Code Models
AI-powered coding assistants for development
Code-modellen voor autocomplete, review en refactoring
Code-generatiemodellen zijn large language models die specifiek getraind of fine-tuned zijn op broncode. Ze drijven IDE-autocomplete, PR-review, automatische refactoring, testgeneratie en cross-language vertaling aan. Je grijpt naar een code-model — in plaats van een algemeen tekstmodel — wanneer je sterkere correctheid op programmeertaken wilt en gestructureerde output (diffs, JSON) die goed samenwerkt met developer-tooling.
21 models available
Codestral
Mistral's code-specialized model. Optimized for code generation, completion, and understanding across 80+ languages.
Code Llama 13B Instruct
Meta's 13B Code Llama tuned for instruction following. A faster mid-size option for code generation and completion, supporting infilling for inserting code at a cursor position. Served on Replicate per call.
Code Llama 34B Instruct
Meta's 34B Code Llama tuned for instruction following. A balance of size and quality for code generation, completion, and explanation, with strong coverage of Python, JavaScript, and other common languages. Runs on Replicate per call.
Code Llama 70B Instruct
Meta's largest Code Llama, a 70B Llama-2 derivative specialized for programming and tuned to follow instructions in chat form. Handles code generation, completion, and explanation across common languages. Served on Replicate as a per-call endpoint.
Code Llama 7B Instruct
Meta's smallest Code Llama at 7B parameters, tuned for instruction following. The cheapest and fastest member of the family for quick code generation, completion, and infilling. Served on Replicate per call.
CodeGen 350M Mono
350M autoregressive code generation model from Salesforce, the smallest of the original CodeGen family. The mono variant was further trained on Python so it is well suited for short Python completions and program synthesis from a natural-language or code prompt.
DeepSeek Coder 1.3B Instruct
1.3B instruction-tuned code model from DeepSeek, trained on 2 trillion tokens of code and natural language across 87 languages with a 16k context window. One of the strongest tiny coders for its size, handling generation, completion and short coding instructions.
DeepSeek Coder 33B Instruct (GGUF)
Quantized GGUF build of DeepSeek's 33B code model, trained on roughly 2T tokens that are about 87 percent code. Designed for repository-level completion and project-aware generation thanks to a 16k context window. Runs on Replicate as a per-call endpoint.
DeepSeek Coder V2
DeepSeek's specialized coding model. Excellent at code generation, debugging, and explanation.
Granite Code 20B
IBM Granite 20B Code Instruct. Larger Granite code model balancing quality and inference cost for enterprise CI/CD code-review automation.
Granite Code 8B
IBM Granite 8B Code Instruct. Trained on permissively-licensed code, strong on multi-language code completion and instruction-following.
Grok Build 0.1
xAI's Grok coding-focused model. Tuned for code generation and software development tasks with a 256k token context window for working over large codebases.
Magicoder S CL 7B
UIUC Magicoder S CL 7B. CodeLlama-7B fine-tuned with OSS-Instruct synthetic data. Strong HumanEval Plus and MBPP Plus performance per parameter.
Phind CodeLlama 34B v2
Phind CodeLlama 34B v2. Highly tuned CodeLlama variant focused on retrieval-augmented developer assistant workflows.
Qwen2.5-Coder 32B Instruct
Alibaba's largest open Qwen2.5-Coder model. Trained on a code-heavy corpus, it matches or beats much larger general models on code generation and repair benchmarks like HumanEval and MBPP, and supports over 40 programming languages with fill-in-the-middle completion.
Qwen2.5-Coder 7B Instruct
The 7B instruct member of Alibaba's Qwen2.5-Coder family. A lighter, faster option for code completion, generation, and bug fixing across 40+ languages, with a 128k context and fill-in-the-middle support. Good price-to-quality balance for everyday coding tasks.
Replit Code v1 3B
Replit's 3B code-completion model, trained on a permissively licensed code subset of the Stack across 20 programming languages. Built for low-latency autocomplete rather than chat. Served on Replicate per call.
Replit Code v1.5 3B
3B code completion model from Replit trained on roughly 1 trillion tokens of permissively licensed code across 30 programming languages, with a 4k context window. Designed for autocomplete-style code generation and fill-in-the-middle.
Stable Code Instruct 3B
Instruction-tuned 3B code model from Stability AI, fine-tuned from stable-code-3b for chat-style coding tasks. Handles code generation, explanation and fix-up across multiple languages and was competitive with larger code models on benchmarks at release.
StarCoder2 15B
BigCode StarCoder2 15B code-generation flagship. Trained on 4T tokens of Stack v2 data with grouped-query attention and 16k context.
WizardCoder 33B
WizardLM WizardCoder 33B v1.1. Evol-Instruct fine-tune of DeepSeek-Coder-33B with strong code-generation benchmark performance.
Top code models picks
Hand-picked across four common criteria — resolved against the live catalog so the picks track price and performance changes.
Mistral's code-specialized model. Optimized for code generation, completion, and understanding across 80+ languages.
Learn more350M autoregressive code generation model from Salesforce, the smallest of the original CodeGen family. The mono variant was further trained on Python so it is well suited for short Python completions and program synthesis from a natural-language or code prompt.
Learn moreMistral's code-specialized model. Optimized for code generation, completion, and understanding across 80+ languages.
Learn moreMistral's code-specialized model. Optimized for code generation, completion, and understanding across 80+ languages.
Learn moreDe prijs in code-generatie volgt hetzelfde per-token-model als algemene tekst. Flagship code-modellen (GPT-5 Codex, Claude 4.6 Sonnet, Codestral) kosten €1-€10 per miljoen input-tokens; budgettiers (Codestral Mamba, DeepSeek Coder, Qwen Coder) kosten €0,05-€0,50 per miljoen. Eén IDE-autocomplete-aanvraag loopt zelden boven enkele duizenden input-tokens, dus de prijs per call zit in fracties van een cent. De rekeningen groeien wanneer je agents uitrolt die zichzelf tientallen keren per taak herprompten.
De afwegingsdriehoek is correctheid, snelheid en context. Flagships lossen lastiger problemen op en volgen projectconventies betrouwbaarder, maar reageren met 30-80 tokens/seconde, wat traag voelt in een strakke autocomplete-loop. Snelle budgetmodellen (Codestral Mamba, GPT-5 Mini) streamen op 200+ tokens/seconde en voelen native in de editor. Voor batchtaken (refactor een heel repo, genereer tests voor vijftig bestanden) wint de correctheid van het flagship. Voor strakke autocomplete-loops wint de snelle tier.
Pas op met cross-file context: de meeste autocomplete-loops sturen alleen het huidige bestand. Voor echte codebase-aware refactoring heb je een retrievallaag nodig die gerelateerde bestanden in de prompt trekt. Tools als Cursor en Continue doen dat automatisch; bouw je het zelf, embed dan eerst de codebase en haal per request de 5-10 meest relevante bestanden op.
Pas op met licentievervuiling: enkele open-weights code-modellen zijn alleen op permissief gelicentieerde code getraind; andere hebben GPL-code meegenomen met onduidelijke herverdelingsvoorwaarden. Als je gegenereerde code in een closed-source product uitrolt, verkies dan commerciële modellen met expliciete code-licentiegaranties.
De topkeuzes hierboven dekken het meest correcte flagship, het goedkoopste werkpaard, het model met de langste context en de snelste autocomplete-optie.
Popular use cases
Common patterns built with code models on Railwail.
Frequently asked questions
Start Building with AI
Access all models through a single API. Get free credits when you sign up — no credit card required.