Helicone | AI model provider information

Loading catalog

Loading catalog

Subscribe

Follow catalog updates and new guides

RSS feedOpen RSS feed

MediumMedium guides

skills.shskills.sh

CodexBank a free Codex reset

01 / 02Open RSS feed and Medium guides

RSS covers catalog changes. Medium has guides. Skills.sh has reusable agent playbooks. Codex reset is for new accounts.

Provider index

Providers

Helicone | AI model provider information

Use Kimi K3 in OpenCode Go. Get $5 off your first month.

The fastest GLM 5.2, Kimi K2.7 and MiniMax M3The fastest GLM 5.2, Kimi K2.7 and MiniMax M3

Get a Codex banked reset for new accounts

Provider details

Helicone

Learn more about this provider, then browse the models currently listed under it.

heliconehelicone

X LinkedIn GitHub Discord Crunchbase

Latest news about Helicone

No articles yet. Fetch the latest news to show it here.

Recent tweets and retweets from Helicone

About Helicone

What they do

Helicone is an open-source LLM observability and gateway platform for routing, logging, debugging, and analyzing production AI traffic.

How they were founded

Founded in 2023 by Justin Torre and Cole Gottdank during Y Combinator's Winter 2023 batch to build LLM observability tooling, later expanding into gateway products.

Sources

These links anchor the profile to public company pages, docs, and reference material.

ycombinator.com

Quick Info

Organization: Helicone
Headquarters: San Francisco, California, United States
SDK package: @ai-sdk/openai-compatible
Synced at: Jul 11, 2026

Models served

90 models available through Helicone

These model results are sorted newest first so you can quickly see the latest options from this provider.

⌕

Heliconeclaude-opus

Anthropic: Claude Opus 4.5

claude-4.5-opusHeliconeReleased Nov 24, 2025200,000 token context windowIn $5.00 · Out $25.00

Input

Output

Heliconegemini-pro

Google Gemini 3 Pro Preview

gemini-3-pro-previewHeliconeReleased Nov 18, 20251,048,576 token context windowIn $2.00 · Out $12.00

Input

Output

Heliconegrok

xAI Grok 4.1 Fast Non-Reasoning

grok-4-1-fast-non-reasoningHeliconeReleased Nov 17, 20252,000,000 token context windowIn $0.20 · Out $0.50

Input

Output

Heliconegrok

xAI Grok 4.1 Fast Reasoning

grok-4-1-fast-reasoningHeliconeReleased Nov 17, 20252,000,000 token context windowIn $0.20 · Out $0.50

Input

Output

Heliconekimi-thinking

Kimi K2 Thinking

kimi-k2-thinkingHeliconeReleased Nov 6, 2025256,000 token context windowIn $0.48 · Out $2.00

Input

Output

Heliconeclaude-haiku

Anthropic: Claude 4.5 Haiku

claude-4.5-haikuHeliconeReleased Oct 1, 2025200,000 token context windowIn $1.00 · Out $5.00

Input

Output

Heliconeclaude-haiku

Anthropic: Claude 4.5 Haiku (20251001)

claude-haiku-4-5-20251001HeliconeReleased Oct 1, 2025200,000 token context windowIn $1.00 · Out $5.00

Input

Output

Heliconeclaude-sonnet

Anthropic: Claude Sonnet 4.5

claude-4.5-sonnetHeliconeReleased Sep 29, 2025200,000 token context windowIn $3.00 · Out $15.00

Input

Output

Heliconeclaude-sonnet

Anthropic: Claude Sonnet 4.5 (20250929)

claude-sonnet-4-5-20250929HeliconeReleased Sep 29, 2025200,000 token context windowIn $3.00 · Out $15.00

Input

Output

Heliconeqwen

Qwen3 VL 235B A22B Instruct

qwen3-vl-235b-a22b-instructHeliconeReleased Sep 23, 2025256,000 token context windowIn $0.30 · Out $1.50

Input

Output

Heliconedeepseek

DeepSeek V3.1 Terminus

deepseek-v3.1-terminusHeliconeReleased Sep 22, 2025128,000 token context windowIn $0.27 · Out $1.00

Input

Output

Heliconedeepseek

deepseek-v3.2HeliconeReleased Sep 22, 2025163,840 token context windowIn $0.27 · Out $0.41

Input

Output

Heliconegrok

xAI Grok 4 Fast Non-Reasoning

grok-4-fast-non-reasoningHeliconeReleased Sep 19, 20252,000,000 token context windowIn $0.20 · Out $0.50

Input

Output

Heliconekimi-k2

Kimi K2 (09/05)

kimi-k2-0905HeliconeReleased Sep 5, 2025262,144 token context windowIn $0.50 · Out $2.00

Input

Output

Heliconegrok

xAI: Grok 4 Fast Reasoning

grok-4-fast-reasoningHeliconeReleased Sep 1, 20252,000,000 token context windowIn $0.20 · Out $0.50

Input

Output

Heliconeclaude-opus

Anthropic: Claude Opus 4.1

claude-opus-4-1HeliconeReleased Aug 5, 2025200,000 token context windowIn $15.00 · Out $75.00

Input

Output

Heliconeclaude-opus

Anthropic: Claude Opus 4.1 (20250805)

claude-opus-4-1-20250805HeliconeReleased Aug 5, 2025200,000 token context windowIn $15.00 · Out $75.00

Input

Output

Heliconeqwen

Qwen3 Coder 30B A3B Instruct

qwen3-coder-30b-a3b-instructHeliconeReleased Jul 31, 2025262,144 token context windowIn $0.10 · Out $0.30

Input

Output

Previous pagePage 1 of 5

Recent tweets and retweets from Helicone

Mar 12, 2026, 6:11 PMUTC

Connor is an ex @helicone_ai intern turned YC founder. He built @tryreplicas while working at Helicone. We used it internally to handle about 70% of our bug reports.

Mar 3, 2026, 5:04 PMUTC

We're excited to share that Helicone is joining @mintlify! 🎉🎉🎉 What this means for our users: Helicone is moving into maintenance mode. Your data is safe and the platform will continue to be accessible, but we will not be shipping new features going forward. Thank you to…

Feb 17, 2026, 8:44 AMUTC

I occasionally use Openrouter. I’m a big fan of @helicone_ai? Not only centralised billing across 100s of models but also incredible analytics.

Dec 19, 2025, 12:24 PMUTC

psa: this is your end of year reminder to turn on prompt caching in your fav LLM provider. gateways like @LiteLLM @PortkeyAI @helicone_ai also have ways to do this this gets you the same output with none of the uncertainty of embedding caching redis is selling these days

Dec 19, 2025, 4:21 PMUTC

The @helicone_ai team went off with this 2025 recap ❄️🎄