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.

Prices from LiteLLM's price fileChecked October 21, 2026

Claude Haiku 5.5 vs Gemini 3.8 Flash side by side

Headline prices in US dollars per 1M tokens: each model's own lab where it sells it, otherwise its cheapest provider. Source: LiteLLM model price file, as of October 21, 2026.
	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

Cheapest provider for each

Claude Haiku 5.5: Anthropic at $0.10 input and $0.50 output per 1M tokens (claude-haiku-5-5)
Gemini 3.8 Flash: Google AI Studio at $0.75 input and $3.75 output per 1M tokens (gemini/gemini-3.8-flash)

Benchmark scores

From the Epoch AI Benchmarking Hub (CC BY 4.0), data as of October 9, 2026. Some results were run by Epoch and others collected by Epoch from each benchmark's own leaderboard, linked in the first column. Each model's best reported reasoning setting is shown in brackets. Higher is better. Only benchmarks with a score for both models are shown.
Benchmark	Claude Haiku 5.5	Gemini 3.8 Flash
Overall
Epoch Capabilities Index	159.3	157.4
Coding and agents
FrontierCode	46.4% (max)	41.2% (medium)
FrontierSWE	43.8% (max)	19.6% (high)
APEX-Agents	56.1% (max)	64.3%
Reasoning and knowledge
GPQA Diamond	89.6% (max)	95.4% (high)
ARC-AGI-2	61.3% (xhigh)	89.2% (high)
SimpleQA Verified	23.8% (max)	69.7% (high)
Math
FrontierMath (tiers 1-3)	75.1% (max)	68.4% (high)
FrontierMath (tier 4)	46.3% (max)	22.0% (high)
OTIS Mock AIME 2024-2025	98.9% (xhigh)	98.9% (high)

When to pick which

Pick Claude Haiku 5.5 for

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

From differences in the data above only; where the data is equal, no reason is given.

Call Claude Haiku 5.5 or Gemini 3.8 Flash with LiteLLM

Both use the OpenAI format through LiteLLM, so switching is a model name change. Set each provider's API key in the environment first.

Python SDK

from litellm import completion

messages = [{"role": "user", "content": "Hello!"}]

# Claude Haiku 5.5
response = completion(model="claude-haiku-5-5", messages=messages)

# Gemini 3.8 Flash
response = completion(model="gemini/gemini-3.8-flash", messages=messages)

# Claude Haiku 5.5, falling back to Gemini 3.8 Flash if the call fails
response = completion(model="claude-haiku-5-5", messages=messages, fallbacks=["gemini/gemini-3.8-flash"])

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.