Gemini
- Lowest price / 1M tokens
- $0.75 in · $3.75 out
- Lowest-priced model
- Gemini 3.7 Flash
- Highest-priced model
- Gemini 4 Argon ($10.00 out)
- Largest context
- 1,048,576 tokens
- Also accepts
- audio, file, image, video
- Downloadable weights
- 0 of 6 models
AI brands · Side by side
Gemini vs Claude
Gemini is made by Google and Claude is made by Anthropic. We compare the models behind them through their APIs: the current lineup, price per million tokens, context limits and the inputs each one accepts. Prices checked 13 November 2026.
Claude
- Lowest price / 1M tokens
- $0.10 in · $0.50 out
- Lowest-priced model
- Claude Haiku 5.5
- Highest-priced model
- Claude Fable 5.1 ($50.00 out)
- Largest context
- 1,000,000 tokens
- Also accepts
- file, image
- Downloadable weights
- 0 of 6 models
The short answer
Through the API, Gemini’s lowest-priced current model, Gemini 3.7 Flash, costs $0.75 per million input tokens and $3.75 per million output tokens; Claude’s lowest-priced current model, Claude Haiku 5.5, costs $0.10 per million input tokens and $0.50 per million output tokens. Claude is the cheaper place to start. At the top end, Gemini 4 Argon costs $10.00 per million output tokens and Claude Fable 5.1 costs $50.00 per million output tokens.
Gemini models accept up to 1,048,576 tokens, Claude models accept up to 1,000,000 tokens. The largest limits are about the same. The limit can differ between models in a family, so check the one you plan to use.
Current models, side by side
The newest text models each company lists through the API, with batch and dated snapshot versions left out. Prices are in USD per million tokens.
Gemini models
| Model | Input / 1M | Output / 1M | Context (tokens) | Also accepts | Weights |
|---|---|---|---|---|---|
| Gemini 4 Hydrogen | $1.50 | $7.50 | 1,048,576 | audio, file, image, video | API only |
| Gemini 4 Carbon | $2.00 | $10.00 | 1,048,576 | audio, file, image, video | API only |
| Gemini 4 Argon | $2.00 | $10.00 | 1,048,576 | audio, file, image, video | API only |
| Gemini 3.8 Flash | $0.83 | $4.13 | 1,048,576 | audio, file, image, video | API only |
| Gemini 3.7 Flash | $0.75 | $3.75 | 1,048,576 | audio, file, image, video | API only |
| Gemini 3.6 Flash | $0.75 | $3.75 | 1,048,576 | audio, file, image, video | API only |
Claude models
| Model | Input / 1M | Output / 1M | Context (tokens) | Also accepts | Weights |
|---|---|---|---|---|---|
| Claude Fable 5.2 | $8.00 | $40.00 | 1,000,000 | file, image | API only |
| Claude Haiku 5.5 | $0.10 | $0.50 | 1,000,000 | file, image | API only |
| Claude Sonnet 5.5 | $2.00 | $10.00 | 1,000,000 | file, image | API only |
| Claude Opus 5.5 | $4.00 | $20.00 | 1,000,000 | file, image | API only |
| Claude Fable 5.1 | $10.00 | $50.00 | 1,000,000 | file, image | API only |
| Claude Opus 5 | $5.00 | $25.00 | 1,000,000 | file, image | API only |
What those prices mean in practice
The same token budget for each model. These are calculations, not measured workloads; cache discounts, media, tools and extra reasoning are left out.
Lowest-priced model from each
| Workload | Gemini 3.7 Flash | Claude Haiku 5.5 |
|---|---|---|
| 1,000 short requestsPer request: 2,000 input + 500 output tokens | $3.38 | $0.45 |
| 100 document summariesPer request: 20,000 input + 1,000 output tokens | $1.88 | $0.25 |
| 10 long-document requestsPer request: 300,000 input + 2,000 output tokens | $2.33 | $1.55 |
Highest-priced model from each
| Workload | Gemini 4 Argon | Claude Fable 5.1 |
|---|---|---|
| 1,000 short requestsPer request: 2,000 input + 500 output tokens | $9.00 | $45.00 |
| 100 document summariesPer request: 20,000 input + 1,000 output tokens | $5.00 | $25.00 |
| 10 long-document requestsPer request: 300,000 input + 2,000 output tokens | $6.20 | $31.00 |
Estimate = requests × (input tokens × input price + output tokens × output price) ÷ 1,000,000, using long-prompt rates where the provider lists them.
Common questions
Is Gemini or Claude cheaper?
Through the API, Gemini’s lowest-priced current model, Gemini 3.7 Flash, costs $0.75 per million input tokens and $3.75 per million output tokens; Claude’s lowest-priced current model, Claude Haiku 5.5, costs $0.10 per million input tokens and $0.50 per million output tokens. Claude is the cheaper place to start. At the top end, Gemini 4 Argon costs $10.00 per million output tokens and Claude Fable 5.1 costs $50.00 per million output tokens.
Which has the bigger context window?
Gemini models accept up to 1,048,576 tokens, Claude models accept up to 1,000,000 tokens. The largest limits are about the same. The limit can differ between models in a family, so check the one you plan to use.
Which is better, Gemini or Claude?
It depends on the task. This page compares price, limits and supported inputs from each provider’s API listing; it does not score answer quality. Run the same prompts through the models you are considering. The cost tables show what a test run costs.
Is the Gemini or Claude subscription the same as the API?
No. The chat apps and their subscriptions are billed separately from the API. The prices on this page are API prices per million tokens, which is what you pay when you build the models into your own application.
More AI brand comparisons
Model list and prices come from OpenRouter’s public model catalogue, checked 13 November 2026. Prices set by the developer can change without notice; confirm on the provider’s pricing page before you commit.