Best API models for coding
Match the model to the change.
Scoped fixes and open-ended engineering are different jobs. Neon at high effort is a strong value test. Microsoft’s MAI cost claims use promotional prices and its own coding tests. Review changes and run your own tests.
Everyday coding and agents; a writing-workflow candidate.
Benchmark $10.02/task · $2.00 in / $10.00 out per 1M
Complex coding, analytical reasoning and mixed-media workflows.
Benchmark $6.45/task · $3.00 in / $15.00 out per 1M
Anthropic’s recommended default for most work, including long-running coding and knowledge work.
Benchmark $10.04/task · $4.00 in / $20.00 out per 1M
Difficult software, computer-use and document workflows.
Benchmark $4.00/task · $8.00 in / $40.00 out per 1M
Hard reasoning and long-horizon agents.
Benchmark $26.54/task · $8.00 in / $40.00 out per 1M
Targeted edits, explanations, routine fixes and rapid iteration.
No token price