Models & Pricing

Compare models

Choose two or three models. Copy the URL to share your selection.

ComparisonGemini 3.6 Flash
gemini-3.6-flash
Choose model 2
TypeChat—
Best forFast, low-cost replies and high-volume everyday tasks—
TokenRex price$0.75 in / $3.75 out per 1M tokens—
Cached input / 1M tokens$0.075 per 1M tokens—
Cache write / 1M tokensNo extra fee—
Cached outputNot offered · standard output rate applies—
Market price$0.75 in / $3.75 out per 1M tokens—
Context window (provider)Not applicable—
Input token limit (provider)1,048,576 tokens—
Maximum output65,536 tokens—
Vendor input modalitiesNot verified—
Vendor output modalitiesNot verified—
TokenRex endpointsPOST /v1/chat/completions—
Benchmarks
Benchmark evidence6 source-linked results—
SWE-Bench Pro
58.7%

Google model-card self-reported score at GA launch, July 21, 2026. Published source text: Model card reports SWE-Bench Pro 58.7%, DeepSWE v1.1 49%, GDPval-AA v2 Elo 1421, and GDM-MRCR v2 91.8% at 128k

Wait Which Model – Gemini 3.6 Flash (citing Google model card)
—
DeepSWE v1.1
49%

DeepSWE v1.1 (Datacurve public leaderboard, highest-scoring thinking level), per Google model card, July 2026 launch. Published source text: in some benchmarks like DeepSWE by Datacurve, we observe up to 65%... all at a lower cost

Google Blog – Introducing Gemini 3.6 Flash, 3.5 Flash-Lite, and 3.5 Flash Cyber
—
GDM-MRCR v2 (128k)
91.8%

Google model-card self-reported score, 128k-token cumulative setting, July 2026 launch. Published source text: GDM-MRCR v2 91.8% at 128k

Wait Which Model – Gemini 3.6 Flash (citing Google model card)
—
OSWorld-Verified (computer use)
83%

Reported from official model card/Google launch materials, July 2026. Published source text: Leads on computer use (83.0% OSWorld-Verified)

Awesome Agents – Gemini 3.6 Flash
—
FrontierCode v1.1 (Extended)
48.02%

Cognition FrontierCode 1.1; Gemini 3.6 Flash; medium effort; chisel harness; Extended subset (150 tasks). Published weighted rubric score (new_score × 100), not the all-or-nothing pass rate; solution-source violations score zero. Source field new_score=0.4802. Publisher evaluation, not a TokenRex measurement; provider effort configuration is not a guarantee of the API's fixed thinking budget.

Cognition · FrontierCode 1.1 original leaderboard
—
FrontierCode v1.1 (Main)
34.37%

Cognition FrontierCode 1.1; Gemini 3.6 Flash; medium effort; chisel harness; Main subset (100 tasks). Published weighted rubric score (new_score × 100), not the all-or-nothing pass rate; solution-source violations score zero. Source field new_score=0.3437. Publisher evaluation, not a TokenRex measurement; provider effort configuration is not a guarantee of the API's fixed thinking budget.

Cognition · FrontierCode 1.1 original leaderboard
—

No overall score, winner or cost-versus-score frontier is calculated without comparable, attributable benchmark evidence. Different test configurations appear separately. Vendor capabilities are distinct from TokenRex API support.

— means no published value or no matching capability. Provider token limits are not tested gateway guarantees; TokenRex media controls and response formats are listed separately.

Gemini 3.6 Flash

Sources and verification

Provider specifications describe the upstream model, not a guarantee of every feature through TokenRex. Prices come from the enabled catalog; benchmark results belong to the exact tested model.

Research notes (1)
  • Published provider limits; maximum-capacity requests have not been independently exercised through TokenRex. Thinking-level variants use the same provider model; reasoning and answer tokens share the output budget.

Popular comparisons

Open the cost calculator →