Qwen3 235B A22B Thinking 2507
Qwen reasoning model for deliberate problem solving, math, and coding
Cheapest input
$0.1
$/MTok · models.dev
Cheapest output
$0.1
$/MTok
Context
262K
tokens
Offers
24
3 sources
Offers
Same model, different listings. First-party, router, and aggregator rows stay separate so you can see the spread instead of a single blended number. Free/$0 listings are hidden by default (2 omitted). Show free/$0 offers.
| Source | Provider | Input | Output | Cache read | Context |
|---|---|---|---|---|---|
| models.devcheapestQwen/Qwen3-235B-A22B-Thinking-2507 | Weights & Biases | $0.1 | $0.1 | $0.1 | 262K |
| models.devQwen/Qwen3-235B-A22B-Thinking-2507 | IO.NET | $0.11 | $0.6 | $0.055 | 262K |
| LiteLLMopenrouter/qwen/qwen3-235b-a22b-thinking-2507 | — | $0.11 | $0.6 | $0.011 | — |
| LiteLLMqwen/qwen3-235b-a22b-thinking-2507 | — | $0.11 | $0.6 | $0.011 | — |
| LiteLLMqwen3-235b-a22b-thinking-2507 | — | $0.11 | $0.6 | $0.011 | — |
| models.devQwen/Qwen3-235B-A22B-Thinking-2507 | SiliconFlow (China) | $0.13 | $0.6 | $0 | 262K |
| models.devQwen/Qwen3-235B-A22B-Thinking-2507 | SiliconFlow | $0.13 | $0.6 | $0 | 262K |
| models.devQwen/Qwen3-235B-A22B-Thinking-2507 | Submodel | $0.2 | $0.6 | $0 | 262K |
| LiteLLMaccounts/fireworks/models/qwen3-235b-a22b-thinking-2507 | — | $0.22 | $0.88 | $0.022 | — |
| LiteLLMfireworks_ai/accounts/fireworks/models/qwen3-235b-a22b-thinking-2507 | — | $0.22 | $0.88 | $0.022 | — |
| models.devqwen/qwen3-235b-a22b-thinking-2507 | Kilo Gateway | $0.23 | $2.30 | $0 | 131K |
| OpenRouterqwen/qwen3-235b-a22b-thinking-2507 | OpenRouter | $0.23 | $2.30 | $0 | 262K |
| models.devqwen/Qwen3-235B-A22B-Thinking-2507 | NanoGPT | $0.3 | $0.5 | $0 | 256K |
| models.devQwen/Qwen3-235B-A22B-Thinking-2507 | Hugging Face | $0.3 | $3 | $0 | 262K |
| models.devqwen/qwen3-235b-a22b-thinking-2507 | Jiekou.AI | $0.3 | $3 | $0 | 131K |
| models.devqwen/qwen3-235b-a22b-thinking-2507 | Novita AI | $0.3 | $3 | $0 | 131K |
| models.devqwen3-235b-a22b-thinking-2507 | LLM Gateway | $0.3 | $3 | $0 | 262K |
| LiteLLMQwen/Qwen3-235B-A22B-Thinking-2507 | — | $0.3 | $2.90 | $0.03 | — |
| LiteLLMQwen3-235B-A22B-Thinking-2507 | — | $0.3 | $2.90 | $0.03 | — |
| LiteLLMdeepinfra/Qwen/Qwen3-235B-A22B-Thinking-2507 | — | $0.3 | $2.90 | $0.03 | — |
| LiteLLMnovita/qwen/qwen3-235b-a22b-thinking-2507 | — | $0.3 | $3 | $0.03 | — |
| models.devqwen3-235b-a22b-thinking-2507 | Venice AI | $0.45 | $3.50 | $0 | 128K |
| LiteLLMtogether_ai/Qwen/Qwen3-235B-A22B-Thinking-2507 | — | $0.65 | $3 | $0.065 | — |
| LiteLLMwandb/Qwen/Qwen3-235B-A22B-Thinking-2507 | — | $10000 | $10000 | $1000 | — |
Capabilities
- Reasoning
- Tool calling
- Structured output
- Open weights
- In: text
- Out: text
Knowledge cutoff: 2025-04Released: 2025-07-25Family: qwen
Scores
Sparse coverage on purpose. Missing a score means we have not linked one yet, not that the model is unranked. Full boards on /benchmarks.
- AA intelligence19.6
- AA coding22.1
- AA agentic3.8
Sources: Arena AI, Artificial Analysis. See /benchmarks.