Claude Opus 5
standardcompute/anthropic/claude-opus-5 · family claude-opus · in: text, image, pdf → out: text · price provider-declared (via models.dev). Capabilities: tools reasoning text image pdf.
$10.00
Blended $/1M (3:1)
$5
Input $/1M
$25
Output $/1M
$30.00
1M in + 1M out
$0.5 −90%
Cache read $/1M
#7993 of 8,550
Cheapest rank
- Provider
- Standard Compute (
standardcompute) - Kind
- text (outputs text)
- Context
- 1,000,000 tokens
- Max output
- 50,000 tokens
- Capabilities
- tools reasoning text image pdf
Same model, other providers
“Claude Opus 5” is offered by 10 providers — cheapest-effective first. Kenari is the cheapest at $0.00 blended.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| Kenari | free | free | $0.00 | 1M |
| Standard Compute (this) | $5 | $25 | $10.00 | 1M |
| NanoGPT | $5 | $25 | $10.00 | 1M |
| Anthropic | $5 | $25 | $10.00 | 1M |
| NEAR AI Cloud | $5 | $25 | $10.00 | 1M |
| Kilo Gateway | $5 | $25 | $10.00 | 1M |
| Venice AI | $5 | $25 | $10.00 | 1M |
| CommandCode | $5 | $25 | $10.00 | 1M |
| Abacus | $5 | $25 | $10.00 | 1M |
| 302.AI | $5 | $25 | $10.00 | 1M |
Call it
jishie indexes & prices models; it does not proxy inference.
Most providers are OpenAI-compatible — point base_url at Standard Compute and pass this model id:
curl $BASE_URL/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
-d '{"model":"anthropic/claude-opus-5","messages":[{"role":"user","content":"hello"}]}'
Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):