AI Coding Models

Models specifically optimized for code generation, debugging, refactoring, and software development tasks.

29 models in this category.

Microsoft Phi-4

Microsoft

Microsoft's compact 14B model with strong reasoning and coding capability. Excellent value for small-scale deployments.

$0.100/M input $0.300/M output ~$0.10 per medium feature

Gemma 3 27B

Google

Google's open-weight 27B model. Budget-friendly with strong coding capability and Google's research backing.

$0.100/M input $0.400/M output ~$0.12 per medium feature

Mistral Nemo

Mistral

Compact 12B open-weight model co-developed with NVIDIA. Excellent coding performance at minimal cost.

$0.150/M input $0.150/M output ~$0.08 per medium feature

Qwen Coder Turbo

Qwen

Fast coding model from Qwen. Good price-performance for code generation.

$0.250/M input $1.25/M output ~$0.34 per medium feature

Llama 3.3 70B

Meta

Meta's open-weight 70B model. Strong coding and general capability, widely supported across AI platforms.

$0.250/M input $1.00/M output ~$0.29 per medium feature

DeepSeek Coder V2

DeepSeek

DeepSeek's coding-specialized model. Open-source and very affordable.

$0.270/M input $1.10/M output ~$0.31 per medium feature

DeepSeek Coder V3

DeepSeek

Latest generation DeepSeek coding model. Improved code understanding and generation over V2.

$0.270/M input $1.10/M output ~$0.31 per medium feature

Codestral

Mistral

Mistral's dedicated coding model. Open-weight and highly optimized for code generation and completion.

$0.300/M input $0.900/M output ~$0.29 per medium feature

Qwen Coder Turbo V2

Qwen

Updated Qwen Coder Turbo with improved code generation quality. Strong value for budget coding.

$0.300/M input $1.20/M output ~$0.34 per medium feature

Mistral Medium

Mistral

Mid-tier Mistral model between Small and Large. Strong coding capability at a moderate price point.

$0.400/M input $2.00/M output ~$0.54 per medium feature

GPT-4.1 mini

OpenAI

Cost-optimized GPT-4.1 variant. Strong coding capability at budget pricing, replacing GPT-4o mini for many use cases.

$0.400/M input $1.60/M output ~$0.46 per medium feature

Qwen 3 Coder

Qwen

Latest Qwen coding-specialized model. Strong performance on HumanEval and competitive programming benchmarks.

$0.500/M input $2.00/M output ~$0.57 per medium feature

Qwen Coder Plus

Qwen

Qwen model specifically optimized for coding tasks.

$0.800/M input $4.00/M output ~$1.08 per medium feature

OpenAI o3-mini

OpenAI

Affordable reasoning model for coding tasks. Best price-performance for algorithm-heavy work.

$1.10/M input $4.40/M output ~$1.27 per medium feature

Gemini 2.5 Pro

Google

Google's most capable model. Strong coding, multimodal understanding, and very competitive pricing.

$1.25/M input $10.00/M output ~$2.44 per medium feature

Grok Code

xAI

xAI's coding-specialized model. Optimized for code generation, debugging, and software engineering tasks.

$1.50/M input $7.50/M output ~$2.02 per medium feature

GPT-4.1

OpenAI

Updated GPT-4 generation with improved instruction following and reduced hallucination. Better coding accuracy than GPT-4o.

$2.00/M input $8.00/M output ~$2.30 per medium feature

Mistral Large 3

Mistral

Latest Mistral flagship model. Improved coding and multilingual capability over Large 2.

$2.00/M input $6.00/M output ~$1.90 per medium feature

GPT-4o

OpenAI

OpenAI's flagship multimodal model. Strong coding and reasoning at competitive pricing.

$2.50/M input $10.00/M output ~$3.06 per medium feature

Claude Sonnet 4

Anthropic

Anthropic's balanced model for coding and general tasks. Best price-performance ratio in the Claude family.

$3.00/M input $15.00/M output ~$4.66 per medium feature

Claude 3.5 Sonnet

Anthropic

Previous generation Sonnet. Still excellent for coding tasks at the same price point.

$3.00/M input $15.00/M output ~$4.66 per medium feature

Qwen 3.6 Plus

Qwen

Qwen's latest general-purpose model. Competitive with Claude Sonnet pricing.

$3.00/M input $15.00/M output ~$4.66 per medium feature

Grok 3

xAI

xAI's flagship model. Strong general-purpose capability with real-time knowledge access through X platform integration.

$3.00/M input $15.00/M output ~$4.05 per medium feature

Grok 4

xAI

Next-generation xAI model with enhanced reasoning and coding capability. Competes with Claude Opus and o3 Pro tier.

$5.00/M input $25.00/M output ~$6.75 per medium feature

Qwen 3 Max

Qwen

Flagship Qwen 3 model. Top-tier reasoning and coding, competitive with Claude Opus and GPT-4.1.

$5.00/M input $20.00/M output ~$5.75 per medium feature

OpenAI o3

OpenAI

Next generation reasoning model. Improved coding and math over o1.

$10.00/M input $40.00/M output ~$11.50 per medium feature

Claude Opus 4

Anthropic

Anthropic's most powerful model. Best for complex reasoning and challenging coding tasks.

$15.00/M input $75.00/M output ~$23.29 per medium feature

OpenAI o1

OpenAI

Reasoning model optimized for complex problem-solving. Excels at math, science, and advanced coding.

$15.00/M input $60.00/M output ~$17.25 per medium feature

OpenAI o3 Pro

OpenAI

Top-tier reasoning model combining o3's coding strength with extended compute. The most powerful OpenAI model for reasoning-heavy coding.

$20.00/M input $80.00/M output ~$23.00 per medium feature