theserverless.dev InferenceList

Models / Alibaba

Qwen: Qwen3.8 27B

qwen/qwen3.8-27b

text image videoContext 1M

Qwen3.8 27B is an open-weight dense vision-language model from Qwen. It is suited for coding, professional workflows, research, multimodal interaction, and long-running agent tasks, with flexible thinking that can be...

Price

Input$0.15

per 1M tokens

Output$1.875

per 1M tokens

Cheaper on Chutes (−64.3%) versus the lab price

Compare this model

Providers

Each row is one seller. Prices are the published rate from that source. A dash means that source did not publish the amount. Sorted by a 3:1 blend of input and output.

ProviderTagQuant InputOutput ContextUptimeStatusSource
Chutes chutes/fp8 fp8 $0.039/1M $1.25/1M 262K 100% Live openrouter-endpoints
NEAR AI — — $0.04/1M $1.35/1M 262K — Listed nearai
NEAR AI near-ai/fp8 fp8 $0.04/1M $1.35/1M 262K 100% Live openrouter-endpoints
Darkbloom darkbloom/fp4 fp4 $0.035/1M $1.5/1M 262K 97% Live openrouter-endpoints
Ionstream ionstream/fp8 fp8 $0.04/1M $1.95/1M 262K 100% Live openrouter-endpoints
Reka reka/fp8 fp8 $0.04/1M $2.2/1M 262K 100% Live openrouter-endpoints
DeepInfra
Price differs from the host list
deepinfra/bf16 bf16 $0.15/1M $1.875/1M 262K 100% Live openrouter-endpoints
Modal modal — $0.04/1M $2.3/1M 262K 100% Live openrouter-endpoints
Tenstorrent tenstorrent/fp4 fp4 $0.15/1M $2/1M 262K 100% Live openrouter-endpoints
Wafer wafer/fp8 fp8 $0.06/1M $2.3/1M 262K 100% Live openrouter-endpoints
DekaLLM dekallm — $0.04/1M $2.5/1M 262K 100% Live openrouter-endpoints
AkashML akashml/fp8 fp8 $0.225/1M $1.98/1M 262K 100% Live openrouter-endpoints
Parasail parasail/fp8 fp8 $0.24/1M $2.2/1M 262K 100% Live openrouter-endpoints
Mancer 2 mancer/fp8 fp8 $0.18/1M $2.5/1M 262K 100% Live openrouter-endpoints
DeepInfra
Price differs from OpenRouter
— — $0.2/1M $2.5/1M 262K — Listed deepinfra
ModelRun modelrun/fp4 fp4 $0.2/1M $2.5/1M 262K 100% Live openrouter-endpoints
Phala — — $0.2/1M $2.5/1M 1M — Listed phala
Phala phala — $0.2/1M $2.5/1M 1M 100% Live openrouter-endpoints
Io Net — fp8 $0.426/1M $2.518/1M 66K — Listed ionet
Alibaba alibaba — $0.425/1M $2.55/1M 1M 100% Live openrouter-endpoints
CoreWeave coreweave/fp8 fp8 $0.4/1M $3/1M 262K 100% Live openrouter-endpoints
Novita — — $0.42/1M $3/1M 1M — Listed novita
Novita novita — $0.42/1M $3/1M 1M 100% Live openrouter-endpoints
Cerebras — fp16/fp8 $0.99/1M $1.49/1M 66K — Listed cerebras
Cerebras cerebras/fp16 fp16 $0.99/1M $1.49/1M 66K 100% Live openrouter-endpoints
AtlasCloud — fp8 $0.5/1M $3/1M 1.0M — Listed atlascloud
Cloudflare — — $0.45/1M $3.2/1M — — Listed cloudflare-pricing
Cloudflare cloudflare — $0.45/1M $3.2/1M 262K — Live openrouter-endpoints
Venice venice/fp8 fp8 $0.45/1M $3.2/1M 262K 100% Live openrouter-endpoints
OVHcloud — — $0.47/1M $3.19/1M 262K — Listed ovh
Groq — — Not published— Not published— 131K — Listed groq

Monthly bill

Token models use the token counts. Image, video, and audio models use units times the flat rate.

$2.03 at list price for this workload

Cache

Cache read$0.0375

per 1M tokens

Every rate
UnitInputOutputFlatConfidence
token $0.15/1M $1.875/1M Not published— official

Price history

Qwen: Qwen3.8 27B
5 0 2026-09-15: $0.2142026-09-16: $0.2142026-09-17: $0.2142026-09-18: $0.2142026-09-19: $0.2142026-09-20: $0.22026-09-21: $0.422026-09-22: $0.422026-09-23: $0.422026-09-24: $0.422026-09-25: $0.422026-09-26: $0.422026-09-27: $0.422026-09-28: $0.422026-09-29: $0.02492026-09-30: $0.02492026-10-01: $0.422026-10-02: $0.422026-10-03: $0.422026-10-04: $0.4252026-10-05: $0.4252026-10-06: $0.4252026-10-07: $0.4252026-10-08: $0.4252026-10-09: $0.4252026-10-10: $0.4252026-10-11: $0.042026-10-12: $0.042026-10-13: $0.042026-10-14: $0.042026-10-15: $0.242026-10-16: $0.242026-10-17: $0.242026-10-18: $0.242026-10-19: $0.242026-10-20: $0.042026-10-21: $0.042026-10-22: $0.042026-10-23: $0.22026-10-24: $0.22026-10-25: $0.22026-10-26: $0.22026-10-27: $0.22026-10-28: $0.0392026-10-29: $0.0392026-10-30: $0.15 2026-09-15 2026-10-30

input or flat output

Daily snapshots
UTC dateUnitInputOutputFlat
2026-09-15 token $0.214 $2.55 Not published—
2026-09-16 token $0.214 $2.55 Not published—
2026-09-17 token $0.214 $2.55 Not published—
2026-09-18 token $0.214 $2.55 Not published—
2026-09-19 token $0.214 $2.55 Not published—
2026-09-20 token $0.2 $2.55 Not published—
2026-09-21 token $0.42 $3 Not published—
2026-09-22 token $0.42 $3 Not published—
2026-09-23 token $0.42 $3 Not published—
2026-09-24 token $0.42 $3 Not published—
2026-09-25 token $0.42 $3 Not published—
2026-09-26 token $0.42 $3 Not published—
2026-09-27 token $0.42 $3 Not published—
2026-09-28 token $0.42 $3 Not published—
2026-09-29 token $0.0249 $4.4 Not published—
2026-09-30 token $0.0249 $2.99 Not published—
2026-10-01 token $0.42 $3 Not published—
2026-10-02 token $0.42 $3 Not published—
2026-10-03 token $0.42 $3 Not published—
2026-10-04 token $0.425 $2.55 Not published—
2026-10-05 token $0.425 $2.55 Not published—
2026-10-06 token $0.425 $2.55 Not published—
2026-10-07 token $0.425 $2.55 Not published—
2026-10-08 token $0.425 $2.55 Not published—
2026-10-09 token $0.425 $2.55 Not published—
2026-10-10 token $0.425 $2.55 Not published—
2026-10-11 token $0.04 $2.3 Not published—
2026-10-12 token $0.04 $2.3 Not published—
2026-10-13 token $0.04 $2.3 Not published—
2026-10-14 token $0.04 $2.3 Not published—
2026-10-15 token $0.24 $2.2 Not published—
2026-10-16 token $0.24 $2.2 Not published—
2026-10-17 token $0.24 $2.2 Not published—
2026-10-18 token $0.24 $2.2 Not published—
2026-10-19 token $0.24 $2.2 Not published—
2026-10-20 token $0.04 $1.35 Not published—
2026-10-21 token $0.04 $1.35 Not published—
2026-10-22 token $0.04 $1.35 Not published—
2026-10-23 token $0.2 $2.5 Not published—
2026-10-24 token $0.2 $2.5 Not published—
2026-10-25 token $0.2 $2.5 Not published—
2026-10-26 token $0.2 $2.5 Not published—
2026-10-27 token $0.2 $2.5 Not published—
2026-10-28 token $0.039 $1.25 Not published—
2026-10-29 token $0.039 $1.25 Not published—
2026-10-30 token $0.15 $1.875 Not published—

Alternatives

Parameters (21)
frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_tokensmin_ppresence_penaltyreasoningreasoning_effortrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_atop_ktop_logprobstop_p
Call this model

OpenRouter id qwen/qwen3.8-27b. InferenceList does not send the request.

curl
curl https://openrouter.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $OPENROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"qwen/qwen3.8-27b","messages":[{"role":"user","content":"Hello"}]}'

JavaScript
await fetch("https://openrouter.ai/api/v1/chat/completions", {
  method: "POST",
  headers: {
    Authorization: "Bearer " + process.env.OPENROUTER_API_KEY,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    model: "qwen/qwen3.8-27b",
    messages: [{ role: "user", content: "Hello" }],
  }),
});

Python
import os, json, urllib.request
req = urllib.request.Request(
    "https://openrouter.ai/api/v1/chat/completions",
    data=json.dumps({"model": "qwen/qwen3.8-27b", "messages": [{"role": "user", "content": "Hello"}]}).encode(),
    headers={"Authorization": "Bearer " + os.environ["OPENROUTER_API_KEY"], "Content-Type": "application/json"},
)
print(urllib.request.urlopen(req).read().decode())

JSON · History JSON