OpenRouter 模型 ↗ · 2026-10-14
google/gemini-4-argon
Model release OpenRouter 模型 Source language: Chinese
OpenRouter 于 2026-10-14 收录该模型(收录时间不等于模型正式发布日期);上下文:1,048,576 tokens;输入价:$2.0000/百万 tokens;输出价:$10.0000/百万 tokens;定位(来源描述):Gemini 4 Argon is Google's flagship reasoning model, built for complex software engineering, deep…
Full text
Google: Gemini 4 Argon
google/gemini-4-argon
Compare
Gemini 4 Argon is Google's flagship reasoning model, built for complex software engineering, deep mathematical and scientific problem solving, and autonomous multi-step agents. Google trained it to keep context across long, multi-step tasks and to turn long documents mixing text, tables, charts and images into a single grounded output. It leads the Vals Index across finance, legal, coding and tax work, and supports long decode of up to 1M output tokens in a single response.
Modalities
In / out price
50% off
$2 / $10per 1M
Context
1.0M
Released
Oct 13, 2026
Compare
Providers
Different companies host the same model. OpenRouter routes your request to one of them based on the routing mode you pick: Balanced (price + speed), Nitro (fastest), or Floor (cheapest).
Latency / throughput
50% off
$4.00$2.00$20.00$10.00$0.20$0.10$0.20$0.104.14s37 tok/s
99.78%
50% off
$4.00$2.00$20.00$10.00$0.20$0.10$0.20$0.108.62s15 tok/s
90.04%
Not used in Standard routing:Why these endpoints are not used
Flex50% off
$2.00$1.00$10.00$5.00$0.10$0.05$0.10$0.055.01s44 tok/s
100.00%
50% off
$4.40$2.20$22.00$11.00$0.22$0.11$0.22$0.114.29s46 tok/s
95.91%
Priority50% off
$7.20$3.60$36.00$18.00$0.36$0.18$0.36$0.185.76s39 tok/s
90.74%
Priority50% off
$7.20$3.60$36.00$18.00$0.36$0.18$0.36$0.185.11s18 tok/s
100.00%
Provider50% offInput / Output /M
Input $2.00 / Output $10.0050% off
37 tok/s99.78% uptime
Input $2.00 / Output $10.0050% off
15 tok/s90.04% uptime
Not used in Standard routing:Why these endpoints are not used
Input $1.00 / Output $5.0050% off
Flex
44 tok/s100.00% uptime
Input $2.20 / Output $11.0050% off
46 tok/s95.91% uptime
Input $3.60 / Output $18.0050% off
Priority
39 tok/s90.74% uptime
Input $3.60 / Output $18.0050% off
Priority
18 tok/s100.00% uptime
Pricing
The average price customers actually pay for this model, next to the prices providers post. Caching and discounts mean the price actually paid is often well below the listed one.
Weighted average
Input
$0.7662/M tokens
Output
$9.697/M tokens
Gemini 4 Argon — Price history
Price history
No effective price data for this selection
$0.745$10.4368.1%75.5%
$0.795$11.4274.7%12.7%
Not used in Standard routing:Why these endpoints are not used
$0.497$11.2983.3%0.3%
Flex
$0.877$5.0914.8%11.4%
Priority
$1.359$20.6472.8%0.1%
Priority
$2.209$18.0240.7%0.0%
ProviderInput / Output /M
Token share
Effective in $0.745 / Effective out $10.43
Token share
75.5%
Effective in $0.795 / Effective out $11.42
Token share
12.7%
Not used in Standard routing:Why these endpoints are not used
Effective in $0.497 / Effective out $11.29
Token share
0.3%
Effective in $0.877 / Effective out $5.09
FlexToken share
11.4%
Effective in $1.359 / Effective out $20.64
PriorityToken share
0.1%
Effective in $2.209 / Effective out $18.02
PriorityToken share
0.0%
Performance
Throughput is how fast the model writes (tokens per second — higher is better). Latency is total round-trip time (lower is better). TTFT is time-to-first-token — how long before you see anything appear (lower is better).
Throughput
46tok/s
P50, best across providers
Latency
4.14s
P50, best provider
Reasoning effortLatency / throughput
Uptime
Uptime is the percentage of the past 3 days that at least one provider was responding to requests. Availability is the percentage of time that inference was successfully served. OpenRouter continuously monitors and uses the next-best provider when one returns an error.
Uptime (3d)The model was reachable. Request routed to a provider.
100.00%
Availability (3d)The model returned inference from any provider. Errors and empty responses count against it.
99.77%
Availability over the last 3 days
Last 72 hours
Availability 99.77%
3 Days Ago2 Days AgoYesterdayNow
Availability over the last 24 hours
OpenRouter Availability
99.76%
Without Routing
97.49%
When an error occurs in an upstream provider, we can recover by routing to another healthy provider, if your request filters allow it. You can access per-provider uptime data programmatically through the Endpoints API. Learn more about our load balancing and provider routing options.
Benchmarks
Scores on standardized evaluations and this model’s own outputs on shared benchmark prompts. Higher percentages are better — and each rank shows where this model lands among the models evaluated on that source.
Benchmark score summary for Google: Gemini 4 Argon (Artificial Analysis, Design Arena and Vals AI)
SourceBenchmarkScore
Artificial AnalysisGemini 4 Argon (High) Intelligence Index50.4
Artificial AnalysisGemini 4 Argon (High) HLE57.1%
Artificial AnalysisGemini 4 Argon (High) AA-LCR79.7%
Artificial AnalysisGemini 4 Argon (High) GDPval-AA56.7%
Artificial AnalysisGemini 4 Argon (High) CritPt27.1%
Artificial AnalysisGemini 4 Argon (High) SciCode61.8%
Artificial AnalysisGemini 4 Argon (High) Terminal-Bench 4.057.1%
Artificial AnalysisGemini 4 Argon (High) AA-Omniscience Accuracy48.3%
Artificial AnalysisGemini 4 Argon (High) AA-Omniscience Non-Hallucination Rate95.7%
Design ArenaGemini 4 Argon Agents Arena Agenticgamedev Elo1264
Design ArenaGemini 4 Argon Agents Arena Blender3d Elo1370
Design ArenaGemini 4 Argon Agents Arena Pdf Elo1251
Design ArenaGemini 4 Argon Agents Arena Spreadsheet Elo1159
Design ArenaGemini 4 Argon Agents Arena Webapps Elo1283
Design ArenaGemini 4 Argon Models Arena 3D Elo1353
Design ArenaGemini 4 Argon Models Arena Code Categories Elo1326
Design ArenaGemini 4 Argon Models Arena Data Visualization Elo1327
Design ArenaGemini 4 Argon Models Arena Game Development Elo1361
Design ArenaGemini 4 Argon Models Arena SVG Elo1340
Design ArenaGemini 4 Argon Models Arena UI Component Elo1331
Design ArenaGemini 4 Argon Models Arena Website Elo1316
Vals AIGemini 4 Argon Access to Justice Benchmark68.5%
Vals AIGemini 4 Argon BioMysteryBench76.3%
Vals AIGemini 4 Argon Code Migration v1.170.8%
Vals AIGemini 4 Argon CyberBench v1.177.9%
Vals AIGemini 4 Argon EMB v1.174.8%
Vals AIGemini 4 Argon Finance Agent v2.167.7%
Vals AIGemini 4 Argon Vals Finance Index66.0%
Vals AIGemini 4 Argon Financial Coaching Bench73.1%
Vals AIGemini 4 Argon HLAB-Vals-1.127.1%
Vals AIGemini 4 Argon Immigration68.1%
Vals AIGemini 4 Argon IOI100.0%
Vals AIGemini 4 Argon LegalBench88.3%
Vals AIGemini 4 Argon Vals Legal Index76.8%
Vals AIGemini 4 Argon Legal Research Bench54.8%
Vals AIGemini 4 Argon MedCode58.8%
Vals AIGemini 4 Argon MedScribe87.4%
Vals AIGemini 4 Argon MysteryMechanism45.5%
Vals AIGemini 4 Argon ProgramBench2.5%
Vals AIGemini 4 Argon ProofBench v1.199.0%
Vals AIGemini 4 Argon Public Benefits Bench v1.169.8%
Vals AIGemini 4 Argon Robo-bench0.8%
Vals AIGemini 4 Argon Vals RSI Index30.6%
Vals AIGemini 4 Argon SAGE89.5%
Vals AIGemini 4 Argon Vals Science Index55.4%
Vals AIGemini 4 Argon SRE Bench44.3%
Vals AIGemini 4 Argon SWE-bench Multimodal56.0%
Vals AIGemini 4 Argon Tax Agent Bench49.2%
Vals AIGemini 4 Argon Terminal-Bench 4.057.6%
Vals AIGemini 4 Argon Terminal-Bench-Science44.3%
Vals AIGemini 4 Argon Vals Index69.4%
Vals AIGemini 4 Argon Vibe Code Bench 1-10021.2%
Vals AIGemini 4 Argon Vibe Code Bench v1.191.9%
Apps
Public apps that send the most traffic to this model. Good signal for what real production workloads look like — and a hint at which use cases this model is best suited for.
1.
Hermes Agent
Hermes Agent is an open-source, self-improving AI agent by Nous Research that runs persistently with memory across sessions, and builds reusable skills from experience. It comes with 40+ built-in tools, including web search, browser automation, and vision, plus scheduled automations and subagents.
465Btokens
2.
Claude Code
Claude Code is Anthropic's agentic coding tool that reads your entire codebase, plans and executes changes across files, runs tests, and iterates on failures, all from natural language prompts.
245Btokens
3.
omp
new
158Btokens
4.
pi
There are many coding agents, but this one is yours.
116Btokens
5.
Brandon asks offline replay
new
85Btokens
Rest of OpenRouter
67.4B
Top 5 Apps
20.5B
Activity
Token volume and request traffic to this model over time.
API
Drop-in code to call this model. OpenRouter's API is OpenAI-compatible — most SDKs work by just swapping the base URL. The only thing that changes between models is the model slug below.
Google: Gemini Pro versions
Not currently available through EU in-region routing. In-region routing docs
Documentation
Guides, cookbooks, blog posts, and tools for building with Google: Gemini 4 Argon on OpenRouter.
Gemini 4 Migration GuideCookbook
Frequently asked questions
Gemini 4 Argon is Google's flagship reasoning model, built for complex software engineering, deep mathematical and scientific problem solving, and autonomous multi-step agents. Google trained it to keep context across long, multi-step tasks and to turn long documents mixing text, tables, charts and images into a single grounded output.
The Gemini 4 Argon documentation on OpenRouter includes the Gemini 4 Migration Guide cookbook. The quickstart covers API keys and your first request, and the API reference lists every parameter.
Gemini 4 Argon costs $2.00/M input tokens and $10.00/M output tokens, with separate rates for Cache Read at $0.10/M tokens, Cache Write at $0.1875/M tokens, Image Input at $2.00/M tokens, Input Audio at $2.00/M tokens, Input Audio Cache at $0.10/M tokens, and Web Search at $14.00/1K calls.
Gemini 4 Argon has a 1,048,576 token context window. It supports up to 1,048,576 completion tokens.
Yes. Gemini 4 Argon accepts tools and tool_choice for function calling. It also supports structured outputs via a JSON schema in response_format.
Gemini 4 Argon accepts audio, files such as PDFs, images, text, and video as input and returns text.
Gemini 4 Argon is served by 2 providers on OpenRouter: Google AI Studio and Google Vertex. Requests are routed to the best available provider, with automatic failover to the others, and you can pin or exclude providers with provider routing.
Gemini 4 Argon was released on October 13, 2026.