Pricingby GlyphQwen3 235B A22B Instruct 2507
Qwen (Alibaba) · Open weights · 262K context · released Jul 21, 2025 · checked 13h ago
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.
Ways to buy 4
| Way to buy | Input | Output | In / out per 1M | Cached | Vs cheapest |
|---|---|---|---|---|---|
fp8 | $0.09 | $0.55 | $0.09 / $0.55Cheapest | n/a | Cheapest |
fp8 | $0.15 | $0.75 | $0.15 / $0.75+46% vs cheapest | n/a | +46% vs cheapest |
fp8 · cached $0.05 | $0.14 | $0.8 | $0.14 / $0.8+49% vs cheapest | $0.05 | +49% vs cheapest |
| GMICloud fp8 · cached $0.07 | $0.35 | $1.4 | $0.35 / $1.4+199% vs cheapest | $0.07 | +199% vs cheapest |
USD per 1M tokens. Regions are separate routes.
Through a gateway
Your own numbers100M input and 20M output tokens a month: $20.00 direct.
Kong AI Gateway$20.00+0%
LiteLLM$20.00+0%
Eden AI$21.10+5.5%
OpenRouter$21.10+5.5%
Cloudflare AI GatewayNot offeredNot offered
HeliconeNot offeredNot offered
Neon AI GatewayNot offeredNot offered
RequestyNot offeredNot offered
TrueFoundry AI GatewayNot offeredNot offered
Vercel AI GatewayNot offeredNot offered
A dash: not on that gateway's own model list. No published token fee: Martian Gateway, Portkey.
Related models
| In / out per 1M | Cheapest route | |||||||
|---|---|---|---|---|---|---|---|---|
Qwen (Alibaba) · 1M | $4 | $12 | $4 / $12 | $6 | 1M | Lab list price | · | Qwen3.8 Max Prime is a higher-throughput variant of Qwen3.8 Max from Alibaba's Qwen team, served as a separate SKU at a higher price point. |
Qwen (Alibaba) · 1M | $0.15 | $0.47 | $0.15 / $0.47 | $0.23 | 1M | Lab list price | · | Qwen3.8 Omni Flash is an omni-modal reasoning model from Alibaba, the first Qwen model built around agentic capabilities with native audio-video understanding. |
Qwen (Alibaba) · 1M | $2 | $6 | $2 / $6 | $3 | 1M | Lab list price | · | Qwen3.8 Max 0902 is an updated snapshot of Qwen3.8 Max from Alibaba's Qwen team. |
Qwen (Alibaba) · 1M | $0.15 | $0.47 | $0.15 / $0.47 | $0.23 | 1M | Lab list price | · | Qwen3.8 Flash is a multimodal reasoning model from Alibaba. |
DeepSeek · 1MCheapest: $0.081 on Particle AI (us-flex) | $0.15 | $0.6 | $0.15 / $0.6 | $0.262 | 1M | $0.081 on Particle AI (us-flex) | · | DeepSeek V4.1 Flash 1017 is the October 17, 2026 snapshot of DeepSeek V4.1 Flash, served by DeepSeek under the deepseek-flash API model name. |
DeepSeek · 1M | $0.045 | $0.3 | $0.045 / $0.3 | $0.109 | 1M | on InferenceNet (fp8) | · | DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture. |
Anthropic · 1M | $0.1 | $0.5 | $0.1 / $0.5 | $0.2 | 1M | Lab list price | · | Claude Haiku 5.5 is Anthropic's small, fast model for high-volume, cost-sensitive work such as summarization, subagents, and browser use. |
NVIDIA · 1M | $0.06 | $0.35 | $0.06 / $0.35 | $0.133 | 1M | on Darkbloom (nvfp4) | · | NVIDIA Nemotron 3.5 Super VL is an open multimodal mixture-of-experts model from NVIDIA, with 12B active parameters out of 120B total. |
About Qwen3 235B A22B Instruct 2507
Takes text in and returns text. First listed Sep 23, 2026. Up to 118K output tokens. Blended price $0.205 per 1M tokens at 3 input to 1 output. Model id qwen3-235b-a22b-2507.
Price history
List price since Sep 23, 2026, from daily reads of the OpenRouter catalog.
Across GlyphCompany profile
Questions
How much does Qwen3 235B A22B Instruct 2507 cost?
$0.09 per million input tokens and $0.55 per million output tokens.
What is the context window of Qwen3 235B A22B Instruct 2507?
262K tokens, with up to 118K tokens of output.
Where is Qwen3 235B A22B Instruct 2507 cheapest?
Of 4 routes tracked, DeepInfra is cheapest at $0.09 input and $0.55 output per million tokens.