Qwen3 1p7b Fp8 Draft

Qwen3 1p7b Fp8 Draft is a text model from Fireworks AI with a context window of 262K tokens and max output of 262K tokens. Pricing starts at 0.10 per million input tokens and 0.10 per million output tokens.

Capabilities

Vision Function Calling Reasoning JSON Schema System Messages Web Search Prompt Caching Audio Input Audio Output

Specifications

Model Keyfireworks_ai/accounts/fireworks/models/qwen3-1p7b-fp8-draft
ProviderFireworks AI
Provider IDfireworks_ai
ModeText
Canonical Nameqwen-3-1.7b-fp8-draft
Context Window262K tokens
Max Output262K tokens

Pricing

TypePer 1K TokensPer 1M Tokens
Input Tokens0.0001000.100
Output Tokens0.0001000.100

Benchmarks

Intelligence Index8.0#220
Coding Index1.4#170
Math Index38.7#67
MMLU-Pro0.6#153
GPQA0.4#182
HLE0.0#113
LiveCodeBench0.3#106
AIME0.5#30
IFBench0.3#152
Time to First Token0.89s#157
SciCode0.0#211
MATH-5000.9#42
AIME 20250.4#67
LCR0.0#151
TerminalBench Hard0.0#148
TAU20.3#99