Qwen: Qwen3.8 27B
qwen/qwen3-8-27bQwen3.8 27B is an open-weight dense vision-language model from Qwen.
Modalities
In / out per 1M$0.15 / $1.88
Context1M
ReleasedAug 14, 2026
Providers
22 providers serve this model upstream.
| Provider | Input /M | Output /M | Cache read /M | Latency P50 | Throughput P50 | Uptime |
|---|---|---|---|---|---|---|
 Darkbloomfp4 | $0.04 | $1.50 | $0.02 | 0.80s | 64 tps | 100% |
| $0.42 | $3.00 | $0.09 | 6.49s | 32 tps | 100% | |
| $0.04 | $2.30 | $0.02 | 3.32s | 20 tps | 100% | |
| $0.45 | $3.20 | Variable | 1.24s | 45 tps | 100% | |
| $0.99 | $1.49 | $0.99 | 0.28s | 730 tps | 99.97% | |
 ModelRun [by Modular]fp4 | $0.20 | $2.50 | $0.09 | 0.42s | 98 tps | 99.95% |
| $0.04 | $2.20 | $0.02 | 0.47s | 51 tps | 99.95% | |
| $0.04 | $1.25 | $0.00 | 2.45s | 31 tps | 99.95% | |
| $0.06 | $2.30 | $0.06 | 1.06s | 80 tps | 99.92% | |
 NEAR AIfp8 | $0.04 | $1.35 | $0.02 | 1.96s | 49 tps | 99.9% |
| $0.15 | $2.00 | $0.05 | 0.52s | 106 tps | 99.86% | |
| $0.24 | $2.20 | $0.05 | 0.74s | 66 tps | 99.82% | |
 CoreWeavefp8 | $0.40 | $3.00 | $0.15 | 0.63s | 48 tps | 99.62% |
| $0.01 | $0.35 | $0.01 | 0.78s | 21 tps | 99.48% | |
| $0.04 | $2.50 | $0.02 | 0.74s | 106 tps | 99.09% | |
| $0.04 | $1.95 | $0.02 | 1.26s | 25 tps | 98.85% | |
 DeepInfraus · bf16 | $0.15 | $1.88 | $0.04 | 0.83s | 31 tps | 98.39% |
| $0.23 | $1.98 | $0.05 | 0.67s | 52 tps | 98.21% | |
| $0.45 | $3.20 | $0.05 | 0.41s | 38 tps | 96.72% | |
| $0.42 | $2.55 | $0.09 | 1.89s | 47 tps | 95.38% | |
| $0.18 | $2.50 | Variable | 0.87s | 66 tps | 94.24% | |
| $0.20 | $2.50 | $0.05 | 2.81s | 58 tps | 88.71% |
Market-wide measurements, refreshed every 15 minutes. They describe who serves Qwen3.8 27B in general, not how ProjectCOZY routes your requests.
Pricing
List rates per 1M tokens — what Qwen3.8 27B costs pay-as-you-go elsewhere, not what you pay here.
Input
$0.15
per 1M tokens
Output
$1.88
per 1M tokens
Cache read
$0.04
per 1M cached tokens
Included in every pass
Qwen3.8 27B is included in every ProjectCOZY pass at no extra cost — one flat rate, no per-token metering. The rates above are there for comparison.
Performance
Time to first token and output speed across every provider, over the last 3 days.
0.0s20.0s40.0s60.0s80.0s
Oct 29, 12 AMOct 29, 8 AMOct 29, 4 PMOct 30, 12 AMOct 30, 8 AMOct 30, 4 PMOct 31, 12 AMOct 31, 8 AMOct 31, 4 PMNov 1, 12 AMNov 1, 8 AM
Tenstorrent Reka AI AkashML DekaLLM NEAR AI NovitaAI Phala Darkbloom Wafer Parasail Cerebras Chutes CoreWeave Venice DeepInfra (us) ModelRun [by Modular] Ionstream Modal Alibaba Cloud Int. Mancer Cloudflare Prime Intellect
0 tok/s1000 tok/s2000 tok/s3000 tok/s4000 tok/s
Oct 29, 12 AMOct 29, 8 AMOct 29, 4 PMOct 30, 12 AMOct 30, 8 AMOct 30, 4 PMOct 31, 12 AMOct 31, 8 AMOct 31, 4 PMNov 1, 12 AMNov 1, 8 AM
Tenstorrent Reka AI AkashML DekaLLM NEAR AI NovitaAI Phala Darkbloom Wafer Parasail Cerebras Chutes CoreWeave DeepInfra (us) ModelRun [by Modular] Ionstream Modal Alibaba Cloud Int. Mancer Venice Cloudflare Prime Intellect
Uptime
100% of requests were served successfully over the last 3 days, across all providers.
Last 3 daysAvailability 99.64%
Oct 29, 6:00 PMNow
Availability over the last 24 hoursAvailability 99.69%
100% 97% 93% 90%
Oct 31, 6:10 PMNow
Apps
Tools that most often run Qwen3.8 27B, by tokens this week.
Activity
2199.3B tokens processed market-wide in the last month.
050.0B100.0B150.0B200.0B
Oct 2Oct 7Oct 12Oct 17Oct 22Oct 27Nov 1
Tokens
FAQ
Which model id do I use for Qwen3.8 27B?
qwen/qwen3.8-27b. Send it as the model field from any OpenAI-compatible client, against https://minuykh.app/v1.
How much context does Qwen3.8 27B hold?
1,000,000 tokens per request, of which up to 235,929 can be the response.
What can it accept and return?
Input: text, image, video. Output: text.
What does Qwen3.8 27B cost on a pass?
Nothing beyond the pass itself. Pay-as-you-go elsewhere it lists at $0.15 per 1M input tokens and $1.88 per 1M output tokens.
Who built Qwen3.8 27B?
Qwen, in the Qwen3.8 family.
Explore
Other models your pass can call.
