Models

40 models shown. Amounts are per the unit stated in each row.
ModelProviderContextPrices
replicate/meta/llama-2-13breplicate4,096
Input

$0.10 per 1M tokens

low
Output

$0.50 per 1M tokens

low
replicate/meta/llama-2-13b-chatreplicate4,096
Input

$0.10 per 1M tokens

low
Output

$0.50 per 1M tokens

low
replicate/meta/llama-2-70breplicate4,096
Input

$0.65 per 1M tokens

low
Output

$2.75 per 1M tokens

low
replicate/meta/llama-2-70b-chatreplicate4,096
Input

$0.65 per 1M tokens

low
Output

$2.75 per 1M tokens

low
replicate/meta/llama-2-7breplicate4,096
Input

$0.05 per 1M tokens

low
Output

$0.25 per 1M tokens

low
replicate/meta/llama-2-7b-chatreplicate4,096
Input

$0.05 per 1M tokens

low
Output

$0.25 per 1M tokens

low
replicate/meta/llama-3-70breplicate8,192
Input

$0.65 per 1M tokens

low
Output

$2.75 per 1M tokens

low
replicate/meta/llama-3-70b-instructreplicate8,192
Input

$0.65 per 1M tokens

low
Output

$2.75 per 1M tokens

low
replicate/meta/llama-3-8breplicate8,086
Input

$0.05 per 1M tokens

low
Output

$0.25 per 1M tokens

low
replicate/meta/llama-3-8b-instructreplicate8,086
Input

$0.05 per 1M tokens

low
Output

$0.25 per 1M tokens

low
replicate/mistralai/mistral-7b-instruct-v0.2replicate4,096
Input

$0.05 per 1M tokens

low
Output

$0.25 per 1M tokens

low
replicate/mistralai/mistral-7b-v0.1replicate4,096
Input

$0.05 per 1M tokens

low
Output

$0.25 per 1M tokens

low
replicate/mistralai/mixtral-8x7b-instruct-v0.1replicate4,096
Input

$0.30 per 1M tokens

low
Output

$1.00 per 1M tokens

low
replicate/openai/gpt-5replicate—
Input

$1.25 per 1M tokens

low
Output

$10.00 per 1M tokens

low
replicate/openai/gpt-oss-20breplicate—
Input

$0.09 per 1M tokens

low
Output

$0.36 per 1M tokens

low
replicate/anthropic/claude-4.5-haikureplicate—
Input

$1.00 per 1M tokens

low
Output

$5.00 per 1M tokens

low
replicate/ibm-granite/granite-3.3-8b-instructreplicate—
Input

$0.03 per 1M tokens

low
Output

$0.25 per 1M tokens

low
replicate/openai/gpt-4oreplicate—
Input

$2.50 per 1M tokens

low
Output

$10.00 per 1M tokens

low
replicate/openai/o4-minireplicate—
Input

$1.00 per 1M tokens

low
Output

$4.00 per 1M tokens

low
Output (reasoning)

$4.00 per 1M tokens

low
replicate/openai/o1-minireplicate—
Input

$1.10 per 1M tokens

low
Output

$4.40 per 1M tokens

low
Output (reasoning)

$4.40 per 1M tokens

low
replicate/openai/o1replicate—
Input

$15.00 per 1M tokens

low
Output

$60.00 per 1M tokens

low
Output (reasoning)

$60.00 per 1M tokens

low
replicate/openai/gpt-4o-minireplicate—
Input

$0.15 per 1M tokens

low
Output

$0.60 per 1M tokens

low
replicate/qwen/qwen3-235b-a22b-instruct-2507replicate—
Input

$0.264 per 1M tokens

low
Output

$1.06 per 1M tokens

low
replicate/anthropic/claude-4-sonnetreplicate—
Input

$3.00 per 1M tokens

low
Output

$15.00 per 1M tokens

low
replicate/deepseek-ai/deepseek-v3replicate65,536
Input

$1.45 per 1M tokens

low
Output

$1.45 per 1M tokens

low

Last updated 10/04/2026, 02:10