Qwen3 235B-A22B Instruct 2507
uberllm/qwen/qwen3-235b-a22b-2507 · family qwen · in: text → out: text · price provider-declared (via models.dev). Capabilities: tools text.
$0.18
Blended $/1M (3:1)
$0.0868
Input $/1M
$0.465
Output $/1M
$0.55
1M in + 1M out
—
Cache read $/1M
#1721 of 9,563
Cheapest rank
- Provider
- UberLLM (
uberllm) - Kind
- text (outputs text)
- Context
- 128,000 tokens
- Max output
- 16,384 tokens
- Capabilities
- tools text
Same model, other providers
“Qwen3 235B-A22B Instruct 2507” is offered by 8 providers — cheapest-effective first. OpenCheap is the cheapest at $0.00 blended.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| OpenCheap | $0.0021 | $0.012 | $0.00 | 262k |
| UberLLM (this) | $0.0868 | $0.465 | $0.18 | 128k |
| Deep Infra | $0.09 | $0.55 | $0.21 | 262k |
| Runcrate | $0.0945 | $0.5775 | $0.22 | 262k |
| Cortecs | $0.199 | $0.598 | $0.30 | 262k |
| Crusoe | $0.22 | $0.8 | $0.36 | 262k |
| Amazon Bedrock | $0.22 | $0.88 | $0.39 | 262k |
| Hugging Face | $0.855 | $2.57 | $1.28 | 262k |
Call it
jishie indexes & prices models; it does not proxy inference.
Most providers are OpenAI-compatible — point base_url at UberLLM and pass this model id:
curl $BASE_URL/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
-d '{"model":"qwen/qwen3-235b-a22b-2507","messages":[{"role":"user","content":"hello"}]}'
Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):