# Claude Sonnet 5 vs GPT-6.2 Sol

As of November 17, 2026, Claude Sonnet 5 and GPT-6.2 Sol cost the same: $2.00 per 1M input tokens and $10.00 per 1M output tokens. Claude Sonnet 5 has the larger context window: 1M tokens versus 922K.

- Page: https://models.litellm.ai/compare/claude-sonnet-5-vs-gpt-6.2-sol
- Claude Sonnet 5: https://models.litellm.ai/models/claude-sonnet-5
- GPT-6.2 Sol: https://models.litellm.ai/models/gpt-6.2-sol

## Side by side

| | Claude Sonnet 5 | GPT-6.2 Sol |
|---|---|---|
| Input, per 1M tokens | $2.00 | $2.00 |
| Output, per 1M tokens | $10.00 | $10.00 |
| Cache read, per 1M tokens | $0.20 | $0.10 |
| Cache write, per 1M tokens | $2.50 | $2.50 |
| Context window | 1,000,000 tokens | 922,000 tokens |
| Max output | 128,000 tokens | 128,000 tokens |
| Image input | Yes | Yes |
| Tool calling | Yes | Yes |
| Structured output (JSON) | Yes | Yes |
| Prompt caching | Yes | Yes |
| Reasoning | Yes | Yes |
| Providers on LiteLLM | 13 | 4 |
| Price shown is from | Anthropic | OpenAI |
| Added to LiteLLM | June 30, 2026 | November 17, 2026 |

Headline prices in USD per 1M tokens, from LiteLLM's model price file.

## Cheapest provider for each

- Claude Sonnet 5: Databricks at $2.00 input per 1M tokens (`databricks/databricks-claude-sonnet-5`)
- GPT-6.2 Sol: OpenAI at $2.00 input per 1M tokens (`gpt-6.2-sol`)

## When to pick which

- Claude Sonnet 5: Available from 13 providers through LiteLLM, vs 4.

## FAQ

### Which is cheaper, Claude Sonnet 5 or GPT-6.2 Sol?

They cost the same: $2.00 per 1M input tokens and $10.00 per 1M output tokens, as of November 17, 2026.

### Which has the larger context window, Claude Sonnet 5 or GPT-6.2 Sol?

Claude Sonnet 5 has the larger context window: 1,000,000 tokens, versus 922,000 for GPT-6.2 Sol.

### Can I switch from Claude Sonnet 5 to GPT-6.2 Sol without changing my code?

Yes. Through LiteLLM both use the OpenAI format, so switching means changing the model name from "claude-sonnet-5" to "gpt-6.2-sol", or pointing a LiteLLM gateway model alias at the other model. You can also use one as a fallback for the other.
