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$0.04 / $2.30
Context1M
ReleasedAug 14, 2026
Providers
19 providers serve this model upstream.
| Provider | Input /M | Output /M | Cache read /M | Latency P50 | Throughput P50 | Uptime |
|---|---|---|---|---|---|---|
| $0.04 | $2.20 | $0.02 | 0.47s | 52 tps | 100% | |
| $0.04 | $2.30 | $0.02 | 0.45s | 59 tps | 100% | |
| $0.99 | $1.49 | $0.99 | 0.31s | 549 tps | 100% | |
| $0.24 | $2.20 | $0.05 | 1.25s | 22 tps | 99.97% | |
| $0.04 | $1.25 | $0.00 | 2.33s | 29 tps | 99.94% | |
| $0.42 | $2.55 | $0.09 | 1.99s | 48 tps | 99.89% | |
| $0.23 | $1.98 | $0.05 | 1.16s | 34 tps | 99.86% | |
 NEAR AIfp8 | $0.04 | $1.35 | $0.02 | 1.14s | 67 tps | 99.83% |
| $0.42 | $3.00 | $0.09 | 1.51s | 39 tps | 99.82% | |
| $0.04 | $2.50 | $0.02 | 0.51s | 145 tps | 99.81% | |
| $0.45 | $3.20 | Variable | 0.88s | 117 tps | 99.79% | |
| $0.20 | $2.50 | Variable | 0.82s | 61 tps | 99.76% | |
 ModelRun [by Modular]fp4 | $0.20 | $2.50 | $0.09 | 0.28s | 191 tps | 99.69% |
| $0.20 | $2.50 | $0.05 | 0.82s | 95 tps | 99.6% | |
| $0.09 | $2.35 | $0.09 | 0.80s | 62 tps | 98.72% | |
| $0.45 | $3.20 | $0.05 | 0.57s | 34 tps | 98.36% | |
 Darkbloomfp4 | $0.04 | $2.20 | $0.02 | 6.17s | 21 tps | 97.34% |
 DeepInfraus · bf16 | $0.15 | $1.88 | $0.04 | 41.34s | 3 tps | 95.91% |
 CoreWeavefp8 | $0.40 | $3.00 | $0.15 | 0.54s | 56 tps | 94.06% |
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
$0.04
per 1M tokens
Output
$2.30
per 1M tokens
Cache read
$0.02
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 11, 12 AMOct 11, 8 AMOct 11, 4 PMOct 12, 12 AMOct 12, 8 AMOct 12, 4 PMOct 13, 12 AMOct 13, 8 AMOct 13, 4 PMOct 14, 12 AMOct 14, 8 AM
Reka AI AkashML DekaLLM NEAR AI Mancer NovitaAI Phala Wafer Parasail Cerebras Chutes CoreWeave Venice DeepInfra (us) ModelRun [by Modular] Ionstream Alibaba Cloud Int. Darkbloom Cloudflare
0 tok/s1000 tok/s2000 tok/s3000 tok/s4000 tok/s
Oct 11, 12 AMOct 11, 8 AMOct 11, 4 PMOct 12, 12 AMOct 12, 8 AMOct 12, 4 PMOct 13, 12 AMOct 13, 8 AMOct 13, 4 PMOct 14, 12 AMOct 14, 8 AM
Reka AI AkashML DekaLLM NEAR AI Mancer NovitaAI Phala Wafer Parasail Cerebras Chutes CoreWeave Venice DeepInfra (us) ModelRun [by Modular] Ionstream Alibaba Cloud Int. Darkbloom Cloudflare
Uptime
100% of requests were served successfully over the last 3 days, across all providers.
Last 3 daysAvailability 99.68%
Oct 11, 2:00 PMNow
Availability over the last 24 hoursAvailability 99.72%
100% 98% 97% 95%
Oct 13, 2:50 PMNow
Apps
Tools that most often run Qwen3.8 27B, by tokens this week.
Activity
1725.2B tokens processed market-wide in the last month.
050.0B100.0B150.0B200.0B
Sep 14Sep 19Sep 24Sep 29Oct 4Oct 9Oct 14
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 http://192.168.1.55/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 $0.04 per 1M input tokens and $2.30 per 1M output tokens.
Who built Qwen3.8 27B?
Qwen, in the Qwen3.8 family.
Explore
Other models your pass can call.
