Compare · 2026
ChatGPT vs Claude vs Gemini
ChatGPT, Claude, and Gemini are product names; the bill is the API tier. GPT-5.6 Sol is $5 in / $30 out; Claude Opus 5 is $5 / $25; Gemini 3.7 Flash is $0.75 / $3.75. GPT-5.6 Luna is the cheap ChatGPT API path at $0.20 / $1.20. The cheaper Flash/Luna tiers win for volume work. Unverified fields stay labelled.
Last verified:Newest vendor-page check on these five catalog rows.
| Brand people search | Catalog row | Tier | API price / 1M | DeepSWE | Context |
|---|---|---|---|---|---|
| ChatGPT / OpenAI API |  GPT-5.6 Sol | Frontier | $5 in / $30 out | 73% · $8.39/task | 1.05M context · 128K max out |
| ChatGPT / OpenAI API | GPT-5.6 Luna | Budget | $0.20 in / $1.20 out | 67% · $3.03/task | 1.05M context · 128K max out |
| Claude |  Claude Opus 5 | Frontier | $5 in / $25 out | 74% · $11.84/task | 1M context · 128K max out |
| Gemini |  Gemini 3.7 Flash | Budget | $0.75 in / $3.75 out | 65% · $2.18/task | 1.05M context · 66K max out |
| Gemini | Gemini 3.1 Pro | Frontier | $2 in / $12 out | 12% · $2.14/task | 1.05M context · 66K max out |
ChatGPT Plus / Pro subscription dollars are not in this API catalog, so they are not quoted. Gemini 3.7 Flash: Introductory paid-tier rates through 2026-12-31. From 2027-01-01 the standard paid rates are $1.50 / $7.50 per million tokens (Gemini API pricing). Cache is $0.075 / MTok through 2026-12-31, then $0.15. Wire calls to `gemini-3.7-flash`. Thinking levels are `low` / `medium` / `high` (API default medium; no MINIMAL).
When the cheaper one wins
GPT-5.6 Luna is cheaper on output at $1.20 per million tokens against $30 for GPT-5.6 Sol — about 25×. Use the cheaper tier for classification, extraction, summarisation, and any task where the expensive model’s extra score does not change the accepted output. The expensive one only pays if your hardest task actually fails on the cheap tier. On DeepSWE 1.1, GPT-5.6 Luna is 67% Pass@1 at $3.03/task versus GPT-5.6 Sol at 73% / $8.39/task. These are standard-tier API rates, excluding batch and cache discounts.
Run the model pickerChatGPT
Claude
Gemini
AI Model Picker is a free, no-signup tool that shortlists frontier, balanced, or budget models from live API prices and context windows.
Common questions
ChatGPT vs Claude vs Gemini
Answered from the verified figures on this page rather than general guidance.
ChatGPT vs Claude vs Gemini — which is best in 2026?
ChatGPT, Claude, and Gemini are product names; the bill is the API tier. GPT-5.6 Sol is $5 in / $30 out; Claude Opus 5 is $5 / $25; Gemini 3.7 Flash is $0.75 / $3.75. GPT-5.6 Luna is the cheap ChatGPT API path at $0.20 / $1.20. The cheaper Flash/Luna tiers win for volume work. Unverified fields stay labelled.
Which is cheaper, ChatGPT, Claude, or Gemini?
On standard API output rates in this catalog: GPT-5.6 Luna $1.20, Gemini 3.7 Flash $3.75, Claude Opus 5 $25, GPT-5.6 Sol $30. ChatGPT consumer plan prices are not in this API catalog, so they stay unquoted.
Which is best for coding?
Claude Opus 5 is DeepSWE 74% Pass@1 at $11.84/task. GPT-5.6 Sol is DeepSWE 73% Pass@1 at $8.39/task. Gemini 3.7 Flash is DeepSWE 65% Pass@1 at $2.18/task. Gemini 3.1 Pro is DeepSWE 12% Pass@1 at $2.14/task. Use DeepSWE cost per task alongside Pass@1; a few points behind at a fraction of the $/task is often the better build.
When does the cheaper model win?
GPT-5.6 Luna is cheaper on output at $1.20 per million tokens against $30 for GPT-5.6 Sol — about 25×. Use the cheaper tier for classification, extraction, summarisation, and any task where the expensive model’s extra score does not change the accepted output. The expensive one only pays if your hardest task actually fails on the cheap tier. On DeepSWE 1.1, GPT-5.6 Luna is 67% Pass@1 at $3.03/task versus GPT-5.6 Sol at 73% / $8.39/task. These are standard-tier API rates, excluding batch and cache discounts.