Claude Opus 4.1
azure/claude-opus-4-1 · family claude-opus · in: text, image, pdf → out: text · price provider-declared (via models.dev). Capabilities: tools reasoning text image pdf.
$30.00
Blended $/1M (3:1)
$15
Input $/1M
$75
Output $/1M
$90.00
1M in + 1M out
$1.5 −90%
Cache read $/1M
#7587 of 7,708
Cheapest rank
- Provider
- Azure (
azure) - Kind
- text (outputs text)
- Context
- 200,000 tokens
- Max output
- 32,000 tokens
- Capabilities
- tools reasoning text image pdf
Same model, other providers
“Claude Opus 4.1” is offered by 10 providers — cheapest-effective first. This one (Azure) is the cheapest.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| Azure (this) | $15 | $75 | $30.00 | 200k |
| Abacus | $15 | $75 | $30.00 | 200k |
| Azure Cognitive Services | $15 | $75 | $30.00 | 200k |
| ZenMux | $15 | $75 | $30.00 | 200k |
| FastRouter | $15 | $75 | $30.00 | 200k |
| Vertex (Anthropic) | $15 | $75 | $30.00 | 200k |
| OpenCode Zen | $15 | $75 | $30.00 | 200k |
| Amazon Bedrock | $15 | $75 | $30.00 | 200k |
| DevPass (LLM Gateway) | $15 | $75 | $30.00 | 200k |
| Vertex | $15 | $75 | $30.00 | 200k |
Call it
jishie indexes & prices models; it does not proxy inference.
Most providers are OpenAI-compatible — point base_url at Azure and pass this model id:
curl $BASE_URL/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
-d '{"model":"claude-opus-4-1","messages":[{"role":"user","content":"hello"}]}'
Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):