Claude Sonnet 4.5
qihang-ai/claude-sonnet-4-5-20250929 · family claude-sonnet · in: text, image, pdf → out: text · price provider-declared (via models.dev). Capabilities: tools reasoning text image pdf.
$0.86
Blended $/1M (3:1)
$0.43
Input $/1M
$2.14
Output $/1M
$2.57
1M in + 1M out
—
Cache read $/1M
#3841 of 7,708
Cheapest rank
- Provider
- QiHang (
qihang-ai) - Kind
- text (outputs text)
- Context
- 200,000 tokens
- Max output
- 64,000 tokens
- Capabilities
- tools reasoning text image pdf
Same model, other providers
“Claude Sonnet 4.5” is offered by 17 providers — cheapest-effective first. This one (QiHang) is the cheapest.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| QiHang (this) | $0.43 | $2.14 | $0.86 | 200k |
| Perplexity Agent | $3 | $15 | $6.00 | 200k |
| NanoGPT | $3 | $15 | $6.00 | 200k |
| Anthropic | $3 | $15 | $6.00 | 1M |
| Databricks | $3 | $15 | $6.00 | 200k |
| Abacus | $3 | $15 | $6.00 | 200k |
| Azure | $3 | $15 | $6.00 | 200k |
| Azure Cognitive Services | $3 | $15 | $6.00 | 200k |
| ZenMux | $3 | $15 | $6.00 | 1M |
| Vercel AI Gateway | $3 | $15 | $6.00 | 1M |
| Vertex (Anthropic) | $3 | $15 | $6.00 | 200k |
| Tempr | $3 | $15 | $6.00 | 200k |
| OpenCode Zen | $3 | $15 | $6.00 | 1M |
Call it
jishie indexes & prices models; it does not proxy inference.
Most providers are OpenAI-compatible — point base_url at QiHang and pass this model id:
curl $BASE_URL/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
-d '{"model":"claude-sonnet-4-5-20250929","messages":[{"role":"user","content":"hello"}]}'
Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):