Gemini 4 Argon via the Tokenator API
What the model is for
Gemini 4 Argon is Google's next-generation frontier multimodal reasoning model, developed by Google DeepMind for complex, long-horizon tasks. It delivers advanced capabilities in software engineering, large-scale code analysis, scientific research, enterprise workflows, financial analysis, and cybersecurity. The model supports text, image, and video understanding, deep multi-step reasoning, autonomous workflows, and extended output generation.
Specification
| Full name | Gemini 4 Argon |
| API ID | gemini-4-argon |
| Model vendor | Gemini |
| Type | Text model (chat / completions) |
| Context window | 1.05M tokens |
| Max output | 1M tokens |
| Image input | yes |
| Tokenator usage multiplier | 2.8× |
| Input modalities | text, image |
| Supported API formats | /v1/chat/completions /v1/responses /v1/messages |
| Upstream providers | 1 |
| Current status | available |
| Data updated | 2026-11-11 |
Benchmarks
| Intelligence index | 50.4 |
| Vals Finance Index (Vals AI) | 66% |
| Vals Index (Vals AI) | 69.4% |
| Vals Legal Index (Vals AI) | 76.8% |
| Vals RSI Index (Vals AI) | 30.6% |
| Vals Science Index (Vals AI) | 55.4% |
| Code Migration v1.1 (Vals AI) | 70.8% |
| IOI (Vals AI) | 100% |
| ProgramBench (Vals AI) | 2.5% |
| SWE-bench Multimodal (Vals AI) | 56% |
| Terminal-Bench 4.0 (Vals AI) | 57.6% |
| Vibe Code Bench 1-100 (Vals AI) | 21.2% |
| Vibe Code Bench v1.1 (Vals AI) | 91.9% |
| ProofBench v1.1 (Vals AI) | 99% |
| BioMysteryBench (Vals AI) | 76.3% |
| MysteryMechanism (Vals AI) | 45.5% |
| Robo-bench (Vals AI) | 0.8% |
| Terminal-Bench-Science (Vals AI) | 44.3% |
| EMB v1.1 (Vals AI) | 74.8% |
| Finance Agent v2.1 (Vals AI) | 67.7% |
| Tax Agent Bench (Vals AI) | 49.2% |
| HLAB-Vals-1.1 (Vals AI) | 27.1% |
| Immigration (Vals AI) | 68.1% |
| Legal Research Bench (Vals AI) | 54.8% |
| LegalBench (Vals AI) | 88.3% |
| MedCode (Vals AI) | 58.8% |
| MedScribe (Vals AI) | 87.4% |
| CyberBench v1.1 (Vals AI) | 77.9% |
| SRE Bench (Vals AI) | 44.3% |
| SAGE (Vals AI) | 89.5% |
| Access to Justice (Vals AI) | 68.5% |
| Public Benefits Bench v1.1 (Vals AI) | 69.8% |
Artificial Analysis and Vals AI data loaded into the catalog for this model.
Upstream providers
| Provider | Multiplier |
|---|---|
| AiPartners Ltd | 2.8× |
A request goes to the first available provider by priority; if it fails, Tokenator switches to the next one.
Example request
curl https://api.tokenator.top/v1/chat/completions \ -H "Authorization: Bearer sk-your-tokenator-key" \ -H "Content-Type: application/json" \ -d '{ "model": "gemini-4-argon", "messages": [{"role": "user", "content": "Hello"}] }'
Compatible tools
The model can be used in any tool that accepts a custom base URL: Claude Code, Codex CLI, OpenCode, Cursor, Cline, Kilo Code, Cherry Studio, DeepSeek Harness, Hermes, Pi, OpenClaw.
See also
FAQ about Gemini 4 Argon
What is the API ID of Gemini 4 Argon?
gemini-4-argon — put this into the model field of your request.
What context window does Gemini 4 Argon have?
1.05M tokens; max output is 1M tokens.
How many tokens will a request cost?
(input × 2.8×) + (output × 2.8×). See the documentation for details.
Which tools support this model?
Any tool that accepts a custom base URL: Claude Code, Codex CLI, OpenCode, Cursor, Cline, Kilo Code. Setup guides are in the integrations section.