Models/Google/Gemini 3.8 Flash

Gemini 3.8 Flash

Gemini 3.8 Flash is the Antigravity default and the Continuum hosted Gemini id. Native spawn is gemini-3.8-flash with effort low, medium, or high. Hosted id is the same bare string.

01

Identity

1,000,000Context in
65,536Context out
2026-09-04Released
ProprietaryWeights
Canonical name
Gemini 3.8 Flash
Aliases
gemini-3.8-flash, continuum/gemini-3.8-flash
Continuum hosted id
gemini-3.8-flash
OpenRouter slug
Not on the 2026-08-19 OpenRouter catalog
Hugging Face
None (closed or unpublished)
Modalities
text, image
Catalog input
$0.75 per million tokens
Catalog output
$3.75 per million tokens
Closed weights Hosted on Continuum Hosted

Closed. Continuum hosts gemini-3.8-flash on the native Antigravity rail and the hosted Continuum rail. Effort variants are low, medium, and high. Gemini 3.5 Flash, 3 Flash, and 3.1 Pro are retired from those pickers.

02

Should I use this for coding agents

Use 3.8 Flash when you want Continuum to spawn Antigravity or serve hosted Gemini. That is the only merchandised Gemini id on those rails.

No independent row for this SKU

No independent board lists this exact SKU as of 2026-08-19.

Closest benchmarked sibling: Gemini 3.7 Flash, 65% ±2% Pass@1 at high on the DeepSWE official board. That is a score for the sibling, not for this SKU.

Boards checked: DeepSWE official (2026-08-13), Artificial Analysis Intelligence Index, vals.ai hero index. Every card that does carry a row is on the coding leaderboard.

DeepSWE

No official DeepSWE mini-swe-agent row for this identity on the public board we fetched.

omitted, not invented as of 2026-08-13 source
Artificial Analysis

No Intelligence Index integer fetched for this identity. Chip omitted.

omitted, not invented as of 2026-08-19 source
Vals Index

We did not open a vals.ai card for this identity. Chip omitted.

omitted, not invented as of 2026-08-19 source

Named benches, printed only

Copied from AA or vals HTML we opened. 0.0% placeholder bars are omitted. Do not average these into the hero tiles, and do not invent CI, $/task, or steps for Artificial Analysis.

BenchPrintedNoteSourceURLAs of
Intro list pair $0.75 / $3.75 per 1M Official Gemini API intro card through 31 December 2026. Cached input $0.075/M. Gemini API pricing source 2026-09-04
Standard list pair $1.50 / $7.50 per 1M Official Gemini API standard card from 1 January 2027. Cached input $0.15/M. Not the live Continuum charge in 2026. Gemini API pricing source 2026-09-04
03

When not to use it

Trust this before you buy

  • Need an OpenRouter week-volume SKU. 3.6 Flash held 2.75T this week and has its own card. 3.7 Flash is the newest OpenRouter Flash. Neither is hosted.
  • Need a historical 3.5 Flash, 3 Flash, or 3.1 Pro session. Those ids still price in analytics. They are not offered for new hosted or Antigravity work.

Plus is $25/mo with $25 weekly hosted usage. The Mac app stays free with your own keys. Get Plus is not Download for Mac.

04

Artifact

Weights

Google does not publish Gemini 3.8 Flash weights. No HF button.

  • Official Gemini API pricing, retrieved 4 Sep 2026: introductory $0.75 / $3.75 per million input / output and $0.075 cached input through 31 December 2026. Standard from 1 January 2027 is $1.50 / $7.50 / $0.15.

What you can open

Lab card and OpenRouter listing only. No Hugging Face Files button, because there is no official repo to point at.

Fetched OpenRouter catalog on 2026-08-19. hugging_face_id was empty.

05

Continuum serving

Continuum hosts gemini-3.8-flash. Antigravity CLI 1.1.26 lists the same id with --effort low|medium|high.

Continuum hosted id gemini-3.8-flash

click to select

We list first-party and OpenRouter, plus Continuum only when the live public allowlist named the id. This is not a 15-host routing table.

06

Economics

Official intro card through 31 December 2026: $0.75 / $3.75 per million, cached input $0.075. That is the Continuum rate card today.

Standard from 1 January 2027 is $1.50 / $7.50 / $0.15. Analytics prices a record by its event time, not by the day you open the chart.

Price this model Opens the pricing calculator preloaded with Gemini 3.8 Flash.
07

Provenance

ClaimSourceAs of
Official intro $0.75 / $3.75 / $0.075 cached per 1M through 2026-12-31; standard $1.50 / $7.50 / $0.15 from 2027-01-01Gemini API pricing2026-09-04
Hosted and Antigravity id gemini-3.8-flash; effort low, medium, highContinuum catalog + agy 1.1.262026-09-04
No base OpenRouter slug on the 2026-08-19 catalog; Hugging Face unlistedOpenRouter /api/v1/models2026-08-19
08

Compare, FAQ, and Get Plus

No other card in this cluster shares a published DeepSWE official row we can put next to this one. We will not compare on vendor-blog numbers.

Continue through Google's model family with Gemini 3.7 Flash.

FAQ

Is this the hosted Flash?

Yes. Continuum hosts gemini-3.8-flash. Gemini 3.5 Flash, 3 Flash, and 3.1 Pro left the hosted and Antigravity pickers.

Why is the price $0.75 and not $1.50?

Google’s intro card holds through 31 December 2026. The $1.50 / $7.50 standard card starts 1 January 2027.

Why does the lab blog disagree with DeepSWE or Scale?

Lab posts pick a harness, an effort, a split, and sometimes a private eval set. DeepSWE publishes the official mini-swe-agent row with cost, tokens, and steps. Scale SWE-bench Pro only counts when the public shared-harness board has a row we can fetch. A higher lab number is usually a different test, not a better one.

OpenAI-compatible call

Verified against the live public allowlist on 2026-08-19. Base URL is https://continuumcode.ai/v1. Keys are cont_sk_ from Settings, Account, Inference API. Personal keys need Plus or above.

curl https://continuumcode.ai/v1/chat/completions \
  -H "Authorization: Bearer $CONTINUUM_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"gemini-3.8-flash","messages":[{"role":"user","content":"Review this diff."}]}'

Plus is $25/mo with $25 weekly hosted usage. The Mac app stays free with your own keys. Get Plus is not Download for Mac.