qwen3-30b-a3b-thinking-2507

apache-2.030B / 3B
Context
262K
Input price
$1/1M tokens
Output price
$1/1M tokens
Snapshotsfireworks/qwen3-30b-a3b-thinking-2507

Capabilities

vision
tool call
structured output
reasoning
json mode
streaming
fine tuning
batch

Details

Model IDfireworks/qwen3-30b-a3b-thinking
Provider Fireworks AI
Creator Qwen
Familyqwen3
Licenseapache-2.0
Parameters30B / 3B
Status—
Input modalitiestext
Output modalitiestext
Architecture—
Knowledge cutoff—
Training data cutoff—
Release date—
Deprecation date—
Typechat
Reasoning tokens—
Max input—
Open weight—
Sourceofficial
Last updated

Pricing

Input
$1
Output
$1
Cache write
—
Cache read
$1
Batch in
—
Batch out
—

Family Comparison: qwen3

ModelContextMax outPricing
qwen3-vl-30b-a3b-instruct262K—$0.15$1
qwen3-vl-30b-a3b-thinking262K—$0.15$0.6
qwen3-8b41K—$0.2$0.2
qwen3-reranker-8b41K—$0.2$1
qwen3-235b-a22b-instruct-2507262K—$0.22$1
qwen3p6-plus——$0.5$3
qwen3-0p6b41K—$1$1
qwen3-14b41K—$1$1
qwen3-1p7b-fp8-draft-131072131K—$1$1
qwen3-1p7b-fp8-draft-4096041K—$1$1
qwen3-1p7b-fp8-draft262K—$1$1
qwen3-1p7b131K—$1$1
qwen3-235b-a22b131K—$1$1
qwen3-30b-a3b-instruct-2507262K—$1$1
qwen3-30b-a3b-thinking-2507262K—$1$1
qwen3-30b-a3b131K—$1$1
qwen3-32b131K—$1$1
qwen3-4b-instruct-2507262K—$1$1
qwen3-4b41K—$1$1
qwen3-coder-30b-a3b-instruct262K—$1$1
qwen3-coder-480b-a35b-instruct262K—$1$1
qwen3-coder-480b-instruct-bf16262K—$1$1
qwen3-embedding-0p6b33K—$1$1
qwen3-embedding-4b41K—$1$1
qwen3-embedding-8b41K—$1$1
qwen3-next-80b-a3b-instruct——$1$1
qwen3-next-80b-a3b-thinking——$1$1
qwen3-omni-30b-a3b-instruct66K—$1$1
qwen3-reranker-0p6b41K—$1$1
qwen3-reranker-4b41K—$1$1
qwen3-vl-235b-a22b-instruct262K—$1$1
qwen3-vl-235b-a22b-thinking262K—$1$1
qwen3-vl-32b-instruct129K—$1$1
qwen3-vl-8b-instruct262K—$1$1
qwen3p5-122b-a10b262K—$1$1
qwen3p5-27b262K—$1$1
qwen3p5-35b-a3b262K—$1$1
qwen3p5-397b-a17b262K—$1$1
qwen3p5-9b262K—$1$1
qwen3p6-27b262K—$1$1
qwen3p6-35b-a3b262K—$1$1

API

GET/v1/models/fireworks/fireworks/qwen3-30b-a3b-thinking