Google announced Gemini 4 Argon on September 30, 2026. Google announces an output limit of 1M tokens for extended reasoning and generation. This is an output limit, not a confirmed input context window or an EvoLink parameter guarantee. EvoLink access and pricing are not verified; subscribe for a verified API launch update.
We will email you after Google publishes a developer API path and EvoLink verifies the route, returned model identity, usage, pricing, and production behavior.
EvoLink product alerts only. This is not a Google program and not an access guarantee.
Want faster updates? Join the EvoLink Discord
The update will include the verified request model ID, live EvoLink pricing, supported inputs and parameters, access limits, and a migration path that retains a current Gemini fallback.
Google announced Gemini 4 Argon on September 30, 2026. Checked October 1, 2026; announcement, public API access and EvoLink availability are tracked separately.
Initial access is limited to trusted cyber defenders through Google's Fairwind Program. Google plans broader access starting with paid API customers and Google AI Ultra subscribers, but has not given a public rollout date. No Gemini 4 Argon entry or request model ID was found in the public Gemini API catalog or changelog when checked on October 1, 2026.
EvoLink has no Gemini 4 Argon route, SKU, or integration date. Use a listed current Gemini route and keep the future candidate unset until request success, returned identity, usage accounting, and billing are verified.
Initial access is limited to trusted cyber defenders through Google's Fairwind Program. Google plans broader access starting with paid API customers and Google AI Ultra subscribers, but has not given a public rollout date. Google's announced introductory rates are $2 per 1M input tokens and $10 per 1M output tokens. After the introductory period they become $4 and $20 respectively. The end date is not announced. These are Google rates, not an EvoLink quote.
Google positions Argon for software engineering, enterprise knowledge work and cybersecurity defense, and publishes model evaluations. These are provider-reported results, not EvoLink tests or a guarantee for your workload.
No Gemini 4 Argon entry or request model ID was found in the public Gemini API catalog or changelog when checked on October 1, 2026.
This page changes from availability watch to live access only after Google publishes the API contract and EvoLink verifies a successful authenticated request, returned model identity, usage, and billing. A Google announcement alone does not change the EvoLink status.
Google positions Argon for software engineering, enterprise knowledge work and cybersecurity defense, and publishes model evaluations. These are provider-reported results, not EvoLink tests or a guarantee for your workload.
Google announces an output limit of 1M tokens for extended reasoning and generation. This is an output limit, not a confirmed input context window or an EvoLink parameter guarantee. The public API model ID, input limits, supported request parameters, quotas and EvoLink contract remain unverified.
Google announces an output limit of 1M tokens for extended reasoning and generation. This is an output limit, not a confirmed input context window or an EvoLink parameter guarantee.
Google positions Argon for software engineering, enterprise knowledge work and cybersecurity defense, and publishes model evaluations. These are provider-reported results, not EvoLink tests or a guarantee for your workload.
A newer route is valuable only when tokens, retries, latency, fallbacks, and review effort produce better economics for accepted work.
Production adoption needs stable identity, inputs, tools, quotas, error behavior, usage records, and rollback, not a consumer announcement alone.
Prepare evidence, configuration, and rollback paths now so launch-day work is validation instead of a provider-specific rewrite.
Do not hard-code a guessed Gemini 4 Argon identifier. Leave the candidate unset until EvoLink verifies a successful request and returned model identity.
Collect real coding, agent, document, multimodal, tool, and structured-output tasks with objective acceptance criteria.
Record quality, latency, tool errors, token use, retries, review effort, and accepted-task cost for Gemini 3.8 Flash and Gemini 3.1 Pro.
Set thresholds for task success, p95 latency, total cost, incidents, policy behavior, human correction, and rollback.
Capture requested and returned model, parameters, inputs, tools, usage, finish reason, safety blocks, fallback chain, and billing.
Keep a measured current route serving users until the candidate proves a workload-specific improvement under controlled traffic.
Google's announced introductory rates are $2 per 1M input tokens and $10 per 1M output tokens. After the introductory period they become $4 and $20 respectively. The end date is not announced. These are Google rates, not an EvoLink quote.
EvoLink access and pricing are not verified; subscribe for a verified API launch update.
| Field | What is documented | What to verify before integration |
|---|---|---|
| Model ID and variants | Gemini 4 Argon is the announced name. Pro, Flash and Flash-Lite variants are not confirmed by this announcement; a product name is not a request model ID. | The public API model ID, input limits, supported request parameters, quotas and EvoLink contract remain unverified. |
| Standard token price | Google's announced introductory rates are $2 per 1M input tokens and $10 per 1M output tokens. After the introductory period they become $4 and $20 respectively. The end date is not announced. These are Google rates, not an EvoLink quote. | EvoLink access and pricing are not verified; subscribe for a verified API launch update. |
| Batch, caching, and service tiers | Google announces a 95% discount on cached input tokens: $0.10 per 1M at the introductory input rate, calculated as $2 × 5%. | Cache write/storage charges, TTL, eligibility, post-introductory cache terms and gateway support still need a documented API contract. |
| Context and output | Google announces an output limit of 1M tokens for extended reasoning and generation. This is an output limit, not a confirmed input context window or an EvoLink parameter guarantee. | The public API model ID, input limits, supported request parameters, quotas and EvoLink contract remain unverified. |
| Inputs and tools | Gemini 3.x documentation baseline, not Argon specifications: Current endpoints document multimodal inputs, thinking, tools, grounding, and structured output | Supported inputs, function schema, grounding, code execution, streaming, and error contract |
| Quotas and data terms | Limits and data-use rules vary by tier, account, and Google channel | RPS, TPM, concurrency, regions, preview terms, retention, and 429 behavior |
| EvoLink route | Keep a measured current Gemini route as the fallback | Request success, returned identity, usage, capacity, billing, and rollback |
These are the request fields teams should prepare and re-test on launch day. Current Gemini behavior is a compatibility baseline, not a Gemini 4 Argon specification.
The public API model ID, input limits, supported request parameters, quotas and EvoLink contract remain unverified.
| Parameter or field | Current Gemini behavior | Gemini 4 Argon launch-day check |
|---|---|---|
| model | Current endpoints use documented model codes | Exact ID, release stage, aliases, and returned identity |
| contents | Gemini content and part objects | Roles, text, image, audio, video, PDF parts, and validation |
| systemInstruction | Supported by current Gemini generation endpoints | Format, precedence, token accounting, and limits |
| maxOutputTokens | GenerationConfig output ceiling | Google announces an output limit of 1M tokens for extended reasoning and generation. This is an output limit, not a confirmed input context window or an EvoLink parameter guarantee. The public API model ID, input limits, supported request parameters, quotas and EvoLink contract remain unverified. |
| temperature / topP / topK | Sampling controls vary by model and task | Accepted ranges, defaults, interactions, and errors |
| thinkingConfig | Thinking controls are documented for current Gemini 3 models | Supported controls, defaults, token visibility, quality, latency, and cost |
| tools / toolConfig | Function calling and selected built-in tools are model dependent | Schema subset, tool choice, parallel calls, and built-in tool support |
| responseMimeType / responseSchema | Structured output is supported on documented current routes | JSON Schema support, validation, finish reasons, and compatibility |
| cachedContent | Context caching is endpoint and tier dependent | Eligibility, TTL, cache identity, hit accounting, and billing |
| safetySettings | Request safety settings use documented harm categories | Supported categories, thresholds, blocks, and finish reasons |
| streamGenerateContent | Streaming is available on compatible Gemini generation routes | Chunk order, usage delivery, tool events, errors, and cancellation |
| usageMetadata / finishReason | Responses expose token usage and completion state | Field shape, thinking/cache accounting, blocks, and invoice reconciliation |
| Limits and regions | Account, service tier, channel, and region dependent | Context, output, RPS, TPM, concurrency, residency, and 429s |
Keep the candidate unset until EvoLink verifies a successful request and returned model identity. This configuration-only example does not send an API request and does not assume a Gemini 4 Argon model ID.
const activeModel = process.env.EVOLINK_PRIMARY_MODEL
const fallbackModel = process.env.EVOLINK_FALLBACK_MODEL
const gemini4Candidate = process.env.EVOLINK_GEMINI_4_MODEL || null
// Keep the candidate unset until EvoLink verifies a callable route and returned identity.
export const modelRouting = {
activeModel,
fallbackModel,
gemini4Candidate,
}Google develops Gemini; EvoLink's role is to make verified model access easier to compare, operate, switch, and roll back after a route is genuinely callable. Today that means evaluating the current Gemini routes and keeping model selection in configuration.
Keep one integration, key, billing surface, and observability path while model selection changes through configuration.
Publish access only after request success, returned identity, usage, pricing, and billing are validated.
Evaluate the candidate offline and in canary traffic while retaining a current Gemini route as the measured rollback.
Use the release tracker for time-sensitive evidence and the comparison guides for decisions about models you can evaluate today.
Google announced Gemini 4 Argon on September 30, 2026. Initial access is limited to trusted cyber defenders through Google's Fairwind Program. Google plans broader access starting with paid API customers and Google AI Ultra subscribers, but has not given a public rollout date.
For teams already on OpenAI workflows: what to run now, what to adapt, and what Gemini 4 Argon must prove before a shadow test.
For long-running agent teams on Claude: record your context-reuse and recovery baseline, then define what a new route must prove.
Google announced Gemini 4 Argon on September 30, 2026. Initial access is limited to trusted cyber defenders through Google's Fairwind Program. Google plans broader access starting with paid API customers and Google AI Ultra subscribers, but has not given a public rollout date.
Initial access is limited to trusted cyber defenders through Google's Fairwind Program. Google plans broader access starting with paid API customers and Google AI Ultra subscribers, but has not given a public rollout date.
No Gemini 4 Argon entry or request model ID was found in the public Gemini API catalog or changelog when checked on October 1, 2026.
No Gemini 4 Argon entry or request model ID was found in the public Gemini API catalog or changelog when checked on October 1, 2026. gemini-4 is this page's URL slug, not an identifier you can call, and you should not assume the final ID will follow that pattern.
Google's announced introductory rates are $2 per 1M input tokens and $10 per 1M output tokens. After the introductory period they become $4 and $20 respectively. The end date is not announced. These are Google rates, not an EvoLink quote. Google announces a 95% discount on cached input tokens: $0.10 per 1M at the introductory input rate, calculated as $2 × 5%. EvoLink access and pricing are not verified; subscribe for a verified API launch update.
Gemini 4 Argon is the announced name. Pro, Flash and Flash-Lite variants are not confirmed by this announcement; a product name is not a request model ID.
No. Gemma is Google's open-weights model family and is a different product. Gemma 4 downloads, licenses, or self-hosting guides are not evidence about the Gemini 4 Argon API.
Google announces an output limit of 1M tokens for extended reasoning and generation. This is an output limit, not a confirmed input context window or an EvoLink parameter guarantee. The public API model ID, input limits, supported request parameters, quotas and EvoLink contract remain unverified.
EvoLink access and pricing are not verified; subscribe for a verified API launch update.
Review Gemini 3.8 Flash for the current Flash tier or Gemini 3.1 Pro for the current Pro-family baseline, then verify the listed EvoLink route before production.
Prepare a workload-specific comparison now, then run it when an eligible, documented route is available. Preserve your current baseline, acceptance criteria and fallback during replay, shadow and canary stages. The public API release date has not been announced.
Verify the official model ID, price, inputs, context and output limits, tools, thinking controls, streaming, quotas, regions, request success, returned identity, usage, and billing, then promote through replay, shadow, and canary stages with rollback.
Review provider-documented current models and verify each EvoLink route before production. Compare actual Gemini 4 Argon calls only after route verification.
Gemini 3.8 Flash
ListedGoogle's newest listed Flash model, positioned for long-horizon software engineering and agents. Verify the EvoLink route before production.
View model
Gemini 3.1 Pro
ListedThe documented current Pro-family baseline for complex reasoning, coding, tools, and multimodal work. Verify the EvoLink route before production.
View model
Gemini Model Family
CompareCompare current Gemini listings by model access, price, context, production role, and workload fit.
View model