HomeCoding models
Coding models
OpenRouter’s programming collection is the filter. The table is who is cheap on a long repo and who is cheap on a long patch.
Updated 2026-09-27
No public board on OpenRouter names a single best coding model. The programming collection groups candidates. Your repo, your tests, and the output price decide.
| Slug | Input / M | Output / M | Fit |
|---|---|---|---|
| deepseek/deepseek-v4-flash-0731 | $0.021 | $0.32 | Large context, short patches |
| deepseek/deepseek-v4-pro | $0.348 | $0.696 | Long answers, 0423 price |
| qwen/qwen3-32b | $0.08 | $0.28 | Small dense, 131K |
| z-ai/glm-5.2 | $0.650 | $2.04 | Long agent runs |
| qwen/qwen3.7-max | $1.48 | $4.43 | Flagship Qwen, 1M |
| anthropic/claude-sonnet-5 | $2 | $10 | Claude Code default class |
A coding agent spends more on output than a chatbot when it rewrites files. Sonnet 5 at $10 per million output tokens is a different monthly bill from V4 Pro 0423 at $0.70. Run the same task on two slugs before you lock a default.
The collection URL is openrouter.ai/collections/programming. Relace Search and Apply are narrower coding tools on their own page.
Questions
What is the cheapest coding model on this list?
DeepSeek V4 Flash 0731, at $0.021 per million input tokens on 27 Sep 2026. It is not automatically the one that passes your tests.
Which model should Claude Code use?
An Anthropic slug. OpenRouter says Claude Code is only guaranteed against Anthropic’s first-party provider. See the Claude Code guide.
Where is the collection?
https://openrouter.ai/collections/programming
Related
- Coding agents
OpenRouter’s coding-agent apps include Claude Code, OpenCode, and others. The agent is the client. The model is the slug you attach.
- DeepSeek API price
On 27 Sep 2026 OpenRouter listed DeepSeek V4 Pro 0423 at $0.348 / $0.696 per million tokens, and V4 Pro 0813 at $0.245 / $3.50.
- Claude Sonnet 5 pricing
Claude Sonnet 5 was $2 input and $10 output per million tokens on 27 Sep 2026. Batch is $1 and $5. The slug is anthropic/claude-sonnet-5.
- GLM 5.2 API
GLM 5.2 on OpenRouter was $0.650 input and $2.042 output per million tokens on 27 Sep 2026. The slug is z-ai/glm-5.2, with a 1M context.