This model was retired on 2026-04-16. The pricing below is the last-known rate, kept for migration reference.

Qwen3 235B A22B Thinking 2507Deprecated

AlibabaReleasedApr 29, 2025KnowledgeApr 2025
Tool useReasoningStructured output
Context
262K
Max output
262K
Serving providers
5
Cheapest input
$0.22 /1M
Prices are on-demand list rates. Enterprise commitments (committed-use discounts, provisioned throughput, negotiated rates) can be materially lower.

Pricing by serving provider

last-known · per 1M tokens · click a provider to expand
Serving providerInput /1MOutput /1MEndpoints
Fireworks AI$0.22$0.881
OpenRouter$0.23$2.301
DeepInfra$0.30$2.901
Novita$0.30$3.001
Together AI$0.65$3.001

Price history

input + output $/1M since we started tracking
Input Output
$0.000$0.500$1.00Jul 30Oct 4Jan 13Jul 31$0.880$0.220

Cost calculator

estimate your monthly spend on this model
$114
estimated / month

Model IDs

copy the exact identifier for your platform
fireworks_ai/accounts/fireworks/models/qwen3-235b-a22b-thinking-2507qwen/qwen3-235b-a22b-thinking-2507deepinfra/Qwen/Qwen3-235B-A22B-Thinking-2507novita/qwen/qwen3-235b-a22b-thinking-2507together_ai/Qwen/Qwen3-235B-A22B-Thinking-2507

Frequently asked questions

Qwen3 235B A22B Thinking 2507 pricing, context and availability

Is Qwen3 235B A22B Thinking 2507 still available?

Qwen3 235B A22B Thinking 2507 was retired on 2026-04-16. The pricing on this page is the last-known rate, kept for migration reference.

How much did Qwen3 235B A22B Thinking 2507 cost?

Qwen3 235B A22B Thinking 2507's last-known pricing, before it was retired on 2026-04-16, was $0.22 per 1M input tokens and $0.88 per 1M output tokens.

What was the context window of Qwen3 235B A22B Thinking 2507?

Qwen3 235B A22B Thinking 2507 had a 262K token context window and could return up to 262K output tokens.

What could Qwen3 235B A22B Thinking 2507 do?

Qwen3 235B A22B Thinking 2507 supported tool use, reasoning and structured output.

Other Alibaba models

compare pricing across the Alibaba lineup
Pricing verified against LiteLLM + OpenRouter + provider pages · refreshed daily

Every weekday

AI moves fast. Here's your debrief.

News, analysis, tools, and more.

For people who build with AI