Claude Sonnet 5.5 vs Kimi K3
Claude Sonnet 5.5 is the cheaper model at list prices: $2 input and $10 output per 1M tokens against $3 and $15 for Kimi K3, so our feature session costs $10.80 against $16.20. Kimi K3 makes its case elsewhere. Its weights are open, it reads video as well as text and images, and it can write replies of up to 944K tokens.
Price
Kimi K3 costs 1.5 times as much per token. Its cached input is $0.30 against $0.10, so with 90% of prompts cached the feature session costs $4.54 on Kimi K3 and $2.59 on Sonnet 5.5. A long agent day is $146 against $97.50.
Running Kimi K3 in Claude Code
Claude Code can talk to any endpoint that speaks the Anthropic Messages API, and Moonshot runs one for Kimi. Your Claude plan doesn't cover those requests, and Anthropic doesn't support that routing. Using Claude Code with GLM or Kimi has the settings and what still works.
Scores, size and dates
Sonnet 5.5 scored 70.6% on Terminal-Bench 4.0, 46.2% on FrontierCode 1.1 and 64.5% on Humanity's Last Exam with tools. We found no Kimi K3 score on any of them.
Kimi K3 reads up to 1.05M tokens, Sonnet 5.5 up to 1M; Sonnet writes up to 128K per reply. Kimi K3 was first listed on the API on 16 July 2026, and Anthropic released Sonnet 5.5 two months later, on 28 September.
Side by side
| Claude Sonnet 5.5 | Kimi K3 | |
|---|---|---|
| Maker | Anthropic | Moonshot AI |
| Released | 28 September 2026[1] | 16 July 2026[2] first API listing |
| Context window | 1M tokens[1] | 1.05M tokens[3] As served by the price's provider on OpenRouter. |
| Max output | 128K tokens[1] | 944K tokens[3] As served by the price's provider on OpenRouter. |
| Input price | $2 per 1M tokens[1] | $3 per 1M tokens[3] |
| Output price | $10 per 1M tokens[1] | $15 per 1M tokens[3] |
| Cached input | $0.10 per 1M tokens[4] | $0.30 per 1M tokens[3] |
| Long prompts | One price | One price |
| Price change | None announced | None announced |
| Open weights | No[1] Offered through the Claude API and cloud platforms; no weights are published. | Yes[5] Custom licence. |
| Reads | text, image[1] | text, image, video[2] |
Benchmarks
None of the benchmarks below has a published score for both models. We only show a score we can cite with its source and date; "Not published" means we found none for that model, not that it scored zero.
| Benchmark | Claude Sonnet 5.5 | Kimi K3 |
|---|---|---|
| Terminal-Bench 4.0Agentic coding tasks in a real terminal. | 70.6%[6] | Not published |
| FrontierCode 1.1 (Main)Hard software engineering tasks. | 46.2%[6] Max effort. | Not published |
| Humanity's Last Exam (with tools)Expert-level questions across many fields, tools allowed. | 64.5%[6] | Not published |
What a coding session costs
Our own estimate from the list prices above, for three sessions we define: a coding agent resends the conversation with every call, so prompts are large and grow. "Cached" assumes 90% of prompt tokens are read from the prompt cache and leaves out cache write fees. A long-prompt price applies when a call's prompt is over its threshold. Work out your own mix with the token cost calculator.
| Session | Claude Sonnet 5.5 | Claude Sonnet 5.5 cached | Kimi K3 | Kimi K3 cached |
|---|---|---|---|---|
| Quick fix10 calls of 25K prompt and 1.5K output tokens | $0.65 | $0.22 | $0.97 | $0.37 |
| Feature session60 calls of 80K prompt and 2K output tokens | $10.80 | $2.59 | $16.20 | $4.54 |
| Long agent day300 calls of 150K prompt and 2.5K output tokens | $97.50 | $20.55 | $146 | $36.90 |
Value for money and release gap
Claude Sonnet 5.5 is dated 2 months later (74 days; Kimi K3: first API listing). Price per point divides our feature-session cost by a published score: lower means more score for the money. It is a rough lens, not a ranking.
| Measure | Claude Sonnet 5.5 | Kimi K3 |
|---|---|---|
| Input tokens per $1 | 500K | 333K |
| Filling the whole context window once | $2.00 | $3.15 |
Questions
Is Kimi K3 cheaper than Claude Sonnet 5.5?
No. At list prices Kimi K3 costs $3 per 1M input tokens and $15 per 1M output, against $2 and $10 for Sonnet 5.5. Our feature session costs $16.20 on Kimi K3 and $10.80 on Sonnet 5.5.
Does Kimi K3 have open weights?
Yes, according to the source we cite. The weights of Claude Sonnet 5.5 are not open.
Which has the bigger context window?
Kimi K3, slightly: 1.05M tokens against 1M. Its output limit is far larger, 944K tokens against 128K for Sonnet 5.5.
Most compared
Any other two models: pick them in the lists at the top of the page.
- Claude Opus 5.5 vs Claude Sonnet 5.5
- Claude Sonnet 5 vs Claude Sonnet 5.5
- Claude Haiku 5.5 vs Claude Sonnet 5.5
- Claude Sonnet 5.5 vs GPT-6.1 Sol
- Claude Sonnet 5.5 vs Gemini 4 Argon
- Claude Sonnet 5.5 vs GLM-5.3
- Claude Fable 5.1 vs Claude Opus 5.5
- Claude Opus 5 vs Claude Opus 5.5
- Claude Haiku 4.5 vs Claude Haiku 5.5
- Claude Fable 5 vs Claude Fable 5.1
- Claude Opus 5.5 vs GPT-6.1 Sol
- Claude Opus 5.5 vs GPT-5.6 Sol
- Claude Fable 5.1 vs GPT-6 Astra
- Claude Opus 5.5 vs GPT-6 Astra
- Claude Haiku 5.5 vs GPT-6 Luna
- GPT-6.1 Sol vs GPT-6 Sol
- GPT-6.1 Sol vs GPT-6 Astra
- Claude Opus 5.5 vs Gemini 4 Argon
- Claude Opus 5.5 vs Gemini 3.1 Pro Preview
- Gemini 4 Argon vs GPT-6.1 Sol
- Gemini 3.1 Pro Preview vs Gemini 4 Argon
- Claude Haiku 5.5 vs Gemini 3.8 Flash
- Claude Opus 5.5 vs Grok 4.7
- Claude Opus 5.5 vs DeepSeek V4 Pro
More tools
Sources
Numbers from the makers' own pages, checked by hand, last read . List prices in US dollars before tax. Spotted a mistake? office@shuriken.sh.
Made by Shuriken, the harness for coding agents. Its hot swapping moves your chats to another of your accounts or API keys when one nears its limit. Use only accounts you own and are entitled to use.
Try Shuriken on your own computerYou're signed in
Add your Claude, Codex and Gemini accounts once. Shuriken switches between them so your agents keep working.Your accounts, projects and chats are in the app.
Coming soon