| replicate/meta/llama-2-7b-chat | replicate | 4,096 | |
| replicate/meta/llama-3-70b | replicate | 8,192 | |
| replicate/meta/llama-3-70b-instruct | replicate | 8,192 | |
| replicate/meta/llama-3-8b | replicate | 8,086 | |
| replicate/meta/llama-3-8b-instruct | replicate | 8,086 | |
| replicate/mistralai/mistral-7b-instruct-v0.2 | replicate | 4,096 | |
| replicate/mistralai/mistral-7b-v0.1 | replicate | 4,096 | |
| replicate/mistralai/mixtral-8x7b-instruct-v0.1 | replicate | 4,096 | |
| replicate/openai/gpt-5 | replicate | — | |
| replicate/openai/gpt-oss-20b | replicate | — | |
| replicate/anthropic/claude-4.5-haiku | replicate | — | |
| replicate/ibm-granite/granite-3.3-8b-instruct | replicate | — | |
| replicate/openai/gpt-4o | replicate | — | |
| replicate/openai/o4-mini | replicate | — | - Input
- Output
- Output (reasoning)
|
| replicate/openai/o1-mini | replicate | — | - Input
- Output
- Output (reasoning)
|
| replicate/openai/o1 | replicate | — | - Input
- Output
- Output (reasoning)
|
| replicate/openai/gpt-4o-mini | replicate | — | |
| replicate/qwen/qwen3-235b-a22b-instruct-2507 | replicate | — | |
| replicate/anthropic/claude-4-sonnet | replicate | — | |
| replicate/deepseek-ai/deepseek-v3 | replicate | 65,536 | |
| replicate/anthropic/claude-3.7-sonnet | replicate | — | |
| replicate/anthropic/claude-3.5-haiku | replicate | — | |
| replicate/anthropic/claude-3.5-sonnet | replicate | — | |
| replicate/google/gemini-3-pro | replicate | — | - Input
- Input (>200k ctx)
- Output
- Output (>200k ctx)
|
| replicate/anthropic/claude-4.5-sonnet | replicate | — | |