Last refreshed 2026-07-26. Next refresh: weekly.
Why use Claude 4 Sonnet on Replicate API?
Replicate API offers Claude 4 Sonnet with pay-as-you-go pricing at $3.00/1M input tokens. Replicate is a cloud-based platform that enables users to run machine learning models easily and efficiently.
Compare Claude 4 Sonnet across 2 providers to find the best fit for your use caseInput / 1M
$3.00
Output / 1M
$15.00
Cache
Not sourced
Batch
Not sourced
Setup recipe
Python + curlInstall
pip install replicateAuth
export REPLICATE_API_TOKEN=...Call
import replicate
output = replicate.run(
"anthropic/claude-4-sonnet",
input={"prompt": "Hello"}Model ID
anthropic/claude-4-sonnetRequest example
import replicate
# reads REPLICATE_API_TOKEN from env
# anthropic/claude-4-sonnet format: "owner/model-name" (latest version) or "owner/model-name:version-hash"
output = replicate.run(
"anthropic/claude-4-sonnet",
input={"prompt": "Hello"}
)
# Output is a list or generator depending on the model
print("".join(output))Gotchas
- Use provider model ID "anthropic/claude-4-sonnet", not the LLMReference slug "claude-4-sonnet".
- Replicate uses "owner/model-name" format (e.g. "meta/meta-llama-3-8b-instruct") for the latest version, or "owner/model-name:version-sha" to pin to a specific version. The REST endpoint splits owner and model-name into the path: /v1/models/{owner}/{model-name}/predictions.
- The examples expect REPLICATE_API_TOKEN; rename it only if your application config maps the new variable.
Compare Claude 4 Sonnet Across Providers
| Provider | Input (per 1M) | Output (per 1M) |
|---|---|---|
| Snowflake Cortex | — | — |
| Replicate API | $3.00 | $15.00 |
Pricing
| Type | Price (per 1M) |
|---|---|
| Input tokens | $3.00 |
| Output tokens | $15.00 |
Capabilities
VisionMultimodalJSON / Tool useFine-tuning
About Claude 4 Sonnet
Anthropic Claude 4 Sonnet API snapshot (claude-sonnet-4-20250514), deprecated April 14, 2026 with Claude API retirement scheduled for June 15, 2026. Use Claude Sonnet 4.6 for current integrations.
Get Started
Model Specs
Released2025-05-14
Context200k
ArchitectureDecoder Only
Knowledge cutoff2025-10