LLM Comparison
Claude Sonnet 5 vs Kimi K3
Side-by-side specs, pricing & capabilities · Updated September 2026
Price vs Intelligence
Add to comparison
2/6 models| Organization | ||
| OpenTools Score | 63 10.4 | 80 8.9 |
| Family | Claude Sonnet | Kimi |
| Status | Current | Current |
| Release Date | Jun 2026 | — |
| Context Window | 1.0M tokens | 1.0M tokens |
| Input Price | $2.00/M tokens | $3.00/M tokens |
| Output Price | $10.00/M tokens | $15.00/M tokens |
| Pricing Notes | Claude API standard pricing is $2 input and $10 output per million tokens. Cache reads are $0.20, 5-minute cache writes $2.50, and 1-hour cache writes $4 per million tokens. Batch API input/output receives a 50% discount. Current official documentation lists these rates without the previously recorded August 31 introductory expiry; provider-specific rates may differ. | Official Kimi pricing lists kimi-k3 at $3.00 per 1M cache-miss input tokens, $0.30 per 1M cache-hit input tokens, and $15.00 per 1M output tokens. Official troubleshooting docs say max_completion_tokens defaults to 131,072 and maximum output length is 1024*1024 minus prompt tokens. |
| Capabilities | textvisionreasoningcodingtool-useextended-thinkingagents | textvisionreasoningcodingtool-usestructured-outputjson-modelong-contextagentic |
| Max Output | 128K tokens | 131K tokens |
| API Identifier | claude-sonnet-5 | kimi-k3 |
| Benchmarks | ||
| Artificial Analysis Intelligence Index | 53artificial-analysis | 57artificial-analysis |
| Artificial Analysis Intelligence Index v4.3 | 38https://artificialanalysis.ai/models/claude-sonnet-5 | 44https://artificialanalysis.ai/models/kimi-k3 |
| GPQA Diamond | 91.1111artificial-analysis | 93.5354artificial-analysis |
| SciCode | 54.2824artificial-analysis | 59.4907artificial-analysis |
| Terminal-Bench 2.1 | 80.5243artificial-analysis | 85.0187artificial-analysis |
| AA-Briefcase | — | 1543artificial-analysis |
| AA-Briefcase Rubric Pass Rate | — | 51artificial-analysis |
| Artificial Analysis Intelligence Index v4.1.1 | — | 60artificial-analysis |
| View Claude Sonnet 5 | View Kimi K3 | |
Cost Calculator
Enter your expected monthly token usage to compare costs.
| Model | Input | Output | Total / mo | vs Best |
|---|---|---|---|---|
| Claude Sonnet 5Cheapest | $2.00 | $5.00 | $7.00 | — |
| Kimi K3 | $3.00 | $7.50 | $10.50 | +50% |
Anthropic
Claude Sonnet 5
Claude Sonnet 5 is Anthropic next-generation Sonnet model and a drop-in upgrade from Sonnet 4.6. Anthropic docs state that adaptive thinking is on by default, manual extended thinking is removed, sampling parameter overrides return errors, and the model supports a 1M token context window with 128K max output.
Moonshot AI
Kimi K3
Kimi K3 is Moonshot AI open-weight 2.8T-parameter flagship model for long-horizon coding, end-to-end knowledge work, reasoning, and native multimodal understanding. Official Kimi documentation lists the API model ID kimi-k3, a 1M-token context window, automatic context caching, tool calls, JSON mode, structured outputs, and always-on reasoning effort controls.
More Comparisons
Looking for more AI models?
Browse All LLMs