Replicate
Run open-source machine learning models with a cloud API. Inference platform · Community · Image Generation · Open Source · Video Generation
Intelligence vs Price
Best value among Replicate models on this chart: Gemini 3 Pro · GPT-5 · Grok 4 (and 4 more on the dashed frontier). Hover any dot for full pricing, or click a creator in the legend to isolate.
Replicate models
40 models, 40 with pricingModel | Creator | Input Price, $ | Output Price, $ | Context | Max Output | Inference Providers | Intelligence | Coding | |
|---|---|---|---|---|---|---|---|---|---|
| Gemini 3 Pro | 2.00 | 12.00 | N/A | N/A | compare (3) | 48.4#1 | 46.5#1 | ||
| GPT-5 | 1.25 | 10.00 | 410K | 128K | compare (9) | 44.6#2 | 36.0#3 | ||
| Grok 4 | 1.25 | 2.50 | 256K | N/A | compare (6) | 41.5#3 | 40.5#2 | ||
| GPT-5 Mini | 0.250 | 2.00 | 400K | 128K | compare (8) | 41.2#4 | 35.3#4 | ||
| Claude Sonnet 4.5 | 3.00 | 15.00 | 1.0M | 64K | compare (10) | 37.1#5 | 33.5#5 | ||
| GPT OSS 120B | 0.039 | 0.180 | 131K | 131K | compare (20) | 33.3#6 | 28.6#8 | ||
| o4 Mini | 1.00 | 4.00 | 200K | 100K | compare (5) | 33.1#7 | 25.6#12 | ||
| Claude Sonnet 4 | 3.00 | 15.00 | 1.0M | 64K | compare (10) | 33.0#8 | 30.6#6 | ||
| Claude Haiku 4.5 | 1.00 | 5.00 | 200K | 64K | compare (9) | 31.0#9 | 29.6#7 | ||
| Claude Sonnet 3.7 | 3.00 | 15.00 | 200K | 128K | compare (9) | 30.8#10 | 26.7#10 | ||
| o1 | 15.00 | 60.00 | 200K | 100K | compare (5) | 30.7#11 | 20.5#14 | ||
| DeepSeek V3.1 | 0.135 | 0.500 | 164K | 66K | compare (14) | 28.1#12 | 28.4#9 | ||
| GPT-5 Nano | 0.050 | 0.400 | 400K | 128K | compare (8) | 26.8#13 | 20.3#15 | ||
| GPT-4.1 | 2.00 | 8.00 | 1.0M | 33K | compare (6) | 26.3#14 | 21.8#13 | ||
| GPT OSS 20B | 0.030 | 0.140 | 131K | 131K | compare (15) | 24.5#15 | 18.5#17 | ||
| GPT-4.1 Mini | 0.400 | 1.60 | 1.0M | 33K | compare (5) | 22.9#16 | 18.5#16 | ||
| o1 Mini | 1.10 | 4.40 | 128K | 66K | compare (3) | 20.4#17 | N/A | ||
| DeepSeek R1 | 0.280 | 0.400 | 164K | 66K | compare (14) | 18.8#18 | 15.9#21 | ||
| Claude Haiku 3.5 | 0.800 | 4.00 | 200K | 8K | compare (7) | 18.7#19 | 10.7#24 | ||
| Gemini 2.5 Flash | 0.150 | 0.600 | 1.0M | 66K | compare (9) | 17.8#20 | 17.8#18 | ||
| Qwen3 235B A22B Instruct | 0.090 | 0.580 | 262K | 33K | compare (10) | 17.0#21 | 14.0#22 | ||
| DeepSeek V3 | 0.200 | 0.200 | 400K | 128K | compare (12) | 16.5#22 | 16.4#20 | ||
| GPT-4o | 2.50 | 10.00 | 131K | 16K | compare (6) | 14.5#23 | 16.6#19 | ||
| Claude Sonnet 3.5 | 3.00 | 15.00 | 1.0M | 8K | compare (6) | 14.2#24 | 26.0#11 | ||
| GPT-4.1 Nano | 0.100 | 0.400 | 1.0M | 33K | compare (5) | 13.0#25 | 11.2#23 | ||
| GPT-4o mini | 0.150 | 0.600 | 131K | 16K | compare (6) | 12.6#26 | N/A | ||
| Llama 2 7B Chat | 0.050 | 0.150 | 4K | 4K | compare (4) | 9.7#27 | N/A | ||
| Llama 3 70B Instruct | 0.120 | 0.300 | 131K | 8K | compare (9) | 8.9#28 | 6.8#25 | ||
| Llama 2 70B Chat | 0.500 | 0.900 | 4K | 4K | compare (7) | 8.4#30 | N/A | ||
| Llama 2 13B Chat | 0.100 | 0.200 | 4K | 4K | compare (4) | 8.4#29 | N/A | ||
| Mixtral 8x7B Instruct | 0.070 | 0.150 | 33K | 16K | compare (9) | 7.7#31 | N/A | ||
| Mistral 7B Instruct | 0.010 | 0.100 | 127K | 16K | compare (9) | 7.4#32 | N/A | ||
| Granite 3.3 8B Instruct | 0.030 | 0.200 | 8K | 8K | compare (2) | 7.0#33 | 3.4#27 | ||
| Llama 3 8B Instruct | 0.030 | 0.040 | 32K | 8K | compare (9) | 6.4#34 | 4.0#26 | ||
| Llama 2 13B | 0.100 | 0.200 | 4K | 4K | compare (2) | N/A | N/A | ||
| Llama 2 70B | 0.100 | 0.100 | 4K | 4K | compare (2) | N/A | N/A | ||
| Llama 2 7B | 0.050 | 0.200 | 4K | 4K | compare (2) | N/A | N/A | ||
| Llama 3 70B | 0.590 | 0.790 | 8K | 8K | compare (3) | N/A | N/A | ||
| Llama 3 8B | 0.050 | 0.080 | 8K | 8K | compare (4) | N/A | N/A | ||
| Mistral 7B | 0.050 | 0.150 | 33K | 8K | compare (5) | N/A | N/A |