tokenstat
tokenstat

Qwen3 235B A22B Instruct

Qwen/Qwen3-235B-A22B-Instruct-2507 · rates as of · Benchmarks · AI plans · Calculator

Qwen instruction model for multilingual chat, reasoning, and tool use

Cheapest input
$0
$/MTok · models.dev
Cheapest output
$0
$/MTok
Context
262K
tokens
Sources
2
33 listings

Price changes

Cheapest list input/output only. Rates move rarely, so this is an event log. Down means cheaper. Showing the 8 latest changes.

  • ↑ higherOutput $0.408 → $0.455
  • ↑ higherInput $0.062 → $0.069

Sources

Same model, different sources. Our first-party rate is listed first, then router and aggregator rows stay separate so you can see the spread instead of a single blended number. Showing free/$0 listings. Hide them.

SourceProviderInputOutputCache readContext
models.devcheapestQwen/Qwen3-235B-A22B-Instruct-2507ModelScope$0$0$0262K
models.devqwen3-235b-a22b-instruct-2507Cortecs$0.069$0.455$0.018262K
models.devQwen/Qwen3-235B-A22B-Instruct-2507DeepInfra$0.09$0.55$0.009262K
models.devqwen/qwen3-235b-a22b-instruct-2507Novita AI$0.09$0.58$0131K
models.devqwen3-235b-a22b-instruct-2507DevPass (LLM Gateway)$0.09$0.58$0262K
models.devnovita/qwen3-235b-a22b-instruct-2507LLM Gateway$0.09$0.58$0131K
models.devQwen/Qwen3-235B-A22B-Instruct-2507Meganova$0.09$0.6$0262K
LiteLLMQwen/Qwen3-235B-A22B-Instruct-2507N/A$0.09$0.55$0.009N/A
LiteLLMQwen3-235B-A22B-Instruct-2507N/A$0.09$0.55$0.009N/A
LiteLLMnovita/qwen/qwen3-235b-a22b-instruct-2507N/A$0.09$0.58$0.009N/A
models.devqwen/qwen3-235b-a22b-instruct-2507Merge Gateway$0.1$0.6$0.05131K
LiteLLMwandb/Qwen/Qwen3-235B-A22B-Instruct-2507N/A$0.1$0.1$0.01N/A
models.devqwen/qwen3-235b-a22b-instruct-2507NanoGPT$0.13$0.5$0.065262K
models.devQwen/Qwen3-235B-A22B-Instruct-2507Abacus$0.13$0.6$0262K
models.devqwen3-235b-a22b-instruct-2507Venice AI$0.15$0.75$0128K
models.devqwen/qwen3-235b-a22b-instruct-2507Jiekou.AI$0.15$0.8$0131K
models.devQwen/Qwen3-235B-A22B-Instruct-2507Submodel$0.2$0.3$0262K
models.devQwen/Qwen3-235B-A22B-Instruct-2507Nebius$0.2$0.6$0.02262K
models.devQwen/Qwen3-235B-A22B-Instruct-2507Crusoe$0.22$0.8$0.11262K
models.devvertex-openai/qwen3-235b-a22b-instruct-2507LLM Gateway$0.22$0.88$0262K
LiteLLMaccounts/fireworks/models/qwen3-235b-a22b-instruct-2507N/A$0.22$0.88$0.022N/A
LiteLLMfireworks_ai/accounts/fireworks/models/qwen3-235b-a22b-instruct-2507N/A$0.22$0.88$0.022N/A
models.devqwen/qwen3-235b-a22b-instruct-2507Eden AI$0.23$0.92$0131K
LiteLLMqwen/qwen3-235b-a22b-instruct-2507N/A$0.264$1.06$0.0264N/A
LiteLLMqwen3-235b-a22b-instruct-2507N/A$0.264$1.06$0.0264N/A
LiteLLMreplicate/qwen/qwen3-235b-a22b-instruct-2507N/A$0.264$1.06$0.0264N/A
models.devqwen3-235b-a22b-instruct-2507302.AI$0.29$1.14$0128K
models.devcerebras/qwen3-235b-a22b-instruct-2507LLM Gateway$0.6$1.20$0262K
models.devqwen3-235b-a22b-instruct-2507Scaleway$0.75$2.25$0.075260K
models.devQwen/Qwen3-235B-A22B-Instruct-2507Hugging Face$0.855$2.56$0262K
models.devqwen3-235b-a22b-instruct-2507GreenPT$1.03$3.08$0262K
models.devQwen/Qwen3-235B-A22B-Instruct-2507Pioneer$1.20$1.20$1.20262K
LiteLLMcrusoe/Qwen/Qwen3-235B-A22B-Instruct-2507N/A$3$3$0.3N/A

Capabilities

  • Reasoning
  • Tool calling
  • Structured output
  • Open weights
  • In: text
  • Out: text
Knowledge cutoff: 2025-04Released: 2025-07-30Family: qwen

Run this model in a real workspace

Launch agents from the project they work in, use remote management to reach another machine, and see this model's sessions and token usage in your own history. Free to use, runs on your device.

CLI for macOS, Linux, and Windows

Data and list-price estimates may contain mistakes. Not investment advice.