Cheapest code-generation models ranked by $/1M tokens.
16 models matched for coding tasks. Cheapest right now: Cohere: North Mini Code (free) at Free blended $/M. Sorted cheapest-first, updated daily.
Subscribe — $9/mo| Model | Input $/M | Output $/M | Blended $/M |
|---|---|---|---|
| Cohere: North Mini Code (free)free cohere | Free | Free | Free |
| Qwen: Qwen3 Coder 30B A3B Instruct qwen | $0.070/M | $0.280/M | $0.122/M |
| Mistral: Codestral 2508 (batch)cache mistralai | $0.150/M | $0.450/M | $0.225/M |
| Qwen: Qwen3 Coder Nextcache qwen | $0.120/M | $0.800/M | $0.290/M |
| Qwen: Qwen3 Coder Flashcache qwen | $0.195/M | $0.975/M | $0.390/M |
| Mistral: Codestral 2508cache mistralai | $0.300/M | $0.900/M | $0.450/M |
| Qwen: Qwen3 Coder 480B A35Bcache qwen | $0.300/M | $1.00/M | $0.475/M |
| OpenAI: GPT-5.1-Codex-Minivisioncache openai | $0.250/M | $2.00/M | $0.688/M |
| Qwen2.5 Coder 32B Instruct qwen | $0.660/M | $1.00/M | $0.745/M |
| Mistral: Devstral 2 2512cache mistralai | $0.400/M | $2.00/M | $0.800/M |
| ByteDance Seed: Seed-2.0-Codevision bytedance-seed | $0.500/M | $3.00/M | $1.12/M |
| MoonshotAI: Kimi K2.7 Codevisioncache moonshotai | $0.671/M | $3.35/M | $1.34/M |
| OpenAI: GPT-5.1-Codex-Maxvisioncache openai | $1.25/M | $10.00/M | $3.44/M |
| OpenAI: GPT-5.1-Codexvisioncache openai | $1.25/M | $10.00/M | $3.44/M |
| OpenAI: GPT-5.3-Codexvisioncache openai | $1.75/M | $14.00/M | $4.81/M |
| OpenAI: GPT-5.2-Codexvisioncache openai | $1.75/M | $14.00/M | $4.81/M |
Pro subscribers get emailed the instant a model they track drops in price, plus a weekly cheapest-per-task digest and full CSV/JSON export.
Subscribe — $9/mo