prev Sonnet, still fast & capable.
Claude Sonnet 4.6 beside its stablemates and nearest rivals. The ◆ marks the best value in each column across every row shown.
| Model | Intelligence | Coding | Speed | Input $/M | Output $/M | Blended $/M | Context |
|---|---|---|---|---|---|---|---|
| Claude Fable 5 | 59.9◆ | 76.5◆ | 60.2◆ | $10◆ | $50◆ | $20◆ | 1M◆ |
| Claude Opus 4.8 | 55.7◆ | 74.3◆ | 65.9◆ | $5◆ | $25◆ | $10◆ | 1M◆ |
| Claude Opus 4.7 | 53.5◆ | 73.6◆ | 60.7◆ | $5◆ | $25◆ | $10◆ | 1M◆ |
| Claude Sonnet 5 | 53.4◆ | 71.5◆ | 82.1◆ | $2◆ | $10◆ | $4◆ | 1M◆ |
| Claude Sonnet 4.6 ◆ | 47.2◆ | 63◆ | 67.8◆ | $3◆ | $15◆ | $6◆ | 1M◆ |
| Claude Opus 5 | —◆ | —◆ | —◆ | $5◆ | $25◆ | $10◆ | 1M◆ |
| DeepSeek V4 Propinned | 44.3◆ | 59.4◆ | 70.9◆ | $0.43◆ | $0.87◆ | $0.54◆ | 1M◆ |
| DeepSeek V4 Flashpinned | 40.3◆ | 56.2◆ | 122◆ | $0.14◆ | $0.28◆ | $0.18◆ | 1M◆ |
The Intelligence Index and its sub-scores, ranked against every scored model in the catalog. A metric that has not been measured for Claude Sonnet 4.6 has been left empty.
How far a month of credits goes on Claude Sonnet 4.6.
Real coding tasks priced end to end on Claude Sonnet 4.6, from a quick lookup to a full-repo agent run.
| Task | Tokens in · out | Claude Sonnet 4.6 | GPT-5.6 Terra | Claude Haiku 4.5 |
|---|---|---|---|---|
| Quick lookup / one-liner | 8K · 1K | $0.02 | $0.02 | $0.0065 |
| Review a 500-line PR | 60K · 4K | $0.13 | $0.12 | $0.04 |
| Fix a bug (agent loop) | 180K · 12K | $0.36 | $0.33 | $0.12 |
| Refactor a module | 320K · 20K | $0.64 | $0.58 | $0.21 |
| Full-repo agent run | 900K · 45K | $1.48 | $1.35 | $0.49 |
$3/M input and $15/M output, cache reads $0.30/M. In an agent loop most input is cache-read, so the effective input rate is about $1.11/M.cmd --model claude-sonnet-4-6, or type /model in a session and pick it. You can switch mid-session without losing context.Command Code is the AI coding agent that continuously learns your taste. Start for $1.