# Claude Haiku 5.5 vs Gemini 3.8 Flash

As of October 21, 2026, Gemini 3.8 Flash costs 650% more per input token than Claude Haiku 5.5 ($0.75 vs $0.10 per 1M) and has a 1,048,576-token context window versus 1,000,000.

- Page: https://models.litellm.ai/compare/claude-haiku-5-5-vs-gemini-3.8-flash
- Claude Haiku 5.5: https://models.litellm.ai/models/claude-haiku-5-5
- Gemini 3.8 Flash: https://models.litellm.ai/models/gemini-3.8-flash

## Side by side

| | Claude Haiku 5.5 | Gemini 3.8 Flash |
|---|---|---|
| Input, per 1M tokens | $0.10 | $0.75 |
| Output, per 1M tokens | $0.50 | $3.75 |
| Cache read, per 1M tokens | $0.01 | $0.075 |
| Cache write, per 1M tokens | $0.125 | – |
| Context window | 1,000,000 tokens | 1,048,576 tokens |
| Max output | 128,000 tokens | 65,536 tokens |
| Image input | Yes | Yes |
| Tool calling | Yes | Yes |
| Structured output (JSON) | Yes | Yes |
| Prompt caching | Yes | Yes |
| Reasoning | Yes | Yes |
| Providers on LiteLLM | 7 | 5 |
| Price shown is from | Anthropic | Google AI Studio |
| Added to LiteLLM | – | September 2, 2026 |

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

## Cheapest provider for each

- Claude Haiku 5.5: Anthropic at $0.10 input per 1M tokens (`claude-haiku-5-5`)
- Gemini 3.8 Flash: Google AI Studio at $0.75 input per 1M tokens (`gemini/gemini-3.8-flash`)

## Benchmark scores

| Benchmark | Claude Haiku 5.5 | Gemini 3.8 Flash |
|---|---|---|
| Epoch Capabilities Index (Overall) | 159.3 | 157.4 |
| FrontierCode (Coding and agents) | 46.4% (max) | 41.2% (medium) |
| FrontierSWE (Coding and agents) | 43.8% (max) | 19.6% (high) |
| APEX-Agents (Coding and agents) | 56.1% (max) | 64.3% |
| GPQA Diamond (Reasoning and knowledge) | 89.6% (max) | 95.4% (high) |
| ARC-AGI-2 (Reasoning and knowledge) | 61.3% (xhigh) | 89.2% (high) |
| SimpleQA Verified (Reasoning and knowledge) | 23.8% (max) | 69.7% (high) |
| FrontierMath (tiers 1-3) (Math) | 75.1% (max) | 68.4% (high) |
| FrontierMath (tier 4) (Math) | 46.3% (max) | 22.0% (high) |
| OTIS Mock AIME 2024-2025 (Math) | 98.9% (xhigh) | 98.9% (high) |

From the Epoch AI Benchmarking Hub (https://epoch.ai/benchmarks), CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/), data as of October 9, 2026: Epoch's own runs and results it collects from each benchmark's leaderboard. Higher is better.

## When to pick which

- Claude Haiku 5.5: Costs 87% less per input token: $0.10 vs $0.75 per 1M.
- Claude Haiku 5.5: Returns up to 128,000 tokens per response, vs 65,536.

## FAQ

### Which is cheaper, Claude Haiku 5.5 or Gemini 3.8 Flash?

Claude Haiku 5.5 is cheaper at 3 input tokens per output token: $0.20 per 1M tokens blended ($0.10 input, $0.50 output), versus $1.50 ($0.75 and $3.75) for Gemini 3.8 Flash, as of October 21, 2026.

### Which has the larger context window, Claude Haiku 5.5 or Gemini 3.8 Flash?

Gemini 3.8 Flash has the larger context window: 1,048,576 tokens, versus 1,000,000 for Claude Haiku 5.5.

### Can I switch from Claude Haiku 5.5 to Gemini 3.8 Flash without changing my code?

Yes. Through LiteLLM both use the OpenAI format, so switching means changing the model name from "claude-haiku-5-5" to "gemini/gemini-3.8-flash", or pointing a LiteLLM gateway model alias at the other model. You can also use one as a fallback for the other.