Compare

Two or three models, side by side.

Rates, worked costs, limits and capabilities from the same data as every model page. Among the models you pick, the lowest price and the largest window are marked.

The comparison is in the address bar, so you can share it. Looking for something else? Browse all 11 models.

Showing a default comparison. Picking other models needs JavaScript; every model's rates are also on the models page.

Model	Claude Opus 5.5Anthropic · Flagship	GPT-6.1 SolOpenAI · Flagship	DeepSeek V4 FlashDeepSeek · FastNew	Claude Sonnet 5Anthropic · Balanced	Claude Haiku 4.5Anthropic · Fast	GPT-5.6 SolOpenAI · Flagship	GPT-5.6 TerraOpenAI · Balanced	Grok 4.6xAI · Balanced	Claude Sonnet 5.5Anthropic · BalancedNew	Grok 4.7xAI · FlagshipNew	DeepSeek V4 ProDeepSeek · BalancedNew
Price per 1M tokens
Input	$4.40	$2.20	$0.24Lowest	$2.20	$1.10	$5.50	$2.20	$2.20	$2.20	$2.20	$1.32
Output	$22.00	$11.00	$0.96Lowest	$11.00	$5.50	$33.00	$13.20	$6.60	$11.00	$6.60	$3.96
Cached input	$0.22	$0.11	$0.0048Lowest	$0.22	$0.11	$0.55	$0.22	$0.55	$0.22	$0.55	$0.044
Output vs input	5×	5×	4×	5×	5×	6×	6×	3×	5×	3×	3×
Example cost
1,000 chat replies (1.5k in, 400 out)	$15.40	$7.70	$0.744Lowest	$7.70	$3.85	$21.45	$8.58	$5.94	$7.70	$5.94	$3.564
1M input + 200k output	$8.80	$4.40	$0.432Lowest	$4.40	$2.20	$12.10	$4.84	$3.52	$4.40	$3.52	$2.112
Limits
Context window	1M	1.05MLargest	1M	1M	200k	1.05M	1.05M	500k	1M	500k	1M
Max output	128k	128k	384kLargest	128k	64k	128k	128k	Not published	128k	Not published	384k
Modalities
Input	Text, Image	Text, Image	Text	Text, Image	Text, Image	Text, Image	Text, Image	Text, Image	Text, Image	Text, Image	Text
Output	Text	Text	Text	Text	Text	Text	Text	Text	Text	Text	Text
Capabilities
Tools	Yes	Yes	Yes	Yes	Yes	Yes	Yes	Yes	Yes	Yes	Yes
Vision	Yes	Yes	No	Yes	Yes	Yes	Yes	Yes	Yes	Yes	No
Reasoning	Yes	Yes	Yes	Yes	Yes	Yes	Yes	Yes	Yes	Yes	Yes
JSON mode	No	Yes	Yes	No	No	Yes	Yes	No	No	No	Yes
Structured output	Yes	Yes	No	Yes	Yes	Yes	Yes	Yes	Yes	Yes	No
Prompt caching	Yes	Yes	Yes	Yes	Yes	Yes	Yes	Yes	Yes	Yes	Yes
Access
API formats	Anthropic, OpenAI	OpenAI	OpenAI	Anthropic, OpenAI	Anthropic, OpenAI	OpenAI	OpenAI	OpenAI	Anthropic, OpenAI	OpenAI	OpenAI
Plan allowances	Pro, Plus, Max	Pro, Plus, Max	Pro, Plus, Max	Pro, Plus, Max	Pro, Plus, Max	Pro, Plus, Max	Pro, Plus, Max	Pro, Plus, Max	Pro, Plus, Max	Pro, Plus, Max	Pro, Plus, Max
Released	22 Sept 2026	29 Sept 2026	10 Sept 2026	30 Jun 2026	15 Oct 2025	9 Jul 2026	9 Jul 2026	Not published	Not published	21 Sept 2026	13 Aug 2026
Links	Model page for Claude Opus 5.5 Try in Chat with Claude Opus 5.5	Model page for GPT-6.1 Sol Try in Chat with GPT-6.1 Sol	Model page for DeepSeek V4 Flash Try in Chat with DeepSeek V4 Flash	Model page for Claude Sonnet 5 Try in Chat with Claude Sonnet 5	Model page for Claude Haiku 4.5 Try in Chat with Claude Haiku 4.5	Model page for GPT-5.6 Sol Try in Chat with GPT-5.6 Sol	Model page for GPT-5.6 Terra Try in Chat with GPT-5.6 Terra	Model page for Grok 4.6 Try in Chat with Grok 4.6	Model page for Claude Sonnet 5.5 Try in Chat with Claude Sonnet 5.5	Model page for Grok 4.7 Try in Chat with Grok 4.7	Model page for DeepSeek V4 Pro Try in Chat with DeepSeek V4 Pro

Rates in US dollars per 1M tokens; struck-through rates are the regular price during a promotion. Example costs use today's rates. Model your own traffic

Switching later is one line.

Every model here runs on the same key and balance, so you can start with one and change the model field when the work changes.

Get an API key All models

Two or three models, side by side.

Comparison

Switching later is one line.