Qwen3 Coder Next
Qwen · Open weights · Released Feb 4, 2026 · qwen/qwen3-coder-next
Best $0.12 in / $0.80 out via Parasail · bf16
262K contextToolsStructured outputPrompt cachingOpen weights
Available from 4 providersUSD / MTOK · PRICES 23 MINUTES AGO · SPEED 5 MINUTES AGO
EST. MONTHLY COSTclick a row for detail · click headers to sort
| PROVIDER | INPUT | OUTPUT | CACHE | CONTEXT | QUANT | TTFT | TPS | UPTIME |
|---|---|---|---|---|---|---|---|---|
 Parasail | $0.12 | $0.80 | $0.07 | 262K | bf16 | ✕ | ✕ | 100.0% |
 StreamLake | $0.18 | $0.90 | $0.036 | 256K | — | 1.6s | 161 tok/s | 100.0% |
 Novita | $0.20 | $1.50 | — | 262K | fp8 | 3s | 177 tok/s | 100.0% |
 Alibaba | $0.30 | $1.50 | — | 262K | — | ✕ | ✕ | 100.0% |
TTFT/TPS: median (P50) over trailing 504h · chat10k profile (~10K in / 200 out) · measured via OpenRouter routing · ✕ = probed, endpoint returned no measurable stream · methodology v1.1 · measured 5 minutes ago
SERVE THIS MODEL AND NOT LISTED? LIST YOUR INFERENCE →
Pricing variants · USD / MTok in / out
STANDARD
$0.12 / $0.80
per MTok in / out
CACHE READ $0.07
Recent changesRSS ↗
Oct 5, 2026endpoint removed · primeintellect5 → 4
Oct 4, 2026endpoint added · primeintellect4 → 5
About
Qwen3-Coder-Next is an open-weight causal language model optimized for coding agents and local development workflows. It uses a sparse MoE design with 80B total parameters and only 3B activated per...
Specifications
Context window262,144
Max output235,929
Modalities intext
Modalities outtext
LicenseOpen weights
ReleasedFeb 4, 2026
TokenizerQwen
WeightsHugging Face ↗
Related
Embed badge
[](https://modelindex.ai/models/qwen/qwen3-coder-next)Sources
OpenRouter API23 minutes ago
AGGREGATORHugging Face23 minutes ago
COMMUNITYModelIndex benchmarks11 days ago
MEASUREDVerified 23 minutes ago · list prices, not negotiated rates.