0.43	$0.87	$0.00
Fireworks AI	deepseek-v4-pro	$1.32	$3.96	$0.04
DeepSeek	deepseek-v4-pro	$0.43$0.37 -15% off	$0.87$0.74 -15% off	$0.00$0.00 -15% off
Alibaba Cloud	deepseek-v4-pro	$2.40	$4.80	$0.20
Azure	gpt-5.5	$5.00	$30.00	$0.50
OpenAI	gpt-5.5	$5.00$4.50 -10% off	$30.00$27.00 -10% off	$0.50$0.45 -10% off
Moonshot AI	kimi-k2.6	$0.95	$4.00	$0.16
Baidu	kimi-k2.6	$0.95	$4.00	$0.16
CanopyWave	kimi-k2.6	$0.95	$4.00	$0.16
Tencent Cloud	kimi-k2.6	$0.86	$3.57	$0.14
Runware	kimi-k2.6	$0.60	$3.05	$0.13
NovitaAI	kimi-k2.6	$0.80	$3.40	$0.16
Z AI	glm-5.1	$1.40	$4.40	$0.26
Tencent Cloud	glm-5.1	$1.40	$4.40	$0.26
EmberCloud	glm-5.1	$0.93	$2.93	$0.17
Baidu	glm-5.1	$1.40	$4.40	$0.26
DeepInfra	glm-5.1	$1.05	$3.50	$0.20
NovitaAI	glm-5.1	$1.38	$4.40	$0.26
MiniMax	minimax-m2.7	$0.30	$1.20	$0.06
Tencent Cloud	minimax-m2.7	$0.30	$1.20	$0.06
NovitaAI	minimax-m2.7	$0.30	$1.20	$0.06
SCX.ai (Turbo)	minimax-m2.7	$0.48	$1.79	$0.05
Gonka24	minimax-m2.7	$0.08	$0.32	$0.02
Azure	gpt-5.4	$2.50	$15.00	$0.25
OpenAI	gpt-5.4	$2.50$2.25 -10% off	$15.00$13.50 -10% off	$0.25$0.23 -10% off
Google AI Studio	gemini-pro-latest	$2.00	$12.00	$0.20
Azure	gpt-5.3-codex	$1.75	$14.00	$0.17
OpenAI	gpt-5.3-codex	$1.75$1.57 -10% off	$14.00$12.60 -10% off	$0.17$0.16 -10% off
Quartz	gemini-3.1-pro-preview	$2.00	$12.00	$0.20
Google Vertex AI	gemini-3.1-pro-preview	$2.00	$12.00	$0.20
Google AI Studio	gemini-3.1-pro-preview	$2.00	$12.00	$0.20
AWS Bedrock(eu-west-2)	claude-sonnet-4-6	$3.30	$16.50	$0.33
AWS Bedrock(jp)	claude-sonnet-4-6	$3.30	$16.50	$0.33
AWS Bedrock(au)	claude-sonnet-4-6	$3.30	$16.50	$0.33
AWS Bedrock(eu)	claude-sonnet-4-6	$3.30	$16.50	$0.33
AWS Bedrock(us)	claude-sonnet-4-6	$3.30	$16.50	$0.33
AWS Bedrock(global)	claude-sonnet-4-6	$3.00	$15.00	$0.30
AWS Bedrock	claude-sonnet-4-6	$3.00	$15.00	$0.30
Vertex AI (Anthropic)	claude-sonnet-4-6	$3.00	$15.00	$0.30
Anthropic	claude-sonnet-4-6	$3.00$2.85 -5% off	$15.00$14.25 -5% off	$0.30$0.28 -5% off
EmberCloud	qwen3-coder-next	$0.11	$0.68	$0.06
Azure	gpt-5.2-codex	$1.75	$14.00	$0.17
Vertex AI (OpenAI-compatible)	glm-4.7	$0.60	$2.20	—
EmberCloud	glm-4.7	$0.38	$1.98	$0.19
Cerebras	glm-4.7	$2.25	$2.75	—

Support

Welcome!

Best Models for Coding

Stay ahead of the curve

Resources

Compliance