Claude Sonnet 5 vs Claude Sonnet 5.5
Claude Sonnet 5.5 costs the same as Claude Sonnet 5 per token, $2 input and $10 output per 1M, and scores higher on every benchmark both have. The jump on Terminal-Bench 4.0 is the largest we track between two versions of one model: 10.3% for Sonnet 5, 70.6% for Sonnet 5.5.
Same price, different model
Anthropic released Sonnet 5 on 30 June 2026 and Sonnet 5.5 three months later, on 28 September. Context (1M tokens), output (128K tokens), inputs (text and images) and the input and output prices are all unchanged. The one price that moved is cached input, from $0.20 to $0.10 per 1M tokens.
The Terminal-Bench jump
Both Terminal-Bench 4.0 figures, 10.3% and 70.6%, come from Anthropic's Sonnet 5.5 page. The benchmark runs agentic coding tasks in a real terminal, the work a coding agent does, so this is the number to look at if you run Sonnet in Claude Code. Outside the terminal the gains are smaller: FrontierCode 1.1 went from 42.4% to 46.2%, and Humanity's Last Exam with tools from 54.9% to 64.5%.
What a session costs on each
Without the cache the two cost the same to the cent: $0.65 for our quick fix, $10.80 for the feature session and $97.50 for a long agent day. With 90% of prompts read from the cache, Sonnet 5.5 is cheaper, $2.59 against $3.02 for the feature session and $20.55 against $24.60 for the long day.
Tasks you tuned on Sonnet 5 are worth one run on Sonnet 5.5 before you switch them; changing the model in Claude Code shows where the model is set.
Side by side
| Claude Sonnet 5 | Claude Sonnet 5.5 | |
|---|---|---|
| Maker | Anthropic | Anthropic |
| Released | 30 June 2026[1] | 28 September 2026[2] |
| Context window | 1M tokens[1] | 1M tokens[2] |
| Max output | 128K tokens[1] | 128K tokens[2] |
| Input price | $2 per 1M tokens[1] | $2 per 1M tokens[2] |
| Output price | $10 per 1M tokens[1] | $10 per 1M tokens[2] |
| Cached input | $0.20 per 1M tokens[3] | $0.10 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. | No[2] Offered through the Claude API and cloud platforms; no weights are published. |
| Reads | text, image[1] | text, image[2] |
Benchmarks
Scores as the makers published them, each with its source and date. Makers run these at different settings, so read a gap of a few points as a tie.
| Benchmark | Claude Sonnet 5 | Claude Sonnet 5.5 |
|---|---|---|
| Terminal-Bench 4.0Agentic coding tasks in a real terminal. | 10.3%[4] | 70.6%[4] |
| FrontierCode 1.1 (Main)Hard software engineering tasks. | 42.4%[4] | 46.2%[4] Max effort. |
| Humanity's Last Exam (with tools)Expert-level questions across many fields, tools allowed. | 54.9%[4] | 64.5%[4] |
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 | Claude Sonnet 5 cached | Claude Sonnet 5.5 | Claude Sonnet 5.5 cached |
|---|---|---|---|---|
| Quick fix10 calls of 25K prompt and 1.5K output tokens | $0.65 | $0.24 | $0.65 | $0.22 |
| Feature session60 calls of 80K prompt and 2K output tokens | $10.80 | $3.02 | $10.80 | $2.59 |
| Long agent day300 calls of 150K prompt and 2.5K output tokens | $97.50 | $24.60 | $97.50 | $20.55 |
Value for money and release gap
Claude Sonnet 5.5 came out 3 months later (90 days). 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 | Claude Sonnet 5.5 |
|---|---|---|
| Input tokens per $1 | 500K | 500K |
| Filling the whole context window once | $2.00 | $2.00 |
| Feature session per point of Terminal-Bench 4.0 | $1.05 | $0.15 |
| Feature session per point of FrontierCode 1.1 (Main) | $0.25 | $0.23 |
| Feature session per point of Humanity's Last Exam (with tools) | $0.20 | $0.17 |
Questions
Is Sonnet 5.5 more expensive than Sonnet 5?
No. Both cost $2 per 1M input tokens and $10 per 1M output tokens. Cached input is cheaper on Sonnet 5.5: $0.10 against $0.20.
Is the 10.3% Terminal-Bench score for Sonnet 5 right?
It is the figure Anthropic lists for Sonnet 5 on its Sonnet 5.5 page, next to 70.6% for Sonnet 5.5. Both are cited in the benchmark table on this page.
Should I move from Sonnet 5 to Sonnet 5.5?
For new work, yes: the per-token price is the same and every published score is higher. Run prompts you tuned on Sonnet 5 once on Sonnet 5.5 first.
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 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 Kimi K3
- 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