Model comparison
Claude Opus 5.5 vs GPT-5.5: the newer model costs less
Claude Opus 5.5 undercuts GPT-5.5 on input, output, and cache hits, yet a cached coding session is only 12% cheaper. GPT-5.5 leaves Codex sign-in soon.
· Prices as of September 28, 2026
Claude Opus 5.5
Anthropic · Released September 22, 2026
Anthropic's recommended starting model for most work, built for long-running agentic coding. Anthropic says it matches Claude Fable 5.1 on most work at a much lower price.
Claude Opus 5.5 facts and comparisonsGPT-5.5
OpenAI · Released April 23, 2026 · Previous generation
OpenAI's April 2026 flagship for coding and professional work, now a previous generation that stays in the API.
GPT-5.5 facts and comparisons
The short answer
Claude Opus 5.5 costs less than GPT-5.5 on every workload here, from $4.40 against $5.00 on the example agentic coding session to $1.72 against $2.55 on output-heavy generation. The session gap is the narrowest because Anthropic's 1-hour cache writes cost more than GPT-5.5's writes, which OpenAI bills as ordinary input. Opus 5.5 is Claude Code's default and suits new work, while GPT-5.5 suits API workflows already built on it, since it leaves ChatGPT and Codex sign-in on October 14, 2026.
Choose Claude Opus 5.5 if
- You want lower per-token rates: $4 input, $20 output, and $0.20 per cache hit, against $5, $30, and $0.50.
- Claude Code is your daily tool, and Opus 5.5 is its default model.
- Your work is output-heavy, where the gap reaches 1.5x.
- Your prompts pass 272K input tokens, where GPT-5.5 bills 2x input and 1.5x output for the full session and Opus 5.5 stays at standard rates up to 1M.
Choose GPT-5.5 if
- You have API integrations tuned to GPT-5.5, which stays in the API after October 14, 2026.
- Your caches turn over quickly, since GPT-5.5 adds no charge for writing the cache.
- OpenAI's claims fit your agents: precise tool use on large tool surfaces, and complex coding that needs planning, codebase navigation, and verification.
Side by side
Specs and prices
| Fact | Claude Opus 5.5 | GPT-5.5 |
|---|---|---|
| Maker | Anthropic | OpenAI |
| API model id | claude-opus-5-5 | gpt-5.5 |
| Released | September 22, 2026 | April 23, 2026 |
| Status | Current | Previous generation |
| Context window | 1M tokens | 1.05M tokens |
| Max output | 128K tokens | 128K tokens |
| Open weights | No | No |
| Input, per 1M tokens | $4 | $5 |
| Cache hit, per 1M | $0.20 | $0.50 |
| Cache write, per 1M | $5 (5-minute), $8 (1-hour) | $5 (same as input) |
| Output, per 1M tokens | $20 | $30 |
| Runs in | Claude Code, Cursor, OpenCode, OpenRouter, and GitHub Copilot | Codex, Cursor, OpenCode, OpenRouter, and GitHub Copilot |
Standard API rates in US dollars, as published by each maker (Claude Opus 5.5: September 26, 2026; GPT-5.5: September 28, 2026). Batch and priority tiers, taxes, and subscription plans are not included. Claude Opus 5.5: The full 1M context window is billed at standard rates. Fast mode, a research preview on the Claude API, costs $8 input and $40 output per million tokens. GPT-5.5: Prompts over 272K input tokens cost 2x for input and 1.5x for output, for the full session.
Cost
What the same work costs
The same token counts, priced at each model’s published rates. Cached tokens are billed at each maker’s cache prices, so the session shows what caching is worth on each model.
Real sessions differ: the two models count the same code as different numbers of tokens, and reasoning settings change how much each one writes. Your own history is the real test.
| Workload | Claude Opus 5.5 | GPT-5.5 |
|---|---|---|
| Agentic coding session, 100K input, 400K written to cache, 2M read from cache, 50K output | $4.40 | $5.00 |
| Large one-off review, 150K input with no cache hits, 10K output | $0.80 | $1.05 |
| Output-heavy generation, 30K input, 80K output | $1.72 | $2.55 |
| A month of sessions, 110 sessions: 5 a day, 22 working days | $484.00 | $550.00 |
| Where the session’s cost goes | ||
| Cache writes | $2.60 | $2.00 |
| Cache reads | $0.40 | $1.00 |
| Uncached input | $0.40 | $0.50 |
| Output | $1.00 | $1.50 |
- caching saves on the session with Claude Opus 5.5 (60%)
- $6.60
- caching saves on the session with GPT-5.5 (64%)
- $9.00
Why the cached session is the closest race
Claude Opus 5.5 is cheaper per token on almost every line. Input costs $4 against $5 for GPT-5.5, output $20 against $30, and a cache hit $0.20 against $0.50. Only writes match: Opus 5.5's 5-minute write costs $5, and GPT-5.5 bills written tokens as ordinary input, also $5.
Anthropic's 1-hour write is where Opus 5.5 gives ground. At 2x input it costs $8 per million, so the session's writes total $2.60 on Opus 5.5 against $2.00 on GPT-5.5. Cache reads swing $0.60 back the other way, $0.40 against $1.00, so the two effects cancel and the remaining gap comes from input and output.
The result is a 12% saving on the session, $4.40 against $5.00, or $66.00 over 110 sessions a month. The uncached review shows a 24% saving, $0.80 against $1.05, and output-heavy generation 33%, $1.72 against $2.55, because GPT-5.5's output price is 1.5x that of Opus 5.5.
GPT-5.5 leaves Codex sign-in on October 14, 2026
OpenAI released GPT-5.5 in April 2026 as its flagship for coding and professional work, calling it "A new class of intelligence for coding and professional work." It is now a previous-generation model. On October 14, 2026 it leaves ChatGPT and Codex sign-in, though it stays in the API and is still listed in Cursor, OpenCode, OpenRouter, and GitHub Copilot.
Codex users who sign in with ChatGPT will need another model after that date, and the Codex docs recommend GPT-6 Sol for complex coding. API users can keep calling GPT-5.5, which caches automatically but, unlike GPT-5.6 and later models, accepts no explicit cache breakpoints.
Positioning, effort, and what caching saves
Anthropic released Opus 5.5 on September 22, 2026, calls it its recommended starting model for most work, and says it "costs 40% less to run than Opus 5." It defaults to medium effort, and changing effort keeps the prompt cache. OpenAI says GPT-5.5 reaches strong results with fewer reasoning tokens than earlier models at the same effort.
Caching saves more on GPT-5.5 in this example, $9.00 or 64% of the uncached cost, against $6.60 or 60% on Opus 5.5. That is because GPT-5.5's uncached input is dearer and it pays no write premium, not because its cache is cheaper to use. Tokenizers differ between the makers, and Opus 5.5's counts about 30% more tokens than earlier Claude models for the same text.
EveryToken prices your own Claude Code and Codex history at each maker's API rates, so you can see the real gap on your work before GPT-5.5 leaves Codex sign-in.
Prompt caching
How each maker bills cached tokens
Anthropic
Claude caches a prompt prefix up to a breakpoint. One top-level cache_control field places the breakpoint automatically and moves it as the conversation grows, or you can mark up to 4 blocks yourself. Claude Code manages caching for you.
A 5-minute cache write costs 1.25x the input price and a 1-hour write costs 2x. A cache hit costs 0.1x input on most models, 0.05x on Claude Opus 5.5, and 0.025x on Claude Fable 5.1 and Claude Mythos 5.1. Every hit restarts the cache lifetime at no charge.
Anthropic's rule of thumb: a 5-minute write pays for itself after one cache read, and a 1-hour write after two.
In Claude Code, the main conversation uses the 1-hour cache on a Claude subscription and the 5-minute cache with an API key. Each model has its own cache, so switching models starts over.
Source: Anthropic: Prompt caching
OpenAI
Prompt caching is on by default. From GPT-5.6 on you can also mark up to four explicit cache breakpoints, while GPT-5.5 and earlier cache automatically only.
From GPT-5.6 on, a cache write costs 1.25x the uncached input price and a cache hit costs 0.1x. GPT-5.5 and earlier add no charge for writing the cache: written tokens are billed as ordinary input, and a hit costs 0.1x on the models compared here.
On GPT-5.6 and later, a cached prefix stays reusable for at least 30 minutes after its last use, and caching starts at 1,024 input tokens.
Source: OpenAI: Prompt caching
Your own numbers
See what Claude Opus 5.5 and GPT-5.5 really cost you.
everyaitoken reads your Claude Code, Cursor, OpenCode, OpenRouter, and Codex history on your Mac and prices every request at API rates, with what caching saved or cost. $9 once.
FAQ
Questions
Is Claude Opus 5.5 cheaper than GPT-5.5?
Yes, on every workload here. The example agentic session costs $4.40 against $5.00, the uncached review $0.80 against $1.05, and output-heavy generation $1.72 against $2.55. These are API-equivalent estimates, not subscription prices.
When does GPT-5.5 leave Codex?
It leaves ChatGPT and Codex sign-in on October 14, 2026. It stays available through the OpenAI API after that date.
Does GPT-5.5 charge for cache writes?
No. OpenAI bills tokens written to the cache as ordinary input on GPT-5.5 and earlier, and a hit costs 0.1x input. From GPT-5.6 on, a write costs 1.25x input.
Does GPT-5.5 charge more for prompts over 272K tokens?
OpenAI bills prompts over 272K input tokens at 2x for input and 1.5x for output, for the full session. Claude Opus 5.5 bills its whole 1M context window at standard rates.
Sources
- Anthropic: Pricing
- Anthropic docs: Claude Opus 5.5
- Anthropic: Claude Opus 5.5
- Anthropic docs: Fast mode
- Claude Code docs: Model configuration
- Cursor docs: Claude Opus 5.5
- OpenRouter: Claude Opus 5.5
- OpenCode docs: Zen
- GitHub Docs: Supported AI models in Copilot
- OpenAI: API pricing
- OpenAI docs: GPT-5.5
- OpenAI: Using GPT-5.5
- OpenAI: API changelog
- Codex docs: Models
- Cursor docs: Models and pricing
- OpenRouter: GPT-5.5
- Anthropic: Prompt caching
- OpenAI: Prompt caching