---
title: LLM APIs pricing
url: "https://toolweight.dev/compare/llm-apis/pricing"
license: CC-BY-4.0
---

# LLM APIs — pricing compared

> Every pricing field in the LLM APIs registry, sourced and dated.

| Tool | $/M input (/M tok) | $/M output (/M tok) | $/M cache read (/M tok) | Batch discount (%) |
| --- | --- | --- | --- | --- |
| Anthropic | $10 /M tok | $50 /M tok | $1 /M tok | 50 % |
| OpenAI | $1.25 /M tok | $10 /M tok | $0.125 /M tok | 50 % |
| Google Gemini | $2 /M tok | $12 /M tok | $0.2 /M tok | 50 % |
| xAI | — | — | — | — |
| Meta Llama | — | — | — | — |
| Mistral AI | — | — | — | 50 % |
| DeepSeek | $0.28 /M tok | $0.42 /M tok | $0.028 /M tok | 0 % |
| Qwen | $1.2 /M tok | $6 /M tok | — | 50 % |
| Moonshot AI | $0.6 /M tok | $2.5 /M tok | $0.15 /M tok | — |
| Z.ai (GLM) | $0.6 /M tok | $2.2 /M tok | — | — |
| Amazon Bedrock | — | — | — | 50 % |
| Cohere | $2.5 /M tok | $10 /M tok | — | — |
| OpenRouter | — | — | — | 0 % |
| Together AI | — | — | — | 50 % |
| Fireworks AI | — | — | — | — |
| Groq | — | — | — | — |
| Cerebras | — | — | — | — |
| Self-hosted (vLLM) | — | — | — | 0 % |

## Provenance

| Tool | Field | Value | Confidence | Verified | Source |
| --- | --- | --- | --- | --- | --- |
| Anthropic | $/M input | $10 /M tok | Vendor-claimed | 2026-06-24 | https://platform.claude.com/docs/en/pricing |
| Anthropic | $/M output | $50 /M tok | Vendor-claimed | 2026-06-24 | https://platform.claude.com/docs/en/pricing |
| Anthropic | $/M cache read | $1 /M tok | Inferred | 2026-06-24 | https://platform.claude.com/docs/en/build-with-claude/prompt-caching |
| Anthropic | Batch discount | 50 % | Vendor-claimed | 2026-06-24 | https://platform.claude.com/docs/en/build-with-claude/batch-processing |
| OpenAI | $/M input | $1.25 /M tok | Vendor-claimed | 2026-01-15 | https://openai.com/api/pricing/ |
| OpenAI | $/M output | $10 /M tok | Vendor-claimed | 2026-01-15 | https://openai.com/api/pricing/ |
| OpenAI | $/M cache read | $0.125 /M tok | Inferred | 2026-01-15 | — |
| OpenAI | Batch discount | 50 % | Vendor-claimed | 2026-01-15 | https://platform.openai.com/docs/guides/batch |
| Google Gemini | $/M input | $2 /M tok | Vendor-claimed | 2026-01-15 | https://ai.google.dev/gemini-api/docs/pricing |
| Google Gemini | $/M output | $12 /M tok | Vendor-claimed | 2026-01-15 | https://ai.google.dev/gemini-api/docs/pricing |
| Google Gemini | $/M cache read | $0.2 /M tok | Inferred | 2026-01-15 | — |
| Google Gemini | Batch discount | 50 % | Vendor-claimed | 2026-01-15 | https://ai.google.dev/gemini-api/docs/batch-mode |
| xAI | $/M input | — | Unknown | — | — |
| xAI | $/M output | — | Unknown | — | — |
| xAI | $/M cache read | — | Unknown | — | — |
| xAI | Batch discount | — | Unknown | — | — |
| Meta Llama | $/M input | — | Unknown | — | — |
| Meta Llama | $/M output | — | Unknown | — | — |
| Meta Llama | $/M cache read | — | Unknown | — | — |
| Meta Llama | Batch discount | — | Unknown | — | — |
| Mistral AI | $/M input | — | Unknown | — | — |
| Mistral AI | $/M output | — | Unknown | — | — |
| Mistral AI | $/M cache read | — | Unknown | — | — |
| Mistral AI | Batch discount | 50 % | Inferred | 2026-01-15 | — |
| DeepSeek | $/M input | $0.28 /M tok | Inferred | 2026-01-15 | https://api-docs.deepseek.com/quick_start/pricing |
| DeepSeek | $/M output | $0.42 /M tok | Inferred | 2026-01-15 | https://api-docs.deepseek.com/quick_start/pricing |
| DeepSeek | $/M cache read | $0.028 /M tok | Inferred | 2026-01-15 | — |
| DeepSeek | Batch discount | 0 % | Inferred | 2026-01-15 | — |
| Qwen | $/M input | $1.2 /M tok | Inferred | 2026-01-15 | — |
| Qwen | $/M output | $6 /M tok | Inferred | 2026-01-15 | — |
| Qwen | $/M cache read | — | Unknown | — | — |
| Qwen | Batch discount | 50 % | Inferred | 2026-01-15 | — |
| Moonshot AI | $/M input | $0.6 /M tok | Inferred | 2026-01-15 | — |
| Moonshot AI | $/M output | $2.5 /M tok | Inferred | 2026-01-15 | — |
| Moonshot AI | $/M cache read | $0.15 /M tok | Inferred | 2026-01-15 | — |
| Moonshot AI | Batch discount | — | Unknown | — | — |
| Z.ai (GLM) | $/M input | $0.6 /M tok | Inferred | 2026-01-15 | — |
| Z.ai (GLM) | $/M output | $2.2 /M tok | Inferred | 2026-01-15 | — |
| Z.ai (GLM) | $/M cache read | — | Unknown | — | — |
| Z.ai (GLM) | Batch discount | — | Unknown | — | — |
| Amazon Bedrock | $/M input | — | Unknown | — | — |
| Amazon Bedrock | $/M output | — | Unknown | — | — |
| Amazon Bedrock | $/M cache read | — | Unknown | — | — |
| Amazon Bedrock | Batch discount | 50 % | Inferred | 2026-01-15 | — |
| Cohere | $/M input | $2.5 /M tok | Inferred | 2026-01-15 | https://cohere.com/pricing |
| Cohere | $/M output | $10 /M tok | Inferred | 2026-01-15 | — |
| Cohere | $/M cache read | — | Unknown | — | — |
| Cohere | Batch discount | — | Unknown | — | — |
| OpenRouter | $/M input | — | Unknown | — | — |
| OpenRouter | $/M output | — | Unknown | — | — |
| OpenRouter | $/M cache read | — | Unknown | — | — |
| OpenRouter | Batch discount | 0 % | Inferred | 2026-01-15 | — |
| Together AI | $/M input | — | Unknown | — | — |
| Together AI | $/M output | — | Unknown | — | — |
| Together AI | $/M cache read | — | Unknown | — | — |
| Together AI | Batch discount | 50 % | Inferred | 2026-01-15 | — |
| Fireworks AI | $/M input | — | Unknown | — | — |
| Fireworks AI | $/M output | — | Unknown | — | — |
| Fireworks AI | $/M cache read | — | Unknown | — | — |
| Fireworks AI | Batch discount | — | Unknown | — | — |
| Groq | $/M input | — | Unknown | — | — |
| Groq | $/M output | — | Unknown | — | — |
| Groq | $/M cache read | — | Unknown | — | — |
| Groq | Batch discount | — | Unknown | — | — |
| Cerebras | $/M input | — | Unknown | — | — |
| Cerebras | $/M output | — | Unknown | — | — |
| Cerebras | $/M cache read | — | Unknown | — | — |
| Cerebras | Batch discount | — | Unknown | — | — |
| Self-hosted (vLLM) | $/M input | — | Unknown | — | — |
| Self-hosted (vLLM) | $/M output | — | Unknown | — | — |
| Self-hosted (vLLM) | $/M cache read | — | Unknown | — | — |
| Self-hosted (vLLM) | Batch discount | 0 % | Inferred | — | — |

## Licence and attribution

Data from toolweight (https://toolweight.dev), licensed CC-BY-4.0.

- Licence: [CC-BY-4.0](https://creativecommons.org/licenses/by/4.0/)
- Canonical HTML: https://toolweight.dev/compare/llm-apis/pricing
- Machine-readable: https://toolweight.dev/compare/llm-apis/pricing.md · https://toolweight.dev/api/v1 · https://toolweight.dev/mcp
- toolweight takes no affiliate revenue and sells no placements. Corrections: https://toolweight.dev/suggest