Skip to main content

Helicone

Aggregator

Helicone routes one API key to many upstream providers, so you can switch models without new accounts.

Visit helicone.ai
Models93
Cheapest for
17 models
Serves
3 model types
Visits in September 202676K−10.3%Unique visitors 33K
  1. Apr
  2. May
  3. Jun
  4. Jul
  5. Aug
  6. Sep
Models by type

Models on Helicone

ModelInputOutputvs officialContext
Sonar$1/1MFrom$1/1M-60%—
Claude-Sonnet-3.5Only here$3/1MFrom$15/1M——
GPT-5$1.25/1MFrom$10/1M
from $8 at APIMart
±0%—
GPT OSS 120B$0.04/1MFrom$0.16/1M
from $0.14 at Requesty
+14%—
Kimi K2 Instruct$0.57/1MFrom$2.30/1M
from $1.68 at APIMart
+37%—
Grok 3$3/1MFrom$15/1M——
Kimi K2.5$1.20/1MFrom$1.20/1M
from $0.555 at APIMart
+116%—
Grok-4$3/1MFrom$15/1M
from $14.25 at Jiekou.AI
+5%—
Claude-Haiku-3.5Cheapest$0.80/1MFrom$4/1M——
Gemini 2.5 Pro$1.25/1MFrom$10/1M
from $8 at APIMart
±0%—
GPT-4o (2024-11-20)$2.50/1MFrom$10/1M
from $8 at APIMart
±0%—
GPT OSS 20B$0.05/1MFrom$0.20/1M
from $0.09 at OpenRouter
+122%—
Gemini 2.5 Flash$0.30/1MFrom$2.50/1M
from $2 at APIMart
±0%—
DeepSeek V3$0.27/1MFrom$1/1M
from $0.89 at Deep Infra
+12%—
Llama 4 Maverick$0.15/1MFrom$0.60/1M
from $0.20 at AIHubMix
+200%—
Llama 4 Scout 17B Instruct$0.08/1MFrom$0.30/1M
from $0.20 at AIHubMix
+50%—
GLM-4.7$0.43/1MFrom$1.75/1M
from $1.10 at AIHubMix
-20%—
GLM-4.6$0.45/1MFrom$1.50/1M
from $1.10 at AIHubMix
-32%—
Qwen3 30B A3BCheapest$0.08/1MFrom$0.29/1M——
Llama-3.3-70B-Instruct$0.13/1MFrom$0.39/1M
from $0.32 at Deep Infra
+22%—
Qwen3 Coder 480B A35B InstructCheapest$0.22/1MFrom$0.95/1M——
GPT Image 1Cheapest$6.25/1MFrom$12.50/1M——
Llama 3.1 8B InstructCheapest$0.02/1MFrom$0.05/1M±0%—
Qwen3-Coder 30B-A3B Instruct$0.10/1MFrom$0.30/1M
from $0.27 at DevPass (LLM Gateway)
+11%—
Grok Code Fast 1$0.20/1MFrom$1.50/1M
from $1.43 at Jiekou.AI
+5%—
Qwen3 32B$0.29/1MFrom$0.59/1M
from $0.25 at Hugging Face
+136%—
Gemma 3 12B ITCheapest$0.05/1MFrom$0.10/1M±0%—
GPT Image 1.5$5/1MFrom$10/1M±0%—
Claude Haiku 4.5 (latest)$1/1MFrom$5/1M
from $4 at APIMart
±0%—
Claude Opus 4$15/1MFrom$75/1M——
Claude Opus 4.1$15/1MFrom$75/1M±0%—
Claude Opus 4.5 (latest)$5/1MFrom$25/1M
from $20 at APIMart
±0%—
Claude Opus 4.6Only here$5/1MFrom$25/1M——
Claude Sonnet 4$3/1MFrom$15/1M——
Claude Sonnet 4.5 (latest)$3/1MFrom$15/1M
from $12 at APIMart
±0%—
Claude Sonnet 4.6Only here$3/1MFrom$15/1M——
Claude-Haiku-3$0.25/1MFrom$1.25/1M——
Claude-Sonnet-3.7$3/1MFrom$15/1M——
Deepseek 3.2$0.26/1MFrom$0.40/1M
from $0.308 at APIMart
+30%—
DeepSeek R1 Distill Llama 70BCheapest$0.03/1MFrom$0.13/1M——
DeepSeek Reasoner$0.56/1MFrom$1.68/1M
from $0.28 at Requesty
+500%—
DeepSeek TNG R1T2 ChimeraOnly here$0.30/1MFrom$1.20/1M——
DeepSeek V3.1 Terminus$0.27/1MFrom$1/1M
from $0.95 at Hugging Face
+5%—
ERNIE 4.5 21B A3BCheapest$0.07/1MFrom$0.28/1M±0%—
Gemini 2.5 Flash-Lite$0.10/1MFrom$0.40/1M
from $0.32 at APIMart
±0%—
Gemini 3 Flash Preview$0.50/1MFrom$3/1M
from $1.50 at Vertex
±0%—
Gemini 3 Pro Preview$2/1MFrom$12/1M
from $9.60 at APIMart
+25%—
Gemini 3.1 Flash Lite Preview$0.25/1MFrom$1.50/1M
from $1.20 at APIMart
+25%—
Gemini Pro Latest$2/1MFrom$12/1M
from $6.90 at Kenari
±0%—
Gemma 2 9B ItOnly here$0.01/1MFrom$0.03/1M——

Helicone at a glance

93 models in total: 87 text, 3 image, 3 moderation. The cheapest is Llama Prompt Guard 2 22M at $0.01 /1M. Grok 4 Fast Non Reasoning has the largest context window, 2M tokens. The most searched is Sonar, with about 112K Google searches a month. The newest is OpenAI GPT-5.4, released Mar 5, 2026.