The Known Good Updated 25 Jul 2026
Providers· First-party endpoint· 45 tracked models

Google — pricing & performance

Compare models All providers Data sources
Models served
45
of 908 tracked models
Mean output speed
87
tokens per second, averaged over
42 measured endpoints
Mean latency
1.9s
time to first token, averaged over
42 measured endpoints
Cheapest blended
$0.12
per 1M tokens at a 3:1
input:output blend
Output speed on Google

Median output tokens per second for each model this host serves, derived from OpenRouter endpoint telemetry. Higher is better. We do not run these measurements ourselves.

12 of 45 models ▾ ☰⚙⇩ +Add model from specific provider
378
188
176
166
142
140
133
121
120
106
105
101
The Known Good
45 models on Google
Full leaderboard →
Model Creator Input $/M Output $/M Blended Speed TTFT Context
Anthropic: Claude Fable 5 Anthropic $10.00 $50.00 $20.00 48 3.4s 1.00M
Anthropic: Claude Haiku 4.5 Anthropic $1.00 $5.00 $2.00 105 0.5s 200k
Anthropic: Claude Opus 4 Anthropic $15.00 $75.00 $30.00 23 1.6s 200k
Anthropic: Claude Opus 4.1 Anthropic $15.00 $75.00 $30.00 22 1.6s 200k
Anthropic: Claude Opus 4.5 Anthropic $5.00 $25.00 $10.00 44 1.2s 200k
Anthropic: Claude Opus 4.6 Anthropic $5.00 $25.00 $10.00 40 2.0s 1.00M
Anthropic: Claude Opus 4.7 Anthropic $5.00 $25.00 $10.00 70 0.9s 1.00M
Anthropic: Claude Opus 4.8 Anthropic $5.00 $25.00 $10.00 70 1.4s 1.00M
Anthropic: Claude Sonnet 4 Anthropic $3.00 $15.00 $6.00 38 1.1s 1.00M
Anthropic: Claude Sonnet 4.5 Anthropic $3.00 $15.00 $6.00 35 1.5s 1.00M
Anthropic: Claude Sonnet 4.6 Anthropic $3.00 $15.00 $6.00 41 1.4s 1.00M
Anthropic: Claude Sonnet 5 Anthropic $2.00 $10.00 $4.00 106 4.4s 1.00M
Claude Opus 5 Anthropic $5.00 $25.00 $10.00 52 3.0s 1.00M
DeepSeek: DeepSeek V3.1 DeepSeek $0.60 $1.70 $0.88 89 0.8s 164k
DeepSeek: DeepSeek V3.2 DeepSeek $0.56 $1.68 $0.84 23 1.0s 164k
Google: Gemini 2.5 Flash Google $0.30 $2.50 $0.85 176 11.1s 1.05M
Google: Gemini 2.5 Flash Lite Google $0.10 $0.40 $0.17 64 0.4s 1.05M
Google: Gemini 2.5 Pro Google $0.62 $5.00 $1.72 99 1.8s 1.05M
Google: Gemini 2.5 Pro Preview 05-06 Google $0.62 $5.00 $1.72 99 1.8s 1.05M
Google: Gemini 2.5 Pro Preview 06-05 Google $0.62 $5.00 $1.72 99 1.8s 1.05M
Google: Gemini 3 Flash Preview Google $0.25 $1.50 $0.56 85 1.2s 1.05M
Google: Gemini 3.1 Flash Lite Google $0.12 $0.75 $0.28 142 1.5s 1.05M
Google: Gemini 3.1 Pro Preview Google $1.00 $6.00 $2.25 99 2.6s 1.05M
Google: Gemini 3.5 Flash Google $0.75 $4.50 $1.69 121 1.4s 1.05M
Google: Gemini 3.5 Flash Lite Google $0.15 $1.25 $0.42 70 3.0s 1.05M
Google: Gemini 3.6 Flash Google $0.75 $3.75 $1.50 188 1.7s 1.05M
Google: Gemma 4 26B A4B Google $0.15 $0.60 $0.26 59 0.3s 262k
Google: Nano Banana (Gemini 2.5 Flash Image) Google $0.15 $1.25 $0.42 166 6.5s 33k
Google: Nano Banana 2 (Gemini 3.1 Flash Image Preview) Google $0.25 $1.50 $0.56 — — 131k
Google: Nano Banana 2 (Gemini 3.1 Flash Image) Google $0.50 $3.00 $1.12 99 10.5s 131k
Google: Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image) Google $0.25 $1.50 $0.56 378 2.3s 66k
Google: Nano Banana Pro (Gemini 3 Pro Image Preview) Google $1.00 $6.00 $2.25 — — 66k
Google: Nano Banana Pro (Gemini 3 Pro Image) Google $2.00 $12.00 $4.50 67 2.5s 66k
Meta: Llama 3.3 70B Instruct Meta $0.72 $0.72 $0.72 73 0.3s 128k
Meta: Llama 4 Maverick Meta $0.35 $1.15 $0.55 46 0.4s 524k
Meta: Llama 4 Scout Meta $0.25 $0.70 $0.36 53 0.7s 1.31M
MiniMax: MiniMax M2 MiniMax $0.30 $1.20 $0.53 133 0.3s 197k
MoonshotAI: Kimi K2 Thinking Moonshot AI $0.60 $2.50 $1.07 101 0.4s 262k
OpenAI: gpt-oss-120b OpenAI $0.090 $0.36 $0.16 85 0.4s 131k
OpenAI: gpt-oss-20b OpenAI $0.070 $0.25 $0.12 — — 131k
Qwen: Qwen3 235B A22B Instruct 2507 Alibaba $0.22 $0.88 $0.39 49 0.5s 262k
Qwen: Qwen3 Coder 480B A35B Alibaba $0.22 $1.80 $0.61 8 0.5s 262k
Qwen: Qwen3 Next 80B A3B Instruct Alibaba $0.15 $1.20 $0.41 44 0.5s 262k
Qwen: Qwen3 Next 80B A3B Thinking Alibaba $0.15 $1.20 $0.41 120 0.5s 262k
Z.ai: GLM 4.7 Z.ai $0.60 $2.20 $1.00 140 0.4s 200k
The Known Good
Source. Prices, endpoint availability and throughput for Google are ingested from OpenRouter; model metadata is enriched from models.dev. A blank cell means the figure was not published for that endpoint — it never means zero. Blended price is (3 × input + output) ÷ 4, the same 3:1 blend used everywhere on this site; see methodology. Quality scores are not provider-specific: a model scores the same wherever it is hosted, so quality lives on the model pages.