Coding models write, complete, explain and refactor code across many languages. They differ in context window, language coverage and cost.
Compare strong open and hosted coding models and call them through one OpenAI-compatible API.
11 modell
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.
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.
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.
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.
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.
IBM Granite 20B Code Instruct. Larger Granite code model balancing quality and inference cost for enterprise CI/CD code-review automation.
IBM Granite 8B Code Instruct. Trained on permissively-licensed code, strong on multi-language code completion and instruction-following.
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. Highly tuned CodeLlama variant focused on retrieval-augmented developer assistant workflows.
BigCode StarCoder2 15B code-generation flagship. Trained on 4T tokens of Stack v2 data with grouped-query attention and 16k context.
WizardLM WizardCoder 33B v1.1. Evol-Instruct fine-tune of DeepSeek-Coder-33B with strong code-generation benchmark performance.
Listed for reference. These models have no verified price or are no longer served, so the API does not run them.
Try any model with a free generation, no signup. Then transparent per-use pricing, no subscription.
Generate clean, editable SVG vectors and convert raster images to vectors with AI. Compare Recraft, StarVector and more through one API.
Remove or replace image backgrounds automatically with AI. Clean cutouts with transparent alpha for products, portraits and objects.
Upscale, sharpen, denoise and restore photos with AI. Bring back old or low-resolution images, fix faces and add detail.
Create professional AI headshots, avatars and stylized portraits from a photo or prompt. Consistent identity, many styles.
Generate logos, icons and line art with AI, including true SVG vector output for crisp scaling at any size.
Generate images from text with the top AI models - Flux, SDXL, Stable Diffusion, Ideogram, Recraft and more, through one API.
