LimitDigest
Home / Compare / AI models / Gemini 4 Hydrogen vs Gemini 3.8 Flash

Gemini 4 Hydrogen vs Gemini 3.8 Flash

Official Google API prices and LMArena scores, checked 2026-11-14. Add up to 2 more models to compare 4.

Verdict

Gemini 3.8 Flash is cheaper and wins more LMArena tasks.

Gemini 3.8 Flash is 2x cheaper on input and output. Gemini 4 Hydrogen scores 43 points higher for coding; Gemini 3.8 Flash scores 37 points higher for reasoning and math. Across 5 shared LMArena tasks, Gemini 3.8 Flash leads 3 to 2. A medium month (20M input + 5M output tokens) costs $67.50 on Gemini 4 Hydrogen and $33.75 on Gemini 3.8 Flash.

  • Pick Gemini 4 Hydrogen if you care most about coding (+43) and creative writing (+5).
  • Pick Gemini 3.8 Flash if you want the lower bill ($33.75 vs $67.50 for a medium month) or you care most about reasoning and math (+37), roleplay (+32) and chat (+11).
Sample month

Medium: 20M input + 5M output tokens a month at list price (short-context rate, no caching or batch discounts).

Gemini 4 HydrogenvsGemini 3.8 Flash
Price per 1M tokens
Input$1.50$0.75 (better)
Cached input$0.075$0.075
Output$7.50$3.75 (better)
Sample month, medium$67.50$33.75 (better)
Context
Context window1M1M
Quality (LMArena relative score, out of 100)
Coding53 (better)10
Chat3546 (better)
Creative writing60 (better)55
Roleplay and characters032 (better)
Reasoning and math3673 (better)
Visionn/a86
Long documentsn/a69
Cheap bulk and agentsn/a27

Marked side is better: lower for prices, higher for context and scores. Bars are scaled to the larger of the two.

Spec
Gemini 4 Hydrogen
Gemini 3.8 Flash
Price per 1M tokens
Input$1.50$0.75
Cached input$0.075$0.075
Output$7.50$3.75
Blend 3:1$3$1.50
Sample month, medium$67.50$33.75
Context
Context window1M tokens1M tokens
Quality (LMArena, out of 100)
Coding53/100 #8 of 5310/100 #29 of 53
Chat35/100 #8 of 5446/100 #6 of 54
Creative writing60/100 #4 of 5455/100 #7 of 54
Roleplay and characters0/100 #19 of 5432/100 #4 of 54
Reasoning and math36/100 #13 of 5273/100 #4 of 52
VisionNot ranked86/100 #3 of 33
Long documentsNot ranked69/100 #8 of 12
Cheap bulk and agentsNot ranked27/100 #17 of 40
Details
ProviderGoogleGoogle
API model idgemini-4-hydrogengemini-3.8-flash
NotesFlat price across the 1M window. Implicit caching only (explicit caching is not supported). No intro promo. Free tier is free of charge and rate-limited.Through Dec 31, 2026. From Jan 1, 2027: $1.50 in, $7.50 out.
Sources
Last checked2026-11-142026-11-14
Official pricingGoogle pricingGoogle pricing

API prices in USD per 1M tokens from each provider's official pricing page. Blend 3:1 = (3 x input + output) / 4. Sample month = stated input and output tokens at the list price, no caching. Quality: relative score out of 100 on each LMArena leaderboard (100 = top model we price on that board, n/a = not ranked there), data licensed CC BY 4.0. See how we pick.

Where each one ranks on LMArena

Relative score out of 100 on each leaderboard (100 = the top model we price there), with the rank among the models from our API price table that appear on that board.

  • Coding (Code Arena): Gemini 4 Hydrogen #8 of 53 (53/100), Gemini 3.8 Flash #29 of 53 (10/100)
  • Chat (Text Arena): Gemini 4 Hydrogen #8 of 54 (35/100), Gemini 3.8 Flash #6 of 54 (46/100)
  • Creative writing (Text Arena creative writing): Gemini 4 Hydrogen #4 of 54 (60/100), Gemini 3.8 Flash #7 of 54 (55/100)
  • Roleplay and characters (Text Arena multi-turn): Gemini 4 Hydrogen #19 of 54 (0/100), Gemini 3.8 Flash #4 of 54 (32/100)
  • Reasoning and math (Text Arena math): Gemini 4 Hydrogen #13 of 52 (36/100), Gemini 3.8 Flash #4 of 52 (73/100)
  • Vision (Vision Arena): Gemini 4 Hydrogen not ranked, Gemini 3.8 Flash #3 of 33 (86/100)
  • Long documents (Document Arena): Gemini 4 Hydrogen not ranked, Gemini 3.8 Flash #8 of 12 (69/100)
  • Cheap bulk and agents (Agent Arena): Gemini 4 Hydrogen not ranked, Gemini 3.8 Flash #17 of 40 (27/100)

Pricing details from the official pages

Gemini 4 Hydrogen lists $1.50 input, $7.50 output, $0.075 cached input per 1M tokens on Google pricing. Gemini 3.8 Flash lists $0.75 input, $3.75 output, $0.075 cached input per 1M tokens on Google pricing. Prices checked 2026-11-14.

  • Gemini 4 Hydrogen: Flat price across the 1M window. Implicit caching only (explicit caching is not supported). No intro promo. Free tier is free of charge and rate-limited.
  • Gemini 3.8 Flash: Through Dec 31, 2026. From Jan 1, 2027: $1.50 in, $7.50 out.

Sample monthly bill at list price, no caching: Light (2M input + 0.5M output tokens): $6.75 vs $3.38. Medium (20M input + 5M output tokens): $67.50 vs $33.75. Heavy (200M input + 50M output tokens): $675 vs $337.50.

FAQ

Is Gemini 4 Hydrogen cheaper than Gemini 3.8 Flash?

Gemini 4 Hydrogen costs $1.50 input and $7.50 output per 1M tokens; Gemini 3.8 Flash costs $0.75 and $3.75. For a medium month (20M input + 5M output tokens) Gemini 3.8 Flash is cheaper: $33.75 vs $67.50.

Which is better for coding, Gemini 4 Hydrogen or Gemini 3.8 Flash?

On LMArena's Code Arena Gemini 4 Hydrogen scores 53/100 (#8 of 53) and Gemini 3.8 Flash 10/100 (#29 of 53), so Gemini 4 Hydrogen is ahead by 43 points.

Which has the bigger context window?

Gemini 4 Hydrogen: 1M tokens. Gemini 3.8 Flash: 1M tokens. Both list the same window.

How much do Gemini 4 Hydrogen and Gemini 3.8 Flash cost per month?

Light (2M input + 0.5M output tokens): $6.75 vs $3.38. Medium (20M input + 5M output tokens): $67.50 vs $33.75. Heavy (200M input + 50M output tokens): $675 vs $337.50. Pick your own token counts in the plan vs API calculator.

Where do these numbers come from?

Prices come from each provider's official pricing page, checked daily. Quality is the relative score on the LMArena leaderboard dataset, licensed CC BY 4.0. Where a model is not ranked we show n/a.

Sources

Related