93Fit score
Qwen3-Coder-30B-A3B-Instruct is a 30.5B parameter Mixture-of-Experts (MoE) model with 128 experts (8 active per forward pass), designed for advanced code generation, repository-scale understanding, and agentic tool use. …
Model details →Best AI models for coding
Ranked by tool-use support, code-related signals in vendor descriptions, and overall capability. Includes both proprietary APIs and open-weight models you can self-host.
92Fit score
DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture. It activates 8B parameters on input and 16B on...
Model details →92Fit score
DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture. It activates 8B parameters on input and 16B on...
Model details →Top 25 models for code generation
| # | Model | Provider | Context | Input price / 1M | Tier |
|---|---|---|---|---|---|
| 1 | Qwen: Qwen3 Coder 30B A3B Instruct | Qwen | 262K Long context (128K+) | $0.07 | Budget |
| 2 | DeepSeek: DeepSeek V4.1 Flash | DeepSeek | 1.0M Ultra context (1M+) | $0.30 | Budget |
| 3 | DeepSeek: DeepSeek V4.1 Flash (batch) | DeepSeek | 1.0M Ultra context (1M+) | $0.11 | Budget |
| 4 | IBM: Granite 4.1 8B | Ibm Granite | 131K Long context (128K+) | $0.05 | Budget |
| 5 | Qwen: Qwen3 Coder Flash | Qwen | 1M Ultra context (1M+) | $0.20 | Budget |
| 6 | Qwen: Qwen3 Coder Plus | Qwen | 1M Ultra context (1M+) | $0.65 | Budget |
| 7 | Kwaipilot: KAT-Coder-Air V2.5 | Kwaipilot | 256K Long context (128K+) | $0.15 | Budget |
| 8 | Kwaipilot: KAT-Coder-Pro V1 | Kwaipilot | 256K Long context (128K+) | $0.21 | Budget |
| 9 | Kwaipilot: KAT-Coder-Pro V2 | Kwaipilot | 262K Long context (128K+) | $0.30 | Budget |
| 10 | Kwaipilot: KAT-Coder-Pro V2.5 | Kwaipilot | 262K Long context (128K+) | $0.74 | Budget |
| 11 | Qwen: Qwen3 Coder 480B A35B | Qwen | 262K Long context (128K+) | $0.30 | Budget |
| 12 | Qwen: Qwen3 Coder 480B A35B (exacto) | Qwen | 262K Long context (128K+) | $0.22 | Budget |
| 13 | Qwen: Qwen3 Coder Next | Qwen | 262K Long context (128K+) | $0.12 | Budget |
| 14 | StepFun: Step 3.7 Flash | Stepfun | 262K Long context (128K+) | $0.20 | Budget |
| 15 | xAI: Grok Code Fast 1 | X Ai | 256K Long context (128K+) | $0.20 | Budget |
| 16 | Inception: Mercury Coder | Inception | 128K Long context (128K+) | $0.25 | Budget |
| 17 | Mistral: Devstral Medium | Mistral AI | 131K Long context (128K+) | $0.40 | Budget |
| 18 | OpenAI: GPT Audio Mini | OpenAI | 128K Long context (128K+) | $0.60 | Budget |
| 19 | OpenAI: GPT Audio | OpenAI | 128K Long context (128K+) | $2.50 | Standard |
| 20 | Qwen: Qwen3 Coder 480B A35B (free) | Qwen | 262K Long context (128K+) | $0.00 | Budget |
| 21 | Z.ai: GLM 4 32B | Z Ai | 128K Long context (128K+) | $0.10 | Budget |
| 22 | Qwen: Qwen2.5 Coder 7B Instruct | Qwen | 33K Short/standard context | $0.03 | Budget |
| 23 | Qwen2.5 Coder 32B Instruct | Qwen | 33K Short/standard context | $0.66 | Budget |
| 24 | Arcee AI: Trinity Large Preview (free) | Arcee Ai | 131K Long context (128K+) | $0.00 | Budget |
| 25 | Google: Gemini 2.5 Flash Lite Preview 09-2025 | 1.0M Ultra context (1M+) | $0.10 | Budget |
Frequently asked questions
What's the best AI coding model right now?
It depends on whether you need raw quality (Claude Opus, GPT-5 Codex), low cost (Qwen Coder, DeepSeek), or self-hosting (Qwen Coder, GPT-OSS). Use the table above sorted by capability score and price tier.
Do these models support tool use?
Most flagship coding models on this page support tool/function calling — look for the 'tool-use' tag. Open-weight models vary; check each model page for the supported parameters.
Which coding model has the largest context window?
Models with 1M+ context (sorted at the top of the long-context column) handle entire monorepos in a single prompt.
Related use cases
AI reasoning modelsAI vision modelslong-context AI models (128K+)AI models for function callingAI models for structured / JSON outputsAI models for agentsfree AI modelsCheapest AI models per tokenmultilingual AI modelsembedding modelssmall / on-device AI modelsAI image generation modelsAI voice / audio modelsAI models for mathAI models for writingopen-source AI modelsAI models for RAGAI models for summarizationAI models for translationAI models for enterprise