Provider
Replicate
40 Models · 40 Prices · Cheapest on 21 · Uptime — · updated 2026-08-04 23:15 UTC
Trust signals · SLA · model-version transparency · pricing stability · quantization-degradation · incident response · data privacy — measured by TKX probe (activating).
About
Replicate is an AI inference provider that utilizes machine learning to serve a variety of models, offering a platform for developers to integrate and deploy AI capabilities into their applications.
AI-generated summary from public information — is this yours? Claim & edit
Models served
| Model | $ in /1M | $ out /1M | Cheapest | Router / Source | Evidence |
|---|---|---|---|---|---|
| granite-3.3-8b-instruct | $0.030 | $0.250 | ✓ | Pricebook (LiteLLM) | Official list |
| llama-2-7b | $0.050 | $0.250 | ✓ | Pricebook (LiteLLM) | Official list |
| llama-2-7b-chat | $0.050 | $0.250 | ✓ | Pricebook (LiteLLM) | Official list |
| llama-3-8b | $0.050 | $0.250 | — | Pricebook (LiteLLM) | Official list |
| llama-3-8b-instruct | $0.050 | $0.250 | — | Pricebook (LiteLLM) | Official list |
| mistral-7b-instruct-v0.2 | $0.050 | $0.250 | ✓ | Pricebook (LiteLLM) | Official list |
| mistral-7b-v0.1 | $0.050 | $0.250 | ✓ | Pricebook (LiteLLM) | Official list |
| gpt-5-nano | $0.050 | $0.400 | — | Pricebook (LiteLLM) | Official list |
| gpt-oss-20b | $0.090 | $0.360 | — | Pricebook (LiteLLM) | Official list |
| gpt-4.1-nano | $0.100 | $0.400 | ✓ | Pricebook (LiteLLM) | Official list |
| llama-2-13b | $0.100 | $0.500 | ✓ | Pricebook (LiteLLM) | Official list |
| llama-2-13b-chat | $0.100 | $0.500 | ✓ | Pricebook (LiteLLM) | Official list |
| gpt-4o-mini | $0.150 | $0.600 | ✓ | Pricebook (LiteLLM) | Official list |
| gpt-oss-120b | $0.180 | $0.720 | — | Pricebook (LiteLLM) | Official list |
| qwen3-235b-a22b-instruct-2507 | $0.264 | $1.06 | — | Pricebook (LiteLLM) | Official list |
| mixtral-8x7b-instruct-v0.1 | $0.300 | $1.00 | — | Pricebook (LiteLLM) | Official list |
| gpt-5-mini | $0.250 | $2.00 | — | Pricebook (LiteLLM) | Official list |
| gpt-4.1-mini | $0.400 | $1.60 | ✓ | Pricebook (LiteLLM) | Official list |
| deepseek-v3.1 | $0.672 | $2.02 | — | Pricebook (LiteLLM) | Official list |
| llama-2-70b | $0.650 | $2.75 | ✓ | Pricebook (LiteLLM) | Official list |
| llama-2-70b-chat | $0.650 | $2.75 | ✓ | Pricebook (LiteLLM) | Official list |
| llama-3-70b | $0.650 | $2.75 | — | Pricebook (LiteLLM) | Official list |
| llama-3-70b-instruct | $0.650 | $2.75 | — | Pricebook (LiteLLM) | Official list |
| deepseek-v3 | $1.45 | $1.45 | — | Pricebook (LiteLLM) | Official list |
| o4-mini | $1.00 | $4.00 | — | Pricebook (LiteLLM) | Official list |
| o1-mini | $1.10 | $4.40 | ✓ | Pricebook (LiteLLM) | Official list |
| claude-4.5-haiku | $1.00 | $5.00 | ✓ | Pricebook (LiteLLM) | Official list |
| claude-3.5-haiku | $1.00 | $5.00 | — | Pricebook (LiteLLM) | Official list |
| gemini-2.5-flash | $2.50 | $2.50 | — | Pricebook (LiteLLM) | Official list |
| gpt-5 | $1.25 | $10.00 | — | Pricebook (LiteLLM) | Official list |
| gpt-4.1 | $2.00 | $8.00 | ✓ | Pricebook (LiteLLM) | Official list |
| gpt-4o | $2.50 | $10.00 | ✓ | Pricebook (LiteLLM) | Official list |
| gemini-3-pro | $2.00 | $12.00 | ✓ | Pricebook (LiteLLM) | Official list |
| deepseek-r1 | $3.75 | $10.00 | — | Pricebook (LiteLLM) | Official list |
| claude-4-sonnet | $3.00 | $15.00 | ✓ | Pricebook (LiteLLM) | Official list |
| claude-3.7-sonnet | $3.00 | $15.00 | ✓ | Pricebook (LiteLLM) | Official list |
| claude-4.5-sonnet | $3.00 | $15.00 | ✓ | Pricebook (LiteLLM) | Official list |
| claude-3.5-sonnet | $3.75 | $18.75 | — | Pricebook (LiteLLM) | Official list |
| grok-4 | $7.20 | $36.00 | — | Pricebook (LiteLLM) | Official list |
| o1 | $15.00 | $60.00 | ✓ | Pricebook (LiteLLM) | Official list |