Qwen3 30B A3B Instruct 2507
wandb/Qwen/Qwen3-30B-A3B-Instruct-2507 · family qwen · in: text → out: text · price provider-declared (via models.dev). Capabilities: tools text.
$0.15
Blended $/1M (3:1)
$0.1
Input $/1M
$0.3
Output $/1M
$0.40
1M in + 1M out
$0.1
Cache read $/1M
#1317 of 7,712
Cheapest rank
- Provider
- CoreWeave (
wandb) - Kind
- text (outputs text)
- Context
- 262,144 tokens
- Max output
- 262,144 tokens
- Capabilities
- tools text
Same model, other providers
“Qwen3 30B A3B Instruct 2507” is offered by 5 providers — cheapest-effective first. ModelScope is the cheapest at $0.00 blended.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| ModelScope | free | free | $0.00 | 262k |
| CoreWeave (this) | $0.1 | $0.3 | $0.15 | 262k |
| OpenRouter | $0.1 | $0.3 | $0.15 | 262k |
| NanoGPT | $0.2 | $0.5 | $0.28 | 256k |
| Clarifai | $0.3 | $0.5 | $0.35 | 262k |
Call it
jishie indexes & prices models; it does not proxy inference.
Most providers are OpenAI-compatible — point base_url at CoreWeave and pass this model id:
curl $BASE_URL/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
-d '{"model":"Qwen/Qwen3-30B-A3B-Instruct-2507","messages":[{"role":"user","content":"hello"}]}'
Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):