Gemini 3.8 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.
- Input / output priceUp to 50% off
$1.50 / $7.50$0.75 / $3.75 per 1M- Context
- 1M tokens
- Released
- Sep 2, 2026
Paste into Claude Code, Cursor, or Codex
Help me set up the Respan gateway: fetch and follow https:/
Providers
4 providers, cheapest first, OpenRouter last, priced per 1M tokens after gateway discounts.
| Provider | Input | Output |
|---|---|---|
Concentrate50% off concentrate/gemini-3.8-flash | ||
Google Gemini AI50% off google_gemini_ai/gemini-3.8-flash | ||
Perplexity perplexity/gemini-3.8-flash | $0.75/M | $3.75/M |
OpenRouter openrouter/gemini-3.8-flash | $0.825/M | $4.125/M |
Is a provider down? Perplexity status, OpenRouter status
Pricing
Averaged across 4 providers, in USD per 1M tokens after gateway discounts.
- Average input
- $0.77 per 1M
- Average output
- $3.84 per 1M
- Average cache read
- $0.08 per 1M
- Average cache write
- $0.04 per 1M
Cost by volume
Total cost from 0 to 1T tokens on the cheapest and most expensive provider.
Throughput and latency
30-day averages from requests through the Respan gateway. Under each figure, every model on the gateway by its average, this one in blue.
Output speed
Higher is better78tokens/sacross providers
Time to first token
Lower is better47sacross providers
Response latency
Lower is better6.6sacross providers
Benchmarks
The Respan Index plus 39 published scores from 11 sources, each linked to where it was published.
54.5/ 100
Respan Index#31 of 176
- 31Gemini 3.8 Flash54.5
- 30GPT-5.555.2
- 32Grok 4.653.4
Published scores
| Benchmark | Score | Source | Published |
|---|---|---|---|
| Terminal-bench 2.1Google | 89.4% | Sep 2, 2026 | |
| WeirdMLHåvard Tveit Ihle | 84.8% | Håvard Tveit Ihle | Oct 5, 2026 |
| DeepSWE v1.1Datacurve | 73.8% | Datacurve | Oct 5, 2026 |
| DeepSWE v1.1Google | 73.7% | Sep 2, 2026 | |
| LiveBench CodingLiveBench | 72.5% | LiveBench | Oct 5, 2026 |
| MirrorCodeEpoch AI | 38.9% | Epoch AI | Oct 31, 2026 |
| Terminal-Bench 4.0Vals AI | 19.7% | Vals AI | Oct 13, 2026 |
| FrontierSWE V2Proximal Labs | 19.6% | Proximal Labs | Oct 5, 2026 |
| Terminal-bench 4.0Google | 19.1% | Sep 2, 2026 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| APEX-AgentsMercor | 64.3% | Mercor | Oct 5, 2026 |
| Vals Finance Agent v2Google | 61.4% | Sep 2, 2026 | |
| OSWorld-2.0Google | 59% | Sep 2, 2026 | |
| LiveBench Agentic CodingLiveBench | 54.2% | LiveBench | Oct 5, 2026 |
| Harvey's Legal Agent BenchmarkGoogle | 10% | Sep 2, 2026 | |
| Vending-Bench 2Andon Labs | 5093.79 · #37 of 68 | Andon Labs | Oct 5, 2026 |
| GDPVal-AA v2Google | 1545 Elo · #1 of 4 | Sep 2, 2026 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| GPQA DiamondEpoch AI | 95.4% | Epoch AI | Oct 5, 2026 |
| LiveBench ReasoningLiveBench | 89.3% | LiveBench | Oct 5, 2026 |
| LABBench2Google | 86.2% | Sep 2, 2026 | |
| SimpleBenchSimpleBench | 82.4% | SimpleBench | Sep 3, 2026 |
| Chess PuzzlesEpoch AI | 58% | Epoch AI | Oct 28, 2026 |
| HLE-VerifiedGoogle | 54.9% | Sep 2, 2026 | |
| LiveBench Data AnalysisLiveBench | 54% | LiveBench | Oct 5, 2026 |
| Mystery Game PuzzlesEpoch AI | 47% | Epoch AI | Oct 5, 2026 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| OTIS Mock AIME 2024-2025Epoch AI | 98.9% | Epoch AI | Oct 5, 2026 |
| LiveBench MathematicsLiveBench | 91.6% | LiveBench | Oct 5, 2026 |
| FrontierMath Tiers 1-3 v2Epoch AI | 68.4% | Epoch AI | Oct 5, 2026 |
| FrontierMath Tier 4 v2Epoch AI | 22% | Epoch AI | Oct 5, 2026 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| LiveBench LanguageLiveBench | 87.8% | LiveBench | Oct 5, 2026 |
| LiveBench Instruction FollowingLiveBench | 81.4% | LiveBench | Oct 5, 2026 |
| SimpleQA VerifiedEpoch AI | 69.7% | Epoch AI | Oct 5, 2026 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| CharXiv Reasoning (no tools)Google | 86.2% | Sep 2, 2026 | |
| Furniture AssemblyEpoch AI | 31.7% | Epoch AI | Oct 5, 2026 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| LMArena WebDevLMArena | 1584 Elo · #40 of 124 | LMArena | Nov 19, 2026 |
| LMArena EloLMArena | 1497 Elo · #12 of 191 | LMArena | Nov 19, 2026 |
| LMArena VisionLMArena | 1293 Elo · #10 of 91 | LMArena | Nov 19, 2026 |
| LMArena AgentLMArena | 0.0149 · #25 of 68 | LMArena | Nov 18, 2026 |
How Gemini compares: Claude vs Gemini, Gemini vs GPT, Gemini vs Grok
Compare Gemini 3.8 Flash: Gemini 3.8 Flash vs Gemini 3.7 Flash, Gemini 3.8 Flash vs Claude Sonnet 5.5, Gemini 3.8 Flash vs Claude Sonnet 5, Gemini 3.8 Flash vs Gemini 3.6 Flash, Gemini 3.8 Flash vs DeepSeek V4.1 Flash, Gemini 3.8 Flash vs Claude Haiku 4.5
Apps
Use Gemini 3.8 Flash in the tools you already run. Each guide points the app at the Respan gateway.
Setup guides for more apps are in the integration docs.
Gemini 3.8 Flash FAQ
Short answers, built from the data on this page.
Gemini 3.8 Flash is a model from Google Gemini AI, released on Sep 2, 2026. 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.
On the Respan gateway, Gemini 3.8 Flash costs from $0.75 per 1M input tokens and $3.75 per 1M output tokens on Concentrate, Google Gemini AI, and Perplexity, after gateway discounts. Averaged across its 4 providers, it costs $0.77 per 1M input tokens and $3.84 per 1M output tokens.
Gemini 3.8 Flash is available through 4 providers: Concentrate, Google Gemini AI, Perplexity, and OpenRouter.
Gemini 3.8 Flash accepts up to 1M tokens of context on its largest provider route.
Point any OpenAI-compatible SDK at https://gateway.respan.ai/v1 with your Respan API key and set the model to "google_gemini_ai/gemini-3.8-flash". To set it up with a coding agent, copy the agent setup prompt at the top of this page.
Gemini 3.8 Flash scores 54.5 out of 100 on the Respan Index v1.1, ranking #31 of 176 models. By category: Coding 36.1, Agents 66.7, Reasoning 53.4, Knowledge & language 70.9, and Human preference 56.0. The Respan Index combines independent and lab-reported benchmark results into one score, using benchmark data collected by Respan.
Gemini 3.8 Flash has 39 published benchmark scores, including Terminal-bench 2.1 89.4%, APEX-Agents 64.3%, and GPQA Diamond 95.4%. Each score links to where it was published; the data is collected by Respan.
Certified where it counts.
Built to meet the security and privacy standards that enterprise and healthcare teams require.
ISO 27001
The internationally recognized standard for information security management.
SOC 2
Secure, compliant management of your data across all of our systems.
GDPR
Operated under GDPR, the world's strictest standard for data privacy.
HIPAA
HIPAA compliant, with a BAA available for healthcare teams.