Claude Haiku 4.5 vs Gemini 3.8 Flash

Pick up to 3 models · pricing, context and capabilities · simulate your product cost

Data updated on September 30, 2026· 217 models

AnthropicHaiku 4.5

Claude Haiku 4.5 is Anthropic’s fastest and most efficient model, delivering near-frontier intelligence at a fraction of the cost and latency of larger Claude models.

View sheet →

Reasoning estimated
Speed estimated
Input
Output
Context
200 K tokens
Max output
64 K
Input, $ per 1M tokens
$1.00
Output, $ per 1M tokens
$5.00
Cache read, $ per 1M
$0.100
Batch (input / output)
$0.500 / $2.50
Tool calling
Yes
Released
10/15/2025
Knowledge cutoff
2025-02-28
API id
anthropic/claude-haiku-4.5
Google3.8 Flash

Gemini 3.8 Flash is Google's most intelligent Flash model with significant gains from 3.7 Flash across software engineering, agentic tasks, and multi-step reasoning.

View sheet →

Reasoning estimated
Speed estimated
Input
Output
Context
▲1 M tokens
Max output
▲66 K
Input, $ per 1M tokens
▲$0.750
Output, $ per 1M tokens
▲$3.75
Cache read, $ per 1M
$0.075
Batch (input / output)
$0.375 / $1.88
Tool calling
Yes
Released
▲09/02/2026
Knowledge cutoff
—
API id
google/gemini-3.8-flash
Third model (optional)
text image audio video PDF / file reasoning (1 to 5, estimated by family) speed (1 to 4, estimated by family)▲ best value among the selected

Which is the better API choice: Claude Haiku 4.5 vs Gemini 3.8 Flash?

  • Gemini 3.8 Flash: cheapest input (25% less than Claude Haiku 4.5)
  • Gemini 3.8 Flash: cheapest output
  • Gemini 3.8 Flash: largest context (1 M)
  • Gemini 3.8 Flash: the newest (09/02/2026)

Gemini 3.8 Flash costs 25% less on input and 25% less on output than Claude Haiku 4.5 ($0.750 / $3.75 versus $1.00 / $5.00 per million tokens). Gemini 3.8 Flash accepts more context (1 M). On capabilities, only Gemini 3.8 Flash accepts audio. Claude Haiku 4.5 and Gemini 3.8 Flash offer a batch tier at half price for jobs that do not need an immediate answer.

What would your product cost?

Estimate the monthly cost with your app's real volume. List prices, no cache or batch discounts.

Claude Haiku 4.5
$35.00/mo
Gemini 3.8 Flash
$26.25/mo

With Gemini 3.8 Flash you save $8.75 a month versus Claude Haiku 4.5 (25% less).

The 6 cheapest for this scenario (chat, last 12 months)

  1. 1Lyria 3 Pro Preview Google$0.00
  2. 2Lyria 3 Clip Preview Google$0.00
  3. 3Qwen3.7 Flash Qwen$0.97
  4. 4DeepSeek V4 Flash 0731 DeepSeek$1.55
  5. 5Ministral 3 3B 2512 Mistral$1.90
  6. 6Qwen3.5-Flash Qwen$2.02

Paste your prompt: tokens and cost per model

Rough estimate (about 4 characters per token). Nothing is sent to any server.

76tokens approx.287 characters

Cost of sending it 1,000 times (input only)

  1. 1Gemini 3.8 Flash Google$0.057
  2. 2Claude Haiku 4.5 Anthropic$0.076
  3. 3Claude Sonnet 5.5 Anthropic$0.152
  4. 4Claude Sonnet 5 Anthropic$0.152
  5. 5Claude Opus 5.5 Anthropic$0.304
  6. 6Claude Opus 5 Anthropic$0.380
  7. 7Claude Fable 5.1 Anthropic$0.760
  8. 8Claude Fable 5 Anthropic$0.760

Popular comparisons

Frequently asked questions

Which is the better API choice: Claude Haiku 4.5 vs Gemini 3.8 Flash?

Gemini 3.8 Flash costs 25% less on input and 25% less on output than Claude Haiku 4.5 ($0.750 / $3.75 versus $1.00 / $5.00 per million tokens). Gemini 3.8 Flash accepts more context (1 M). On capabilities, only Gemini 3.8 Flash accepts audio. Claude Haiku 4.5 and Gemini 3.8 Flash offer a batch tier at half price for jobs that do not need an immediate answer.

Which is cheaper: Claude Haiku 4.5 and Gemini 3.8 Flash?

Gemini 3.8 Flash is cheaper: $0.750 per million input tokens and $3.75 per million output tokens, versus $1.00 / $5.00 for Claude Haiku 4.5.

Which has more context: Claude Haiku 4.5 and Gemini 3.8 Flash?

Gemini 3.8 Flash accepts 1 M tokens of context; Claude Haiku 4.5 accepts 200 K.

Which is newer: Claude Haiku 4.5 and Gemini 3.8 Flash?

Gemini 3.8 Flash was released on 09/02/2026; Claude Haiku 4.5 on 10/15/2025.

What would 10,000 requests a month cost with Claude Haiku 4.5 and Gemini 3.8 Flash?

With 1,500 input and 400 output tokens per request: Claude Haiku 4.5: $35.00; Gemini 3.8 Flash: $26.25 a month, at list price.

Where do the prices come from and how often are they updated?

From the public catalogs of OpenRouter, models.dev and LiteLLM, which publish each provider's list prices. They sync once a day and the last update date is shown above the comparison.

What does price per million tokens mean?

It is what the provider charges per million tokens you send (input) or the model generates (output). A token is roughly 4 characters. Output almost always costs more than input.

Sources: OpenRouter, models.dev and LiteLLM. Prices in USD per million tokens, list price, no volume discounts. Prompt tokens are an estimate; each provider's tokenizer may differ.