Cloud pricing directory
Cloud LLM API Pricing
Browse provider-specific LLM API pricing pages for OpenAI, Anthropic, Google Gemini, DeepSeek, Groq, Together AI, and other hosted model platforms. Each page lists model rates per 1M tokens and example monthly costs for common token volumes.
Pricing data updated 2026-11-02. Always confirm final rates with the provider before making production decisions.
Core provider pricing pages
OpenAI
OpenAI offers GPT-6.1 Sol and Terra for complex work, alongside GPT-6 Luna for cost-sensitive workloads. Compare input and output rates across its model tiers.
Anthropic
Anthropic's Claude family includes Opus 5.5 and Sonnet 5.5 for reasoning, coding, and agentic workloads. Compare their token rates alongside earlier Claude models.
Google Gemini
Google's Gemini API includes Gemini 4 Argon and Gemini 3.8 Flash for multimodal and agentic workloads. Check the provider's current rate card for promotional and standard pricing.
Groq
Ultra-fast inference on dedicated LPU hardware — up to 1,000 tokens/sec. Best for latency-sensitive production apps. Predictable, linear pricing.
Together AI
Together AI provides serverless inference for a range of open-weight models. Model availability and pricing depend on the selected deployment and provider rate card.
DeepSeek
DeepSeek provides models for chat, reasoning, and coding. Compare V4.1 Flash, V4 Pro, and earlier models, and check the provider's current API availability and rates.
More cloud LLM providers
Qwen (Alibaba)
Alibaba's Qwen family includes Qwen3.8 models for general-purpose and coding workloads. Availability and pricing vary by model and serving platform.
Doubao (ByteDance)
ByteDance's Doubao models are available through Volcano Engine. Compare the listed Pro and Mini tiers and verify current pricing and availability with the provider.
Kimi (Moonshot AI)
Moonshot AI's Kimi family includes K3.1 Pro and K2.7 Code for coding, reasoning, and agent workloads. Review model availability and rates for the platform you use.
Zhipu AI (GLM)
Zhipu AI's GLM family includes GLM-5.3 Prime and Flash models alongside earlier generations. Compare rates and confirm regional pricing with the provider.
Hunyuan (Tencent)
Tencent Cloud's Hunyuan models. TurboS is the high-speed inference variant; T1 adds chain-of-thought reasoning. Both are priced in CNY and convert to strong USD value — TurboS offers 256K context at $0.11/$0.28 per 1M tokens.
How to compare provider pricing
Token prices are only one part of the final bill. Compare input and output rates, context length, model quality, retries, cache behavior, latency, and whether your workload can use a smaller model.
Estimate your monthly LLM API bill