Claude Opus 5.5 vs Gemini 4 Argon: API cost
Short answer: For a 10,000-input / 1,000-output request, Gemini 4 Argon is 2× cheaper than Claude Opus 5.5. Per 1M tokens, Claude Opus 5.5 charges $4 in / $20 out; Gemini 4 Argon charges $2 in / $10 out (checked 2026-11-18). A 2,000-input / 500-output chat call costs $0.0180 on Claude Opus 5.5 and $0.0090 on Gemini 4 Argon.
Nearest-priced models, this workload
Showing the 9 models closest in price; change any input to rank every model.
| Model | Per call | Per 1K calls |
|---|---|---|
| Gemini 3.1 Pro Preview | $0.0100 | $10.00 |
| GPT-5.4 | $0.0125 | $12.50 |
| Claude Sonnet 4.6 | $0.0135 | $13.50 |
| GPT-5.6 Sol | $0.0180 | $18.00 |
| Claude Opus 5.5 | $0.0180 | $18.00 |
| GPT-5.5 Rosalind Research | $0.0225 | $22.50 |
| GPT-5.5 Rosalind Discovery | $0.0225 | $22.50 |
| Claude Opus 5 | $0.0225 | $22.50 |
| GPT-5.5 | $0.0250 | $25.00 |
o4-mini is shut down; its last published list rate is kept for comparing old invoices, not as a model you can call today — the model page names its replacement.
Side by side
| Claude Opus 5.5 | Gemini 4 Argon | |
|---|---|---|
| Input /1M | $4 | $2 |
| Cached /1M | $0.2 | $0.1 |
| Output /1M | $20 | $10 |
| Context window | 1M | 1,048,576 |
| Max output | 128K | 65,536 |
| Knowledge cutoff | Jun 2026 | – |
| Batch input / output | $2 / $10 | $1 / $5 |
| Long-context tier | none listed | none listed |
| Status | Latest | current |
Cost for 1,000 calls
| Workload | Claude Opus 5.5 | Gemini 4 Argon |
|---|---|---|
| Chat · 2K/500 ×1,000 | $18.00 | $9.00 |
| RAG · 20K/1K ×1,000 | $100 | $50.00 |
| RAG, 80% cached ×1,000 | $39.20 | $19.60 |
| RAG via Batch API ×1,000 | $50.00 | $25.00 |
| Generation · 500/4K ×1,000 | $82.00 | $41.00 |
| Long prompt · 300K/4K ×1,000 | $1,280 | $640 |
Which costs less, and when
- For a 10K-in / 1K-out request, Gemini 4 Argon is 2× cheaper than Claude Opus 5.5.
- For output-heavy work (500 in / 4K out), Gemini 4 Argon is cheaper; output costs 5× input on Claude Opus 5.5 and 5× on Gemini 4 Argon.
How each provider positions it
- Claude Opus 5.5 — Anthropic: “For long-running agentic coding and knowledge work.”
- Gemini 4 Argon — Google: “Gemini 4 Argon (gemini-4-argon) is our flagship reasoning model, built for complex software engineering, deep mathematical and scientific problem solving, autonomous multi-step agents, and long decode up to 1M tokens.”
Price is one factor; test quality on your own prompts. Sources: Anthropic pricing, Google pricing, Claude Opus 5.5 docs, Gemini 4 Argon docs (checked 2026-11-18).
Claude Opus 5.5: Cache read 0.05x input
Gemini 4 Argon: Rises to $4/$20 on 2026-12-01
Related
Questions
Which is cheaper, Claude Opus 5.5 or Gemini 4 Argon?
For 10,000 input and 1,000 output tokens, Gemini 4 Argon costs $0.0300 and Claude Opus 5.5 costs $0.0600, so Gemini 4 Argon is about 2× cheaper. For output-heavy work (500 in / 4K out), Gemini 4 Argon is cheaper.
How much do 1,000 calls cost on each?
At 2,000 input / 500 output tokens per call, 1,000 calls cost $18.00 on Claude Opus 5.5 and $9.00 on Gemini 4 Argon. At 20,000 input / 1,000 output, they cost $100 and $50.00.
How do cached input prices compare?
Claude Opus 5.5: $0.2 per 1M cached input tokens. Gemini 4 Argon: $0.1 per 1M cached input tokens.
What does a long-context request cost?
A 100,000-input / 1,000-output request costs $0.4200 on Claude Opus 5.5 and $0.2100 on Gemini 4 Argon at standard rates. Claude Opus 5.5 lists a 1M context window; Gemini 4 Argon lists 1,048,576.
Is there a batch discount, and what should I check before switching?
Batch pricing is published for Claude Opus 5.5, Gemini 4 Argon in our dataset; the provider applies it only to asynchronous batch jobs. Before switching, run your own prompts on both, check the output-token share (output usually dominates the bill) and re-check the prices on the date shown at the bottom of this page.
Which should I pick for a coding agent, Claude Opus 5.5 or Gemini 4 Argon?
On cost alone, a 60,000-token agent context with a 4,000-token answer costs $0.3200 on Claude Opus 5.5 and $0.1600 on Gemini 4 Argon at list rates. Quality decides the rest: test both on the same real tasks and compare cost per completed task, because a model that needs a retry is never the cheaper one.
Next step → Turn this into a monthly budget
Price data last checked 2026-11-18 against official sources · how we verify
Price-change alerts
One short email when a provider changes a price or a promo ends. No spam, unsubscribe any time.