Start free trial

Qwen: Qwen3 235B A22B Instruct 2507

qwen/qwen3-235b-a22b-2507
CompareAPITry this model

Qwen3-235B-A22B-Instruct-2507 is a multilingual, instruction-tuned mixture-of-experts language model based on the Qwen3-235B architecture, with 22B active parameters per forward pass.

Modalities
In / out per 1M$0.09 / $0.55
Context256K
ReleasedJul 21, 2025

Providers

7 providers serve this model upstream.

Providers serving this model
ProviderInput /MOutput /MCache read /MLatency P50Throughput P50Uptime
Parasailfp8$0.14$0.80$0.050.53s27 tps100%
Google Vertexus-south1$0.22$0.88Variable0.99s37 tps99.74%
Google Vertexus-south1$0.25$1.00Variable0.68s38 tps99.71%
Venicefp8$0.15$0.75Variable0.89s11 tps96.9%
DeepInfraus · fp8$0.09$0.55Variable0.54s11 tps95.05%
Nebius Token Factoryfp8$0.20$0.60Variable0.47s39 tps84.81%
GMICloudfp8$0.09$0.35$0.02——0%

Market-wide measurements, refreshed every 15 minutes. They describe who serves Qwen3 235B A22B Instruct 2507 in general, not how ProjectCOZY routes your requests.

Pricing

List rates per 1M tokens — what Qwen3 235B A22B Instruct 2507 costs pay-as-you-go elsewhere, not what you pay here.

Input
$0.09
per 1M tokens
Output
$0.55
per 1M tokens
Cache read
—
not published
Included in every pass
Qwen3 235B A22B Instruct 2507 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.

0.0s2.5s5.0s7.5s10.0s
Oct 16, 12 AMOct 16, 8 AMOct 16, 4 PMOct 17, 12 AMOct 17, 8 AMOct 17, 4 PMOct 18, 12 AMOct 18, 8 AMOct 18, 4 PMOct 19, 12 AMOct 19, 8 AM
Nebius Token Factory Google Vertex (us-south1) Parasail Google Vertex (us-south1) DeepInfra (us) Venice
0 tok/s100 tok/s200 tok/s300 tok/s400 tok/s
Oct 16, 12 AMOct 16, 8 AMOct 16, 4 PMOct 17, 12 AMOct 17, 8 AMOct 17, 4 PMOct 18, 12 AMOct 18, 8 AMOct 18, 4 PMOct 19, 12 AMOct 19, 8 AM
Nebius Token Factory Google Vertex (us-south1) Parasail Google Vertex (us-south1) DeepInfra (us) Venice

Uptime

100% of requests were served successfully over the last 3 days, across all providers.

Last 3 daysAvailability 99.69%
Oct 16, 10:00 AMNow
Availability over the last 24 hoursAvailability 99.59%
100% 98% 97% 95%
Oct 18, 10:20 AMNow

Apps

Tools that most often run Qwen3 235B A22B Instruct 2507, by tokens this week.

SkyrimNetGame · 47.3% of tokens9.9BLibrArIaN14.7% of tokens3.1BOpenClawPersonal Agent · 13.6% of tokens2.9BHermes AgentPersonal Agent · 12.3% of tokens2.6BBitsec12.1% of tokens2.5B

Activity

294.9B tokens processed market-wide in the last month.

05.0B10.0B15.0B20.0B
Sep 19Sep 24Sep 29Oct 4Oct 9Oct 14Oct 19
Tokens

FAQ

Which model id do I use for Qwen3 235B A22B Instruct 2507?
qwen/qwen3-235b-a22b-2507. Send it as the model field from any OpenAI-compatible client, against http://192.168.1.55/v1.
How much context does Qwen3 235B A22B Instruct 2507 hold?
262,144 tokens per request, of which up to 16,384 can be the response.
What can it accept and return?
Input: text. Output: text.
What does Qwen3 235B A22B Instruct 2507 cost on a pass?
Nothing beyond the pass itself. Pay-as-you-go elsewhere it lists at $0.09 per 1M input tokens and $0.55 per 1M output tokens.
How current is its knowledge?
Training data runs to Jun 2025. Anything later has to come from your prompt or a tool call.
Who built Qwen3 235B A22B Instruct 2507?
Qwen, in the Qwen3 family.

Explore

Other models your pass can call.

Aion 3.5aion-labs/aion-3.5256KAionAion 3.5 Miniaion-labs/aion-3.5-mini256KAionAion-2.0aion-labs/aion-2.0128KAionAion-3.0aion-labs/aion-3.0128KAionAion-3.0-Miniaion-labs/aion-3.0-mini128KAionAion-RP 1.0 (8B)aion-labs/aion-rp-llama-3.1-8b32KAion