API pricing

LLM API Pricing by Provider

Calcaas tracks per-million-token pricing for 2,561 large language models across 45 providers, including OpenAI, Anthropic, Google Gemini, Vertex AI, AWS Bedrock and Azure OpenAI. Every provider page lists input cost, output cost, context window and capability support, current as of August 11, 2026.

Last updated August 11, 2026 · synced weekly from the upstream model catalog

Google Vertex AI pricing — Claude, Gemini, Llama, Mistral, DeepSeek and Qwen models on one page (104 models).

All providers

OpenRouter

407 models · from $0.030/1M output

Fireworks AI

280 models · from $0.0010/1M output

Novita

180 models · from $0.020/1M output

Azure OpenAI

150 models · from —/1M output

DeepInfra

118 models · from $0.020/1M output

AWS Bedrock

100 models · from $0.040/1M output

OpenAI

95 models · from $0.140/1M output

Vercel AI Gateway

90 models · from —/1M output

Mistral AI

86 models · from $0.040/1M output

Azure AI

72 models · from —/1M output

Together AI

67 models · from $0.100/1M output

Alibaba (DashScope)

60 models · from $0.035/1M output

Nebius

60 models · from $0.030/1M output

Hugging Face

57 models · from $0.250/1M output

Databricks

55 models · from —/1M output

Gemini on Vertex AI

54 models · from $0.250/1M output

Google Vertex AI

52 models · from $0.040/1M output

xAI (Grok)

45 models · from $0.500/1M output

Replicate

40 models · from $0.250/1M output

Qwen (Alibaba)

39 models · from $0.090/1M output

Oracle Cloud

35 models · from $0.090/1M output

GitHub Copilot

31 models · from $1.20/1M output

IBM watsonx

28 models · from $0.100/1M output

Moonshot

28 models · from $2.00/1M output

Anthropic

22 models · from $1.25/1M output

Perplexity

22 models · from $0.200/1M output

DeepSeek

21 models · from $0.100/1M output

Lambda

20 models · from $0.025/1M output

Claude on Vertex AI

19 models · from $1.25/1M output

Groq

19 models · from $0.030/1M output

Mistral (Vertex)

19 models · from $0.150/1M output

OVHcloud

19 models · from $0.100/1M output

SambaNova

19 models · from $0.080/1M output

Snowflake

19 models · from $0.240/1M output

Cohere

16 models · from $0.150/1M output

Hyperbolic

16 models · from $0.200/1M output

Meta Llama

16 models · from $0.020/1M output

Zhipu AI

15 models · from $0.100/1M output

Nscale

14 models · from $0.025/1M output

Anyscale

12 models · from $0.150/1M output

MiniMax

11 models · from $1.02/1M output

AI21 Labs

9 models · from $0.400/1M output

Amazon Bedrock

8 models · from $0.140/1M output

Cerebras

8 models · from $0.100/1M output

Community

8 models · from $0.060/1M output