ChatModelsPricingDocsFor agents
Log inGet API Key

Models / Use cases

Best coding models, ranked with exact prices

Coding is the workload where model choice matters most: tool-calling reliability, long-context repo comprehension, and cost per completed task diverge sharply between models. These are the picks we route the most code through, with exact prices.

Ranked

The picks

1

Claude Sonnet 4.5

$3/Mtok in

The default for coding agents, the strongest tool-use reliability per dollar in the library.

$3 / M input · $15 / M output

2

GLM-5.2

$1.4/Mtok in

The open-weights frontier challenger, strong coding and reasoning at a fraction of frontier pricing.

$1.4 / M input · $4.4 / M output

3

Kimi K3

$3/Mtok in

Open-weights agentic pick, most of the tool-calling reliability at a fraction of the price.

$3 / M input · $15 / M output

4

DeepSeek V4 Flash

$0.44/Mtok in

Bulk codegen, test scaffolding, and autocomplete at commodity prices, pair it with a frontier reviewer.

$0.44 / M input · $1.32 / M output

FAQ

Frequently asked questions

Which model should a coding agent default to?

Start with Claude Sonnet 4.5 for the main loop and route high-volume sub-tasks (lint fixes, summaries) to a cheap tier like Haiku or DeepSeek V4 Flash. With one key across all of them, the split is a config change.

Can I use these models in Claude Code, Cursor, or Cline?

Yes, every tool that accepts an OpenAI-compatible base URL works. See the integration guides for exact setup per tool.

One key. Every model. Exact prices.

Route every pick on this page through one key. Free starter credits included, no subscription required.

Get your API keyBrowse all models