Google: Models Intelligence, Performance & Price
This analysis is intended to support you in choosing the best model provided by Google for your use-case.
Most Intelligent
Updated
Claude Opus 5 (max)Claude Fable 5 (with fallback)Claude Opus 5 (xhigh)Claude Opus 5 (high)Claude Opus 5 (medium)Intelligence index
Total 59 models
Fastest
gpt-oss-20b (high) Vertexgpt-oss-20b (low) VertexGemini 3.5 Flash-Lite AI StudioGemini 2.5 Flash-Lite (AI Studio)Gemini 3.8 Flash (high) AI StudioOutput speed
Total 59 models
Lowest Price
Gemini 2.5 Flash-Lite (AI Studio)Gemini 2.5 Flash-Lite (Non-reasoning) (AI Studio)gpt-oss-20b (low) Vertexgpt-oss-20b (high) Vertexgpt-oss-120b (high) VertexBlended price (per 1M tokens)
Total 59 models
Google offers 59 models, each with different intelligence, performance, and pricing characteristics. Below is a comparison of the key metrics across models.
- For intelligence, the top models on Google are Claude Opus 5 (max) (51), Claude Fable 5 (with fallback) (50), and Claude Opus 5 (xhigh) (50).
- For output speed, the fastest models are gpt-oss-20b (high) Vertex (397 t/s), gpt-oss-20b (low) Vertex (362 t/s), and Gemini 3.5 Flash-Lite AI Studio (358 t/s).
- For latency, Gemini 2.5 Flash-Lite (Non-reasoning) (AI Studio) (0.31s), Gemini 2.5 Flash (Non-reasoning) (AI Studio) (0.44s), and Gemini 2.5 Flash (Non-reasoning) (Vertex) (0.50s) offer the lowest time to first answer token.
- For pricing, Gemini 2.5 Flash-Lite (AI Studio) ($0.07), Gemini 2.5 Flash-Lite (Non-reasoning) (AI Studio) ($0.07), and gpt-oss-20b (low) Vertex ($0.09) offer the lowest blended prices per 1M tokens.
- For context window size, Llama 4 Scout Vertex (1M), Claude Opus 5 (max) (1M), and Claude Fable 5 (with fallback) (1M) support the largest context windows on Google.
Highlights
Intelligence Evaluations
Artificial Analysis Intelligence Index
Intelligence Evaluations
Agentic knowledge work, (Elo-500)/2000
Agentic real-world work tasks, (Elo-500)/2000
Agentic SaaS workflows
Agentic coding & terminal use
Coding
Reasoning & knowledge
Professional document reasoning, All-pass
Physics reasoning
Knowledge
1 - hallucination rate
Long context reasoning
Legal agentic work, criterion pass rate
Agentic business operations
Quantitative analysis on spreadsheets & documents
Agentic tool use
Kubernetes incident root-cause analysis
Visual reasoning
Medical long context reasoning
Intelligence Index vs. Price
Context Window
Context Window
Pricing
Intelligence Index vs. Price
Performance Summary
Output Speed vs. Price
Speed
Measured by Output Speed (tokens per second)
Output Speed
Latency
Measured by Time (seconds) to First Token
Latency: Time To First Answer Token
End-to-End Response Time
Seconds to output 500 tokens, calculated based on time to first token, 'thinking' time for reasoning models, and output speed
End-to-End Response Time vs. Price
Further Analysis | |||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|
Claude Opus 5 (max) | 1M | Proprietary | 51 | $9.38 | 51 | 39.41 | 49.22 | -- | |||
Claude Fable 5 (with fallback) | 1M | Proprietary | 50 | $9.66 | 58 | 80.37 | 88.93 | -- | |||
Claude Opus 5 (xhigh) | 1M | Proprietary | 50 | $7.75 | 51 | 30.69 | 40.55 | -- | |||
Claude Opus 5 (high) | 1M | Proprietary | 48 | $5.64 | 50 | 18.08 | 28.08 | -- | |||
Claude Opus 5 (medium) | 1M | Proprietary | 45 | $3.32 | 49 | 4.86 | 14.97 | -- | |||
Claude Opus 4.8 (max) | 1M | Proprietary | 42 | $5.84 | 58 | 15.42 | 24.09 | -- | |||
Gemini 3.8 Flash (high) AI Studio | 1M | Proprietary | 41 | $1.24 | 299 | 16.09 | 17.76 | -- | |||
Claude Opus 4.7 (max) | 1M | Proprietary | 41* | -- | 63 | 17.20 | 25.17 | -- | |||
Gemini 3.8 Flash (medium) AI Studio | 1M | Proprietary | 40 | $0.93 | -- | -- | -- | -- | |||
Claude Opus 5 (low) | 1M | Proprietary | 40 | $1.57 | 48 | 3.28 | 13.65 | -- | |||
Gemini 3.7 Flash (medium) AI Studio | 1M | Proprietary | 40* | -- | 286 | 4.95 | 6.69 | -- | |||
Gemini 3.7 Flash (high) AI Studio | 1M | Proprietary | 39 | $0.93 | 288 | 11.87 | 13.61 | -- | |||
Claude Sonnet 5 (max) | 1M | Proprietary | 38 | $7.36 | 71 | 178.12 | 185.14 | -- | |||
Gemini 3.7 Flash (low) AI Studio | 1M | Proprietary | 37* | -- | 272 | 0.88 | 2.71 | -- | |||
Gemini 3.6 Flash AI Studio | 1M | Proprietary | 34 | $0.93 | 179 | 16.81 | 19.61 | -- | |||
Gemini 3.8 Flash (low) AI Studio | 1M | Proprietary | 34 | -- | -- | -- | -- | -- | |||
Gemini 3.5 Flash (medium) | 1M | Proprietary | 34* | -- | 201 | 13.34 | 15.83 | -- | |||
Gemini 3.5 Flash AI Studio | 1M | Proprietary | 33 | $1.56 | 208 | 14.93 | 17.34 | -- | |||
Claude Opus 4.6 (max) | 1M | Proprietary | 32* | -- | 40 | 9.27 | 21.72 | -- | |||
Claude Sonnet 4.6 (max) | 200k | Proprietary | 30 | $4.13 | 48 | 123.50 | 133.98 | -- | |||
Gemini 3.1 Pro Preview (AI Studio) | 1M | Proprietary | 30 | $0.67 | 116 | 26.96 | 31.25 | -- | |||
Gemini 3.1 Pro Preview (Vertex) | 1M | Proprietary | 30 | $0.98 | 119 | 26.00 | 30.19 | -- | |||
Claude Opus 4.5 Vertex | 200k | Proprietary | 29* | -- | 45 | 19.16 | 30.32 | -- | |||
Gemini 3 Pro Preview (high) (Vertex) | 1M | Proprietary | 28* | -- | -- | -- | -- | -- | |||
 GLM-5 | 200k | Open | 28* | -- | 76 | 1.43 | 48.93 | 40.92 | |||
Claude Opus 4.6 (Non-reasoning, high) | 1M | Proprietary | 26* | -- | 39 | 2.59 | 15.46 | -- | |||
Gemini 3 Flash (AI Studio) | 1M | Proprietary | 26* | -- | 200 | 6.05 | 8.56 | -- | |||
Claude Sonnet 4.6 (Non-reasoning, high) | 200k | Proprietary | 25* | -- | 44 | 1.96 | 13.34 | -- | |||
Gemini 3.5 Flash (minimal) AI Studio | 1M | Proprietary | 24* | -- | 205 | 0.91 | 3.34 | -- | |||
Claude Opus 4.5 (Non-reasoning) Vertex | 200k | Proprietary | 24* | -- | 44 | 1.11 | 12.41 | -- | |||
Claude 4.1 Opus Vertex | 200k | Proprietary | 23* | -- | -- | -- | -- | -- | |||
Gemini 3.5 Flash-Lite AI Studio | 1M | Proprietary | 23 | $0.12 | 358 | 9.49 | 10.89 | -- | |||
Gemini 3 Pro Preview (low) (Vertex) | 1M | Proprietary | 22* | -- | -- | -- | -- | -- | |||
GLM-4.7 | 200k | Open | 22* | -- | 173 | 0.67 | 15.14 | 11.58 | |||
 Kimi K2 Thinking Vertex | 262k | Open | 22* | -- | 204 | 0.75 | 12.99 | 9.79 | |||
Claude 4.5 Sonnet Vertex | 1M | Proprietary | 21 | $0.53 | 39 | 10.87 | 23.67 | -- | |||
Claude 4 Opus Vertex | 200k | Proprietary | 21* | -- | -- | -- | -- | -- | |||
Claude 4.5 Sonnet (Non-reasoning) Vertex | 1M | Proprietary | 19* | -- | 38 | 1.37 | 14.48 | -- | |||
 MiniMax-M2 Vertex | 197k | Open | 19* | -- | 140 | 0.61 | 18.51 | 14.32 | |||
Claude 4.1 Opus (Non-reasoning) Vertex | 200k | Proprietary | 19* | -- | -- | -- | -- | -- | |||
Gemini 3 Flash (Non-reasoning) (AI Studio) | 1M | Proprietary | 18* | -- | 193 | 0.94 | 3.53 | -- | |||
Claude 4.5 Haiku Vertex | 200k | Proprietary | 18 | $0.24 | 89 | 15.37 | 20.96 | -- | |||
GLM-4.7 (Non-reasoning) | 200k | Open | 17* | -- | 155 | 0.69 | 3.92 | -- | |||
Gemma 4 26B A4B AI Studio | 262k | Open | 17* | -- | 47 | 1.07 | 54.49 | 42.74 | |||
Gemini 2.5 Pro Vertex | 1M | Proprietary | 17 | $0.23 | 108 | 24.26 | 28.87 | -- | |||
Gemini 2.5 Pro (AI Studio) | 1M | Proprietary | 17 | $0.23 | 124 | 23.09 | 27.12 | -- | |||
Claude 4 Opus (Non-reasoning) Vertex | 200k | Proprietary | 17* | -- | -- | -- | -- | -- | |||
Gemini 3.1 Flash-Lite (AI Studio) | 1M | Proprietary | 16 | $0.04 | 281 | 5.39 | 7.17 | -- | |||
Gemma 4 31B (AI Studio) | 262k | Open | 15 | $0.00 | 35 | 1.00 | 64.68 | 49.44 | |||
Claude 4.5 Haiku (Non-reasoning) Vertex | 200k | Proprietary | 15* | -- | 88 | 0.81 | 6.50 | -- | |||
Claude 3.7 Sonnet (Non-reasoning) Vertex | 200k | Proprietary | 15* | -- | -- | -- | -- | -- | |||
Gemini 2.5 Pro (May) (AI Studio) | 1M | Proprietary | 15* | -- | -- | -- | -- | -- | |||
 DeepSeek V3.1 (Non-reasoning) Vertex | 164k | Open | 14* | -- | -- | -- | -- | -- | |||
DeepSeek V3.1 Vertex | 164k | Open | 13* | -- | -- | -- | -- | -- | |||
DeepSeek R1 0528 Vertex | 164k | Open | 13* | -- | 154 | 1.05 | 17.31 | 13.01 | |||
Gemini 2.5 Flash (AI Studio) | 1M | Proprietary | 13* | -- | 223 | 23.47 | 25.71 | -- | |||
Gemini 2.5 Flash (Vertex) | 1M | Proprietary | 13* | -- | 187 | 22.57 | 25.25 | -- | |||
gpt-oss-120b (high) Vertex | 131k | Open | 12 | $0.06 | 170 | 0.64 | 15.31 | 11.73 | |||
 Qwen3 235B 2507 Vertex | 262k | Open | 12* | -- | 92 | 0.77 | 6.23 | -- | |||
Qwen3 Coder 480B Vertex | 262k | Open | 12* | -- | 155 | 0.78 | 4.00 | -- | |||
Qwen3 Next 80B A3B (Reasoning) Vertex | 262k | Open | 11* | -- | 131 | 0.66 | 19.72 | 15.25 | |||
Gemini 2.5 Flash-Lite (Sep) (AI Studio) | 1M | Proprietary | 10* | -- | -- | -- | -- | -- | |||
gpt-oss-120b (low) Vertex | 131k | Open | 10* | -- | 154 | 0.51 | 16.72 | 12.96 | |||
gpt-oss-20b (low) Vertex | 131k | Open | 10* | -- | 362 | 0.32 | 7.23 | 5.52 | |||
Gemini 2.5 Flash (Non-reasoning) (Vertex) | 1M | Proprietary | 10* | -- | 149 | 0.50 | 3.87 | -- | |||
Gemini 2.5 Flash (Non-reasoning) (AI Studio) | 1M | Proprietary | 10* | -- | 198 | 0.44 | 2.97 | -- | |||
Qwen3 Next 80B A3B Vertex | 262k | Open | 10* | -- | 275 | 0.59 | 2.41 | -- | |||
Gemini 2.5 Flash-Lite (Sep) (Non-reasoning) (AI Studio) | 1M | Proprietary | 9* | -- | -- | -- | -- | -- | |||
gpt-oss-20b (high) Vertex | 131k | Open | 9 | $0.01 | 397 | 0.36 | 6.65 | 5.03 | |||
Gemini 2.5 Flash-Lite (AI Studio) | 1M | Proprietary | 9* | -- | 352 | 20.34 | 21.77 | -- | |||
Gemini 2.0 Flash (exp) (AI Studio) | 1M | Proprietary | 8* | -- | -- | -- | -- | -- | |||
 Llama 3.3 70B Vertex | 128k | Open | 8* | -- | 139 | 0.64 | 4.23 | -- | |||
Gemini 2.5 Flash-Lite (Non-reasoning) (AI Studio) | 1M | Proprietary | 7* | -- | 280 | 0.31 | 2.10 | -- | |||
Llama 4 Scout Vertex | 1.31M | Open | 6 | $0.16 | 147 | 0.71 | 4.10 | -- | |||
Gemma 3 27B (AI Studio) | 128k | Open | 5 | $0.00 | -- | -- | -- | -- | |||
Gemma 3 4B (AI Studio) | 128k | Open | 5* | -- | -- | -- | -- | -- | |||
Gemma 3n E2B (AI Studio) | 32k | Open | 5* | -- | -- | -- | -- | -- | |||
Gemma 3 1B (AI Studio) | 32k | Open | 5* | -- | -- | -- | -- | -- | |||
Gemma 3 12B (AI Studio) | 128k | Open | 4 | $0.00 | -- | -- | -- | -- | |||
Key definitions
Frequently Asked Questions
Common questions about Google
Google offers 59 models that we track: Claude Opus 5 (max), Claude Fable 5 (with fallback), Claude Opus 5 (xhigh), Claude Opus 5 (high), Claude Opus 5 (medium), Claude Opus 4.8 (max), Gemini 3.8 Flash (high) AI Studio, Claude Opus 4.7 (max), Claude Opus 5 (low), Gemini 3.7 Flash (medium) AI Studio, Gemini 3.7 Flash (high) AI Studio, Claude Sonnet 5 (max), Gemini 3.7 Flash (low) AI Studio, Gemini 3.6 Flash AI Studio, Gemini 3.5 Flash (medium), Gemini 3.5 Flash AI Studio, Claude Opus 4.6 (max), Claude Sonnet 4.6 (max), Gemini 3.1 Pro Preview (AI Studio), Gemini 3.1 Pro Preview (Vertex), Claude Opus 4.5 Vertex, GLM-5, Claude Opus 4.6 (Non-reasoning, high), Gemini 3 Flash (AI Studio), Claude Sonnet 4.6 (Non-reasoning, high), Gemini 3.5 Flash (minimal) AI Studio, Claude Opus 4.5 (Non-reasoning) Vertex, Gemini 3.5 Flash-Lite AI Studio, GLM-4.7, Kimi K2 Thinking Vertex, Claude 4.5 Sonnet Vertex, Claude 4.5 Sonnet (Non-reasoning) Vertex, MiniMax-M2 Vertex, Gemini 3 Flash (Non-reasoning) (AI Studio), Claude 4.5 Haiku Vertex, GLM-4.7 (Non-reasoning), Gemma 4 26B A4B AI Studio, Gemini 2.5 Pro Vertex, Gemini 2.5 Pro (AI Studio), Gemini 3.1 Flash-Lite (AI Studio), Gemma 4 31B (AI Studio), Claude 4.5 Haiku (Non-reasoning) Vertex, DeepSeek R1 0528 Vertex, Gemini 2.5 Flash (AI Studio), Gemini 2.5 Flash (Vertex), gpt-oss-120b (high) Vertex, Qwen3 235B 2507 Vertex, Qwen3 Coder 480B Vertex, Qwen3 Next 80B A3B (Reasoning) Vertex, gpt-oss-120b (low) Vertex, gpt-oss-20b (low) Vertex, Gemini 2.5 Flash (Non-reasoning) (Vertex), Gemini 2.5 Flash (Non-reasoning) (AI Studio), Qwen3 Next 80B A3B Vertex, gpt-oss-20b (high) Vertex, Gemini 2.5 Flash-Lite (AI Studio), Llama 3.3 70B Vertex, Gemini 2.5 Flash-Lite (Non-reasoning) (AI Studio), and Llama 4 Scout Vertex.
The most intelligent model available on Google is Claude Opus 5 (max) with an Intelligence Index score of 51.
The fastest model on Google by output speed is gpt-oss-20b (high) Vertex at 397.4 tokens per second.
The model with the lowest time to first answer token on Google is Gemini 2.5 Flash-Lite (Non-reasoning) (AI Studio) at 0.31s. Lower latency means faster initial response time.
The most affordable model on Google by blended price is Gemini 2.5 Flash-Lite (AI Studio) at $0.07 per 1M tokens (7:2:1 cache hit/input/output ratio).
Prices on Google vary up to 115x across models, from $0.07 per 1M tokens for Gemini 2.5 Flash-Lite (AI Studio) to $7.70 per 1M tokens for Claude Fable 5 (with fallback).
Yes, Google offers an OpenAI-compatible API, making it easy to switch from OpenAI or use existing OpenAI SDK integrations.
46 of 59 models on Google support JSON mode for structured output.
Yes, all 59 models on Google support function calling (tool use).
Yes, Google offers 43 reasoning models: Claude Opus 5 (max), Claude Fable 5 (with fallback), Claude Opus 5 (xhigh), Claude Opus 5 (high), Claude Opus 5 (medium), Claude Opus 4.8 (max), Gemini 3.8 Flash (high) AI Studio, Claude Opus 4.7 (max), Claude Opus 5 (low), Gemini 3.7 Flash (medium) AI Studio, Gemini 3.7 Flash (high) AI Studio, Claude Sonnet 5 (max), Gemini 3.7 Flash (low) AI Studio, Gemini 3.6 Flash AI Studio, Gemini 3.5 Flash (medium), Gemini 3.5 Flash AI Studio, Claude Opus 4.6 (max), Claude Sonnet 4.6 (max), Gemini 3.1 Pro Preview (AI Studio), Gemini 3.1 Pro Preview (Vertex), Claude Opus 4.5 Vertex, GLM-5, Gemini 3 Flash (AI Studio), Gemini 3.5 Flash-Lite AI Studio, GLM-4.7, Kimi K2 Thinking Vertex, Claude 4.5 Sonnet Vertex, MiniMax-M2 Vertex, Claude 4.5 Haiku Vertex, Gemma 4 26B A4B AI Studio, Gemini 2.5 Pro Vertex, Gemini 2.5 Pro (AI Studio), Gemini 3.1 Flash-Lite (AI Studio), Gemma 4 31B (AI Studio), DeepSeek R1 0528 Vertex, Gemini 2.5 Flash (AI Studio), Gemini 2.5 Flash (Vertex), gpt-oss-120b (high) Vertex, Qwen3 Next 80B A3B (Reasoning) Vertex, gpt-oss-120b (low) Vertex, gpt-oss-20b (low) Vertex, gpt-oss-20b (high) Vertex, and Gemini 2.5 Flash-Lite (AI Studio). Reasoning models use extended thinking to work through complex problems before providing an answer.
Yes, 18 of 59 models on Google are open weight models: GLM-5, GLM-4.7, Kimi K2 Thinking Vertex, MiniMax-M2 Vertex, GLM-4.7 (Non-reasoning), Gemma 4 26B A4B AI Studio, Gemma 4 31B (AI Studio), DeepSeek R1 0528 Vertex, gpt-oss-120b (high) Vertex, Qwen3 235B 2507 Vertex, Qwen3 Coder 480B Vertex, Qwen3 Next 80B A3B (Reasoning) Vertex, gpt-oss-120b (low) Vertex, gpt-oss-20b (low) Vertex, Qwen3 Next 80B A3B Vertex, gpt-oss-20b (high) Vertex, Llama 3.3 70B Vertex, and Llama 4 Scout Vertex.
Yes, provider performance can vary over time due to infrastructure changes, load balancing, and updates. We continuously benchmark all providers and display historical performance trends in the "Over Time" charts.
When choosing a model on Google, consider: intelligence (for quality-sensitive tasks), output speed (for throughput-intensive tasks), latency (for interactive applications requiring quick first responses), pricing (for cost-sensitive workloads), and features like context window size, JSON mode, or function calling support.