Models are included when their public model metadata indicates coding, programming, developer, software, or code generation use cases.
Best LLM API Models for Coding
This guide highlights models whose public metadata indicates coding, programming, developer, or software-oriented use cases.
50Models listed
1M input + 500K outputCost example tokens
USD / 1MNormalized prices
Quick shortlist
Start with MiniMax M3.
This guide starts with coding-oriented models and practical popularity signals so developers can shortlist options faster.
The ranking is a discovery aid, not a final recommendation. Always compare the model against your workload and verify provider pricing before production use.
Model Ranking
Browse all models| Model | Provider | Prompt | Output | Sample cost | Your Cost | Context | Popularity | Release |
|---|---|---|---|---|---|---|---|---|
| New🔥MiniMax M3 | MiniMax | $0.3 | $1.2 | $0.9 | $0.9 | 1.05M | #4 | |
| 🔥DeepSeek V4 Pro | DeepSeek | $0.435 | $0.87 | $0.87 | $0.87 | 1.05M | #5 | |
| 🔥Claude Sonnet 4.6 | Anthropic | $3 | $15 | $10.5 | $10.5 | 1M | #6 | |
| 🔥Owl Alpha | OpenRouter | $0 | $0 | $0 | $0 | 1.05M | #7 | |
| 🔥Claude Opus 4.7 | Anthropic | $5 | $25 | $17.5 | $17.5 | 1M | #8 | |
| 🔥Gemini 3 Flash Preview | $0.5 | $3 | $2 | $2 | 1.05M | #10 | ||
| New🔥Step 3.7 Flash | StepFun | $0.2 | $1.15 | $0.77 | $0.77 | 256K | #11 | |
| 🔥Gemini 2.5 Flash | $0.3 | $2.5 | $1.55 | $1.55 | 1.05M | #13 | ||
| 🔥Laguna M.1 (free) | Poolside | $0 | $0 | $0 | $0 | 262.14K | #14 | |
| 🔥Gemini 3.5 Flash | $1.5 | $9 | $6 | $6 | 1.05M | #16 | ||
| 🔥MiMo-V2.5-Pro | Xiaomi | $0.435 | $0.87 | $0.87 | $0.87 | 1.05M | #17 | |
| 🔥Claude Opus 4.6 | Anthropic | $5 | $25 | $17.5 | $17.5 | 1M | #18 | |
| Kimi K2.6 | MoonshotAI | $0.66 | $3.41 | $2.37 | $2.37 | 262.14K | #21 | |
| GLM 5.1 | Z.ai | $0.98 | $3.08 | $2.52 | $2.52 | 202.75K | #24 | |
| GPT-5.4 Mini | OpenAI | $0.75 | $4.5 | $3 | $3 | 400K | #29 | |
| GPT-5.4 | OpenAI | $2.5 | $15 | $10 | $10 | 1.05M | #30 | |
| Gemini 3.1 Pro Preview | $2 | $12 | $8 | $8 | 1.05M | #31 | ||
| Qwen3.7 Max | Qwen | $1.25 | $3.75 | $3.12 | $3.12 | 1M | #35 | |
| GLM 5 | Z.ai | $0.6 | $1.92 | $1.56 | $1.56 | 202.75K | #37 | |
| Kimi K2.5 | MoonshotAI | $0.375 | $2.025 | $1.39 | $1.39 | 262.14K | #38 | |
| MiniMax M2.5 | MiniMax | $0.12 | $0.48 | $0.36 | $0.36 | 204.8K | #40 | |
| GPT-5 Nano | OpenAI | $0.05 | $0.4 | $0.25 | $0.25 | 400K | #41 | |
| Laguna XS.2 (free) | Poolside | $0 | $0 | $0 | $0 | 262.14K | #47 | |
| GPT-5.3-Codex | OpenAI | $1.75 | $14 | $8.75 | $8.75 | 400K | #48 | |
| Gemini 2.5 Pro | $1.25 | $10 | $6.25 | $6.25 | 1.05M | #57 | ||
| Qwen3 Coder 480B A35B | Qwen | $0.22 | $1.8 | $1.12 | $1.12 | 1.05M | #59 | |
| GLM 4.7 | Z.ai | $0.4 | $1.75 | $1.27 | $1.27 | 202.75K | #63 | |
| GPT-5 | OpenAI | $1.25 | $10 | $6.25 | $6.25 | 400K | #65 | |
| GPT-4.1 | OpenAI | $2 | $8 | $6 | $6 | 1.05M | #66 | |
| Claude Sonnet 4 | Anthropic | $3 | $15 | $10.5 | $10.5 | 1M | #71 | |
| Qwen3.5-9B | Qwen | $0.1 | $0.15 | $0.17 | $0.17 | 262.14K | #74 | |
| Nemotron 3 Nano 30B A3B (free) | NVIDIA | $0 | $0 | $0 | $0 | 256K | #75 | |
| GLM 4.7 Flash | Z.ai | $0.06 | $0.4 | $0.26 | $0.26 | 202.75K | #80 | |
| Kimi K2.6 (free) | MoonshotAI | $0 | $0 | $0 | $0 | 262.14K | #83 | |
| Qwen3 Coder Next | Qwen | $0.11 | $0.8 | $0.51 | $0.51 | 262.14K | #87 | |
| Nemotron 3 Nano 30B A3B | NVIDIA | $0.05 | $0.2 | $0.15 | $0.15 | 262.14K | #89 | |
| Qwen3 Next 80B A3B Instruct | Qwen | $0.09 | $1.1 | $0.64 | $0.64 | 262.14K | #95 | |
| Qwen2.5 7B Instruct | Qwen | $0.04 | $0.1 | $0.09 | $0.09 | 131.07K | #106 | |
| GPT-5.2-Codex | OpenAI | $1.75 | $14 | $8.75 | $8.75 | 400K | #108 | |
| GPT-5 Codex | OpenAI | $1.25 | $10 | $6.25 | $6.25 | 400K | #111 | |
| GPT-5.1-Codex | OpenAI | $1.25 | $10 | $6.25 | $6.25 | 400K | #113 | |
| Claude 3.5 Haiku | Anthropic | $0.8 | $4 | $2.8 | $2.8 | 200K | #118 | |
| o3 Mini | OpenAI | $1.1 | $4.4 | $3.3 | $3.3 | 200K | #122 | |
| Ring-2.6-1T | inclusionAI | $0.075 | $0.625 | $0.39 | $0.39 | 262.14K | #123 | |
| Qwen3 Coder 30B A3B Instruct | Qwen | $0.07 | $0.27 | $0.21 | $0.21 | 160K | #126 | |
| Mistral Medium 3.5 | Mistral | $1.5 | $7.5 | $5.25 | $5.25 | 262.14K | #131 | |
| Grok Build 0.1 | xAI | $1 | $2 | $2 | $2 | 256K | #137 | |
| GPT-5.1-Codex-Mini | OpenAI | $0.25 | $2 | $1.25 | $1.25 | 400K | #141 | |
| Qwen2.5 72B Instruct | Qwen | $0.36 | $0.4 | $0.56 | $0.56 | 131.07K | #142 | |
| Devstral 2 2512 | Mistral | $0.4 | $2 | $1.4 | $1.4 | 262.14K | #144 |
Pricing FAQ
How is the sample workload cost calculated?
The sample workload uses 1,000,000 input tokens plus 500,000 output tokens, then applies each model's normalized USD price per 1 million tokens.
Why do input and output token prices matter separately?
Many applications are output-token heavy, while retrieval and classification workloads may be input-token heavy. Comparing both prices helps avoid picking a model that is cheap for the wrong workload shape.
Should I verify prices before production use?
Yes. AI Model Matrix normalizes public pricing metadata for comparison, but provider availability, limits, and prices can change. Always verify the final contract or provider dashboard before production use.
Related Guides
Cheapest LLM APIs
Sort models by estimated workload cost and normalized token prices.
Open guideLargest Context Windows
Find models for long documents, retrieval, and codebase context.
Open guideCoding Models
Compare code-oriented models by cost, context, and practical popularity signals.
Open guideFree Models
Browse zero-price models for prototypes and evaluation.
Open guideRAG Models
Start from large context windows and practical input-cost constraints.
Open guideChatbot Costs
Find budget-sensitive models for output-heavy assistant traffic.
Open guideCost Calculator
Enter your own input and output token volume before narrowing the shortlist.
Estimate costAlternatives
Find cheaper candidates around popular model anchors.
Find alternatives