tokenstat
tokenstat

Qwen3.6 35B-A3B

Qwen/Qwen3.6-35B-A3B · rates as of · How this catalog is built · Benchmarks

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

Cheapest input
$0.045
$/MTok · models.dev
Cheapest output
$0.3
$/MTok
Context
1.0M
tokens
Sources
3
46 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.

Input $/MTok over sampled dates
Output $/MTok
  • ↓ lowerOutput $0.4 → $0.3
  • ↓ lowerInput $0.05 → $0.045
  • ↓ lowerOutput $0.42 → $0.4
  • ↓ lowerInput $0.07 → $0.05
  • ↓ lowerOutput $0.95 → $0.42
  • ↓ lowerInput $0.1 → $0.07

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. Free/$0 listings are hidden by default (2 omitted). Show free/$0 listings.

SourceProviderInputOutputCache readContext
models.devcheapestqwen3.6-35b-a3bEngy$0.045$0.3$0.015208K
LiteLLMQwen/Qwen3.6-35B-A3BN/A$0.05$0.4$0.02N/A
LiteLLMQwen3.6-35B-A3BN/A$0.05$0.4$0.02N/A
LiteLLMsail/Qwen/Qwen3.6-35B-A3BN/A$0.05$0.4$0.02N/A
models.devqwen3-6-35b-a3bEmpirioLabs AI$0.07$0.42$0.035131K
models.devqwen3.6-35b-a3bSaladCloud AI Gateway$0.09$0.6$0262K
models.devqwen/qwen3.6-35b-a3bKilo Gateway$0.1$0.9$0.025262K
OpenRouterqwen/qwen3.6-35b-a3bOpenRouter$0.1$0.9$0.025262K
models.devQwen/Qwen3.6-35B-A3BDeepInfra$0.1$0.95$0.1262K
models.devQwen/Qwen3.6-35B-A3BCoreWeave$0.1$0.95$0.05262K
models.devqwen3-6-35b-a3bVenice AI$0.1$1$0256K
models.devqwen/qwen3.6-35b-a3bNanoGPT$0.112$0.8$0.0561.0M
models.devqwen/qwen3.6-35b-a3b:thinkingNanoGPT$0.112$0.8$0.0561.0M
LiteLLMpinstripes/ps/qwen3.6-35b-a3bN/A$0.14$0.45$0.014N/A
LiteLLMps/qwen3.6-35b-a3bN/A$0.14$0.45$0.014N/A
models.devQwen/Qwen3.6-35B-A3BHugging Face$0.15$0.95$0262K
models.devqwen/qwen3.6-35b-a3bAmbient$0.15$1$0.15262K
LiteLLMlibertai/qwen3.6-35b-a3bN/A$0.15$0.5$0.015N/A
LiteLLMlibertai/qwen3.6-35b-a3b-thinkingN/A$0.15$0.5$0.015N/A
LiteLLMqwen3.6-35b-a3b-thinkingN/A$0.15$0.5$0.015N/A
models.devalibaba/qwen3.6-35b-a3bZenifra$0.19$0.48$0262K
models.devTEE/qwen3.6-35b-a3bNanoGPT$0.2$1.27$0.1262K
LiteLLMzerogpu/qwen3.6-35b-a3bN/A$0.2$1.50$0.2N/A
models.devQwen/Qwen3.6-35B-A3BSiliconFlow$0.24$1.80$0.15262K
models.devqwen/qwen3.6-35b-a3bMerge Gateway$0.248$1.49$0.0496262K
models.devqwen/qwen3.6-35b-a3bNovita AI$0.248$1.49$0262K
models.devqwen/qwen3.6-35b-a3bOrcaRouter$0.248$1.49$0262K
models.devnovita/qwen3.6-35b-a3bLLM Gateway$0.248$1.49$0262K
models.devqwen3.6-35b-a3bDevPass (LLM Gateway)$0.248$1.49$0262K
models.devqwen3.6-35b-a3bOpper$0.248$1.49$0262K
LiteLLMnovita/qwen/qwen3.6-35b-a3bN/A$0.248$1.49$0.0248N/A
LiteLLMwandb/Qwen/Qwen3.6-35B-A3BN/A$0.25$1.25$0.025N/A
LiteLLMqwen/qwen3.6-35b-a3bN/A$0.25$1.50$0.025N/A
LiteLLMqwen3.6-35b-a3bN/A$0.25$1.50$0.025N/A
LiteLLMscaleway/qwen/qwen3.6-35b-a3bN/A$0.25$1.50$0.025N/A
models.devqwen3.6-35b-a3bAIHubMix$0.254$1.52$0.0254262K
models.devQwen/Qwen3.6-35B-A3BSiliconFlow (China)$0.269$1.61$0262K
models.devqwen3.6-35b-a3bCortecs$0.279$1.67$0262K
models.devqwen3.6-35b-a3b302.AI$0.28$1.70$0262K
models.devqwen3.6-35b-a3bScaleway$0.2804$1.68$0128K
models.devqwen3.6-35b-a3bGreenPT$0.342$2.05$0262K
models.devQwen/Qwen3.6-35B-A3BEvroc$0.345$1.38$0262K
models.devqwen3.6-35b-a3bAlibaba / Qwen$0.375$2.25$0262K
models.devalibaba/qwen3.6-35b-a3bLLM Gateway$0.375$2.25$0262K
LiteLLMstreamlake/qwen3.6-35b-a3bN/A$0.375$2.25$0.0375N/A
models.devQwen/Qwen3.6-35B-A3BThinking Machines$0.45$1.33$0.0966K

Capabilities

  • Reasoning
  • Tool calling
  • Structured output
  • Attachments
  • Open weights
  • In: text
  • In: image
  • In: video
  • Out: text
Knowledge cutoff: 2025-04Released: 2026-04-17Output limit: 236K tokensFamily: qwen

Scores

Sparse coverage on purpose. Missing a score means we have not linked one yet, not that the model is unranked. Hover or tap the i next to any score for its source. Full boards on /benchmarks.

Arena rows are community-vote Elo from Arena AI, Artificial Analysis indices arrive via OpenRouter, and launch-eval figures are collected from vendor announcements, analyst writeups, and community benchmarks. Full boards and credits on /benchmarks.

See what this model costs you

The app reads the sessions your tools already wrote and prices this model's tokens at the published API rate. Free on your computer.