Comparison
Claude vs Gemini: Anthropic's flagship against Google's
Two very different philosophies: Claude's careful, consistent output versus Gemini's scale and context.
Editorial updated 21 Sept 2026
Source: OpenRouter (live)
Claude and Gemini rarely get compared head to head, which is odd because they are the two flagships most likely to differ on price for a given task. Claude is generally the dearer of the two per token; Gemini compensates with a larger context window and native handling of images, audio and video on input.
For writing, analysis and multi-step coding sessions Claude is usually the more consistent performer. For summarising enormous corpora, processing media, or any workload where you want to put the whole document set in the prompt rather than retrieve chunks, Gemini's context advantage is decisive.
As always the figures below are live and capabilities are as declared on each listing.
Live figures
The numbers
Best value in each row is highlighted. “Not declared” means the provider does not advertise the feature on its listing.
| Attribute | ||
|---|---|---|
| Input priceUSD per 1M tokens | $5.00 | $2.00 (best) |
| Output priceUSD per 1M tokens | $25.00 | $12.00 (best) |
| Blended price75% in / 25% out | $10.00 | $4.50 (best) |
| Vs. market median | 12.5× dearer | 5.6× dearer |
| Value rankcheapest = 1 | #384 | #358 (best) |
| Context windowtokens | 1M | 1.0M (best) |
| Max outputtokens | 128K (best) | 66K |
| Input modalities | text, image, file | audio, file, image, text, video |
| Output modalities | text | text |
| Tool calling | Declared | Declared |
| Reasoning | Declared | Declared |
| Structured output | Declared | Declared |
| Listed on OpenRouter | 2026-07-24 (best) | 2026-02-19 |
Blended price assumes a 3:1 input-to-output token mix. Median is across all 417 priced models.
Add or swap modelsRead-out
What the numbers say
- Google: Gemini 3.1 Pro Preview is the cheapest here at $4.50/M blended — 2.2× less than Anthropic: Claude Opus 5.
- Google: Gemini 3.1 Pro Preview offers the largest context window (1.0M tokens) versus 1M for Anthropic: Claude Opus 5.
Our view
Which should you choose?
- Claude Opus 5
- Choose Claude for consistency in long agentic and writing tasks and when output quality matters more than price.
- Gemini 3.1 Pro Preview
- Choose Gemini for very long context, multimodal input and lower per-token pricing at scale.
Models
Model pages
Full pricing history, capabilities and alternatives for each model in this comparison.
Anthropic
$10.00
/M blended
$4.50
/M blended
More comparisons
Other head-to-heads
- Claude vs GPT-5: which frontier model should you pay for?
Anthropic's flagship Claude against OpenAI's GPT-5 line on price, context and declared capabilities, with live figures.
- Claude Sonnet vs GPT-5 Mini: the mid-tier workhorses
The two models most production apps actually run. How the price gap compares to the capability gap.
- Gemini vs GPT-5: Google's flagship against OpenAI's
Gemini's very long context and multimodal input against GPT-5's ecosystem and pricing.
Newsletter
Stay Ahead of AI
Get the most important developments in artificial intelligence delivered directly to your inbox.
No hype. No spam.
Just trusted insights, major model releases, pricing updates, benchmark changes, product reviews, and practical guidance from across the AI ecosystem.
- Weekly AI Briefing
- Major Model Releases
- Pricing & Benchmark Updates
- Unsubscribe Anytime
The AI HQ Briefing
One email a week. Read in five minutes.