Replicate model pricing
As of October 10, 2026, 39 Replicate models are available through LiteLLM. The most recently added are Claude 4.5 Haiku, Claude 4.5 Sonnet, Gemini 3 Pro. Prices below are Replicate's list prices.
Replicate models
| Model | Lab | Price | Context | Providers | Added |
|---|---|---|---|---|---|
| Claude 4.5 Haiku | Anthropic | $1 / $5 per 1M tokens | – | 1 | Jan 2026 |
| Claude 4.5 Sonnet | Anthropic | $3 / $15 per 1M tokens | – | 1 | Jan 2026 |
| Gemini 3 Pro | $2 / $12 per 1M tokens | 1M | 2 | Jan 2026 | |
| Granite 3.3 8B Instruct | – | $0.03 / $0.25 per 1M tokens | 8K | 2 | Oct 2025 |
| DeepSeek V3.1 | DeepSeek | $0.672 / $2.016 per 1M tokens | 160K | 12 | Aug 2025 |
| GPT OSS 120B | OpenAI | $0.18 / $0.72 per 1M tokens | 131K | 22 | Aug 2025 |
| GPT OSS 20B | OpenAI | $0.09 / $0.36 per 1M tokens | 128K | 14 | Aug 2025 |
| GPT-5 | OpenAI | $1.25 / $10 per 1M tokens | 272K | 8 | Aug 2025 |
| GPT-5 Mini | OpenAI | $0.25 / $2 per 1M tokens | 272K | 8 | Aug 2025 |
| GPT-5 Nano | OpenAI | $0.05 / $0.40 per 1M tokens | 272K | 7 | Aug 2025 |
| Qwen3 235B A22B Instruct 2507 | Alibaba | $0.264 / $1.06 per 1M tokens | 128K | 8 | Aug 2025 |
| Grok 4 | xAI | $7.20 / $36 per 1M tokens | 128K | 4 | Jul 2025 |
| Claude 4 Sonnet | Anthropic | $3 / $15 per 1M tokens | 200K | 5 | Jun 2025 |
| Gemini 2.5 Flash | $0.30 / $2.50 per 1M tokens | 1M | 8 | Jun 2025 | |
| GPT-4.1 | OpenAI | $2 / $8 per 1M tokens | 1M | 6 | Apr 2025 |
| GPT-4.1 Mini | OpenAI | $0.40 / $1.60 per 1M tokens | 1M | 4 | Apr 2025 |
| GPT-4.1 Nano | OpenAI | $0.10 / $0.40 per 1M tokens | 1M | 4 | Apr 2025 |
| o4 Mini | OpenAI | $1 / $4 per 1M tokens | 200K | 4 | Apr 2025 |
| Claude 3.7 Sonnet | Anthropic | $3 / $15 per 1M tokens | 200K | 7 | Feb 2025 |
| DeepSeek R1 | DeepSeek | $3.75 / $10 per 1M tokens | 64K | 16 | Jan 2025 |
| DeepSeek V3 | DeepSeek | $1.45 / $1.45 per 1M tokens | 64K | 15 | Jan 2025 |
| o1 | OpenAI | $15 / $60 per 1M tokens | 200K | 4 | Dec 2024 |
| Claude 3.5 Haiku | Anthropic | $1 / $5 per 1M tokens | 200K | 6 | Nov 2024 |
| o1 Mini | OpenAI | $1.10 / $4.40 per 1M tokens | 128K | 2 | Sep 2024 |
| GPT-4o Mini | OpenAI | $0.15 / $0.60 per 1M tokens | 128K | 7 | Jul 2024 |
| Claude 3.5 Sonnet | Anthropic | $3.75 / $18.75 per 1M tokens | 200K | 7 | Jun 2024 |
| GPT-4o | OpenAI | $2.50 / $10 per 1M tokens | 128K | 7 | May 2024 |
| Llama 2 13B | Meta | $0.10 / $0.50 per 1M tokens | 4K | 1 | May 2024 |
| Llama 2 70B | Meta | $0.65 / $2.75 per 1M tokens | 4K | 1 | May 2024 |
| Llama 2 7B | Meta | $0.05 / $0.25 per 1M tokens | 4K | 1 | May 2024 |
| Llama 3 70B | Meta | $0.65 / $2.75 per 1M tokens | 8K | 3 | May 2024 |
| Llama 3 8B | Meta | $0.05 / $0.25 per 1M tokens | 8K | 3 | May 2024 |
| Llama3 8B Instruct | Meta | $0.05 / $0.25 per 1M tokens | 8K | 8 | May 2024 |
| Mistral 7B Instruct V0.2 | Mistral AI | $0.05 / $0.25 per 1M tokens | 4K | 3 | May 2024 |
| Mistral 7B V0.1 | Mistral AI | $0.05 / $0.25 per 1M tokens | 4K | 1 | May 2024 |
| Llama3 70B Instruct | Meta | $0.65 / $2.75 per 1M tokens | 8K | 7 | Apr 2024 |
| Mixtral 8x7B Instruct V0.1 | Mistral AI | $0.30 / $1 per 1M tokens | 4K | 6 | Jan 2024 |
| Llama 2 13B Chat | Meta | $0.10 / $0.50 per 1M tokens | 4K | 2 | – |
| Llama 2 70B Chat | Meta | $0.65 / $2.75 per 1M tokens | 4K | 4 | – |
