Helicone

Aggregatornot counted in provider totals

Pricing page ↗ Helicone's own price list, link checked 2026-10-19. Check the prices below against it.

3 subscription plans from this gateway (flat fees, separate from the per-token prices below)

Endpoints
85
Models
85

Gateway pricing

Models carried
85
Exclusive
6
Median vs direct
±0% list input price vs direct, across 75 priced models

FEES

Inference markup
0%
Billing unit
per token
Notes
Credit purchase fee not stated on pages found.
  • Inference markup “You pay exactly what providers charge (0% markup)”, read 2026-10-11
  • Routing notes “Routes to the cheapest provider first. Equal-cost providers are load balanced.”, read 2026-10-11

Subscription plans

Hand-curated flat fees, not per-token prices.

PlanTierPriceAPI accessVerified
Helicone HobbyFreeFree2026-10-11
Helicone ProStandard$79 / month2026-10-11
Helicone TeamTeam$799 / month2026-10-11

Filter and compare these plans

Models served

85 shown

ModelCreatorTypeIn $/1MOut $/1Mvs directContextMax outputToolsRegion
Baidu Ernie 4.5 21B A3B Thinking
ernie-4.5-21b-a3b-thinking
BaiduChat$0.07$0.28±0%128K8KRegion not stated
ChatGPT-4o
chatgpt-4o-latest
OpenAIChat$5.00$20±0%128K16.4KRegion not stated
Claude 3.5 Sonnet v2
claude-3.5-sonnet-v2
AnthropicChat$3.00$15—200K8.2KRegion not stated
Claude Haiku 3
claude-3-haiku-20240307
AnthropicChat$0.25$1.25±0%200K4.1KRegion not stated
Claude Haiku 3.5
claude-3.5-haiku
AnthropicChat$0.80$4.00±0%200K8.2KRegion not stated
Claude Haiku 4.5
claude-4.5-haiku
AnthropicChat$1.00$5.00±0%200K8.2KRegion not stated
Claude Opus 4
claude-opus-4
AnthropicChat$15$75±0%200K32KRegion not stated
Claude Opus 4.1
claude-opus-4-1
AnthropicChat$15$75±0%200K32KRegion not stated
Claude Opus 4.5
claude-4.5-opus
AnthropicChat$5.00$25±0%200K64KRegion not stated
Claude Sonnet 3.7
claude-3.7-sonnet
AnthropicChat$3.00$15±0%200K64KRegion not stated
Claude Sonnet 4
claude-sonnet-4
AnthropicChat$3.00$15±0%200K64KRegion not stated
Claude Sonnet 4.5
claude-4.5-sonnet
AnthropicChat$3.00$15±0%200K64KRegion not stated
DeepSeek R1
deepseek-reasoner
DeepSeekChat$0.56$1.68+195%128K64KRegion not stated
DeepSeek R1 Distill Llama 70B
deepseek-r1-distill-llama-70b
DeepSeekChat$0.03$0.13−96%128K4.1KRegion not stated
DeepSeek TNG R1T2 Chimera
deepseek-tng-r1t2-chimera
DeepSeekChat$0.30$1.20—130K164KRegion not stated
DeepSeek V3
deepseek-v3
DeepSeekChat$0.56$1.68+75%128K8.2KRegion not stated
deepseek-v3.1-terminus
deepseek-v3.1-terminus
DeepSeekChat$0.27$1.00±0%128K16.4KRegion not stated
deepseek-v3.2
deepseek-v3.2
DeepSeekChat$0.27$0.41−10%164K65.5KRegion not stated
Gemini 2.5 Flash
gemini-2.5-flash
GoogleChat$0.30$2.50±0%1.05M65.5KRegion not stated
Gemini 2.5 Flash-Lite
gemini-2.5-flash-lite
GoogleChat$0.10$0.40±0%1.05M65.5KRegion not stated
Gemini 2.5 Pro
gemini-2.5-pro
GoogleChat$1.25$10±0%1.05M65.5KRegion not stated
Gemini 3 Pro Preview
gemini-3-pro-preview
GoogleChat$2.00$12±0%1.05M65.5KRegion not stated
Gemma 3 12B IT
gemma-3-12b-it
GoogleChat$0.05$0.10−16%131K8.2KRegion not stated
GLM-4.6
glm-4.6
Z.ai (Zhipu AI)Chat$0.45$1.50−18%205K131KRegion not stated
Google Gemma 2
gemma2-9b-it
GoogleChat$0.01$0.03−93%8.2K8.2KRegion not stated
GPT OSS 20B
gpt-oss-20b
OpenAIChat$0.05$0.20±0%131K131KRegion not stated
GPT-4.1
gpt-4.1
OpenAIChat$2.00$8.00±0%1.05M32.8KRegion not stated
GPT-4.1 mini
gpt-4.1-mini
OpenAIChat$0.40$1.60±0%1.05M32.8KRegion not stated
GPT-4.1 nano
gpt-4.1-nano
OpenAIChat$0.10$0.40±0%1.05M32.8KRegion not stated
GPT-4o
gpt-4o
OpenAIChat$2.50$10±0%128K16.4KRegion not stated
GPT-4o mini
gpt-4o-mini
OpenAIChat$0.15$0.60±0%128K16.4KRegion not stated
GPT-5
gpt-5
OpenAIChat$1.25$10±0%400K128KRegion not stated
GPT-5 Mini
gpt-5-mini
OpenAIChat$0.25$2.00±0%400K128KRegion not stated
GPT-5 Nano
gpt-5-nano
OpenAIChat$0.05$0.40±0%400K128KRegion not stated
GPT-5 Pro
gpt-5-pro
OpenAIChat$15$120±0%128K32.8KRegion not stated
GPT-5-Chat
gpt-5-chat-latest
OpenAIChat$1.25$10—128K16.4KRegion not stated
GPT-5-Codex
gpt-5-codex
OpenAIChat$1.25$10±0%400K128KRegion not stated
GPT-5.1
gpt-5.1
OpenAIChat$1.25$10±0%400K128KRegion not stated
GPT-5.1 Codex
gpt-5.1-codex
OpenAIChat$1.25$10±0%400K128KRegion not stated
GPT-5.1 Codex Mini
gpt-5.1-codex-mini
OpenAIChat$0.25$2.00±0%400K128KRegion not stated
GPT-OSS 120B
gpt-oss-120b
OpenAIChat$0.04$0.16−73%131K131KRegion not stated
Grok 3
grok-3
xAIChat$3.00$15±0%131K131KRegion not stated
Grok 3 Mini
grok-3-mini
xAIChat$0.30$0.50±0%131K131KRegion not stated
Grok 4
grok-4
xAIChat$3.00$15±0%256K256KRegion not stated
Grok 4 Fast Non-Reasoning
grok-4-fast-non-reasoning
xAIChat$0.20$0.50−78%2M2MRegion not stated
Grok 4 Fast Reasoning
grok-4-fast-reasoning
xAIChat$0.20$0.50±0%2M2MRegion not stated
Grok 4.1 Fast Non-Reasoning
grok-4-1-fast-non-reasoning
xAIChat$0.20$0.50±0%2M30KRegion not stated
Grok 4.1 Fast Reasoning
grok-4-1-fast-reasoning
xAIChat$0.20$0.50±0%2M2MRegion not stated
Grok Code Fast 1
grok-code-fast-1
xAIChat$0.20$1.50−67%256K10KRegion not stated
Hermes 2 Pro Llama 3 8B
hermes-2-pro-llama-3-8b
Nous ResearchChat$0.14$0.14±0%131K131KRegion not stated
Kimi K2 (07/11)
kimi-k2-0711
Moonshot AIChat$0.57$2.30—131K16.4KRegion not stated
Kimi K2 0905
kimi-k2-0905
Moonshot AIChat$0.50$2.00−17%262K16.4KRegion not stated
Llama 3.1 8B Instruct
llama-3.1-8b-instruct
MetaChat$0.02$0.05−80%16.4K16.4KRegion not stated
Llama 3.3 70b Instruct
llama-3.3-70b-instruct
MetaChat$0.13$0.39−78%128K16.4KRegion not stated
Llama 4 Maverick
llama-4-maverick
MetaChat$0.15$0.60−57%131K8.2KRegion not stated
Llama-4-Scout-17B-16E-Instruct-FP8
llama-4-scout
MetaChat$0.08$0.30−56%131K8.2KRegion not stated
Meta Llama 3.1 8B Instant
llama-3.1-8b-instant
MetaChat$0.05$0.08−60%131K32.7KRegion not stated
Meta Llama 3.3 70B Versatile
llama-3.3-70b-versatile
MetaChat$0.59$0.79+49%131K32.7KRegion not stated
Meta Llama Guard 4 12B
llama-guard-4
MetaChat$0.21$0.21—131K1KRegion not stated
Meta Llama Prompt Guard 2 22M
llama-prompt-guard-2-22m
MetaModeration$0.01$0.01—5122Region not stated
Meta Llama Prompt Guard 2 86M
llama-prompt-guard-2-86m
MetaModeration$0.01$0.01—5122Region not stated
Mistral Large 2.1
mistral-large-2411
Mistral AIChat$2.00$6.00±0%128K32.8KRegion not stated
Mistral Nemo
mistral-nemo
Mistral AIChat$20$40+68,866%128K16.4KRegion not stated
Mistral Small 3.2
mistral-small
Mistral AIChat$0.075$0.20−74%128K16.4KRegion not stated
Moonshot Kimi K2 Thinking
kimi-k2-thinking
Moonshot AIChat$0.48$2.00−20%256K262KRegion not stated
o1
o1
OpenAIChat$15$60±0%200K100KRegion not stated
o1 mini
o1-mini
OpenAIChat$1.10$4.40±0%128K65.5KRegion not stated
o3
o3
OpenAIChat$2.00$8.00±0%200K100KRegion not stated
o3-mini
o3-mini
OpenAIChat$1.10$4.40±0%200K100KRegion not stated
o3-pro
o3-pro
OpenAIChat$20$80±0%200K100KRegion not stated
o4-mini
o4-mini
OpenAIChat$1.10$4.40+4.8%200K100KRegion not stated
OpenAI GPT-5.1 Chat
gpt-5.1-chat-latest
OpenAIChat$1.25$10—128K16.4KRegion not stated
Perplexity Sonar Deep Research
sonar-deep-research
PerplexityChat$2.00$8.00±0%127K4.1KRegion not stated
Qwen2.5 Coder 7B fast
qwen2.5-coder-7b-fast
Alibaba (Qwen)Chat$0.03$0.09—32K8.2KRegion not stated
Qwen3 235B A22B Thinking
qwen3-235b-a22b-thinking
Alibaba (Qwen)Chat$0.30$2.90—262K81.9KRegion not stated
Qwen3 30B A3b fp8
qwen3-30b-a3b
Alibaba (Qwen)Chat$0.08$0.29−11%41K41KRegion not stated
Qwen3 32B
qwen3-32b
Alibaba (Qwen)Chat$0.29$0.59+100%131K41KRegion not stated
Qwen3 Coder
qwen3-coder
Alibaba (Qwen)Chat$0.22$0.95−27%262K16.4KRegion not stated
Qwen3 VL 235B A22B Instruct
qwen3-vl-235b-a22b-instruct
Alibaba (Qwen)Chat$0.30$1.50±0%256K16.4KRegion not stated
Qwen3-Coder 30B-A3B Instruct
qwen3-coder-30b-a3b-instruct
Alibaba (Qwen)Chat$0.10$0.30−9.1%262K262KRegion not stated
Qwen3-Next 80B-A3B Instruct
qwen3-next-80b-a3b-instruct
Alibaba (Qwen)Chat$0.14$1.40−6.7%262K16.4KRegion not stated
Sonar
sonar
PerplexityChat$1.00$1.00±0%127K4.1KRegion not stated
Sonar Pro
sonar-pro
PerplexityChat$3.00$15±0%200K4.1KRegion not stated
Sonar Reasoning
sonar-reasoning
PerplexityChat$1.00$5.00±0%127K4.1KRegion not stated
Sonar Reasoning Pro
sonar-reasoning-pro
PerplexityChat$2.00$8.00±0%127K4.1KRegion not stated

One row per model and variant. Dated pins appear on the model page, not as separate rows. Prices are indicative; verify with the provider.