Skip to main content

Helicone

Aggregator

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

PricingDocscontact@helicone.ai
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
GPT-4.1 mini$0.40/1MFrom$1.60/1M
from $1.28 at APIMart
±0%—
GPT-4.1 nano$0.10/1MFrom$0.40/1M
from $0.32 at APIMart
±0%—
GPT-5 Chat LatestCheapest$1.25/1MFrom$10/1M±0%—
GPT-5 Codex$1.25/1MFrom$10/1M
from $8 at APIMart
+25%—
GPT-5 Pro$15/1MFrom$120/1M
from $96 at APIMart
±0%—
GPT-5.1$1.25/1MFrom$10/1M
from $8 at APIMart
±0%—
GPT-5.1 Codex$1.25/1MFrom$10/1M
from $8 at APIMart
+25%—
GPT-5.1 Codex mini$0.25/1MFrom$2/1M
from $1.60 at APIMart
+25%—
GPT-5.1-InstantCheapest$1.25/1MFrom$10/1M±0%—
Grok 3 MiniCheapest$0.30/1MFrom$0.50/1M——
Grok 4 Fast Non ReasoningCheapest$0.20/1MFrom$0.50/1M——
Grok 4 Fast ReasoningCheapest$0.20/1MFrom$0.50/1M——
Grok 4.1 Fast$0.20/1MFrom$0.50/1M
from $0.475 at Jiekou.AI
+5%—
Grok 4.1 Fast (Reasoning)$0.20/1MFrom$0.50/1M
from $0.475 at Jiekou.AI
+5%—
Hermes 2 Pro Llama 3 8BCheapest$0.14/1MFrom$0.14/1M±0%—
Kimi K2 0905Cheapest$0.50/1MFrom$2/1M——
Kimi K2 Thinking$0.48/1MFrom$2/1M
from $1.68 at APIMart
+19%—
Llama Guard 4 12B$0.21/1MFrom$0.21/1M
from $0.18 at Deep Infra
+17%—
Llama Prompt Guard 2 22MCheapest$0.01/1MFrom$0.01/1M——
Mistral-Large$2/1MFrom$6/1M——
Nano Banana Pro$2/1MFrom$12/1M
from $3.50 at Kie.ai
±0%—
O1 Mini$1.10/1MFrom$4.40/1M
from $3.52 at APIMart
+25%—
O3 Pro$20/1MFrom$80/1M
from $64 at APIMart
±0%—
O4 Mini$1.10/1MFrom$4.40/1M
from $3.52 at APIMart
±0%—
OpenAI GPT-4.1$2/1MFrom$8/1M
from $6.40 at APIMart
±0%—
OpenAI GPT-4o mini$0.15/1MFrom$0.60/1M
from $0.48 at APIMart
±0%—
OpenAI GPT-5 Mini$0.25/1MFrom$2/1M
from $1.60 at APIMart
±0%—
OpenAI GPT-5 Nano$0.05/1MFrom$0.40/1M
from $0.32 at APIMart
±0%—
OpenAI GPT-5.2$1.75/1MFrom$14/1M
from $11.20 at APIMart
±0%—
OpenAI GPT-5.2 Pro$21/1MFrom$168/1M
from $134.40 at APIMart
±0%—
OpenAI GPT-5.4$2.50/1MFrom$15/1M
from $12 at APIMart
±0%—
OpenAI o1$15/1MFrom$60/1M
from $48 at APIMart
±0%—
OpenAI o3$2/1MFrom$8/1M
from $6.40 at APIMart
±0%—
OpenAI o3 mini$1.10/1MFrom$4.40/1M
from $3.52 at APIMart
±0%—
Perplexity Sonar Deep Research$2/1MFrom$8/1M——
Prompt Guard 2 86MCheapest$0.01/1MFrom$0.01/1M——
Qwen2.5 Coder 7B fastOnly here$0.03/1MFrom$0.09/1M——
Qwen3 235B A22b Thinking 2507$0.30/1MFrom$2.90/1M
from $2.30 at Hugging Face
+26%—
Qwen3 Next 80B A3B Instruct$0.14/1MFrom$1.40/1M
from $1.10 at Deep Infra
+27%—
Qwen3 VL 235B A22B Instruct$0.30/1MFrom$1.50/1M
from $0.88 at Deep Infra
+70%—
Sonar Pro$3/1MFrom$15/1M——
Sonar ReasoningOnly here$1/1MFrom$5/1M——
Sonar Reasoning Pro$2/1MFrom$8/1M——

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.

Cheapest

  1. Llama Prompt Guard 2 22M$0.01/1M
  2. Prompt Guard 2 86M$0.01/1M
  3. Gemma 2 9B It$0.03/1M
  4. Llama 3.1 8B Instruct$0.05/1M
  5. Qwen2.5 Coder 7B fast$0.09/1M

Largest context

  1. Grok 4 Fast Non Reasoning2M
  2. Grok 4.1 Fast2M
  3. Grok 4.1 Fast (Reasoning)2M
  4. Llama 4 Scout 17B Instruct1.31M
  5. OpenAI GPT-5.41.05M

Most searched

  1. Sonar112K
  2. Claude-Sonnet-3.547K
  3. GPT-535K
  4. GPT OSS 120B35K
  5. Kimi K2 Instruct26K

Newest

  1. OpenAI GPT-5.4Mar 5, 2026
  2. Gemini 3.1 Flash Lite PreviewMar 3, 2026
  3. Gemini 3 Pro PreviewFeb 19, 2026
  4. Gemini Pro LatestFeb 19, 2026
  5. Kimi K2.5Jan 1, 2026