Skip to main content

Clef Flash

Clef-flash is the fast 9B member of Cloudflare's open-source Clef decision model family, a fine-tune of Qwen3.5-9B served on Workers AI. It turns a state (text or structured JSON) plus a schema of typed questions into decisions, returning a calibrated probability for every allowed option of every question in a single forward pass instead of generating tokens. Use it for low-latency classification, routing, scoring, and guardrails through the Decisions API. Note: Workers AI currently truncates long text state to roughly the first 2K tokens, so content beyond that is not read; images are counted separately.

Model card on Hugging Face
Input / output priceUp to 50% off
$0.038 / $0.00$0.019 / $0.00 per 1M
Context
25K tokens
Released
Oct 1, 2026
Agent setup

Paste into Claude Code, Cursor, or Codex

Help me set up the Respan gateway: fetch and follow https://www.respan.ai/docs/agent-setup.md. Use model "clef-flash".

Read docs

Providers

5 providers, cheapest first, retired then OpenRouter last, priced per 1M tokens after gateway discounts.

ProviderInputOutput
Concentrateconcentrate/clef-flash
$0.019/M$0.00/M
DeepInfradeepinfra/Cloudflare/clef-flash
$0.038/M$0.00/M
Prime Intellectprime_intellect/cloudflare/clef-flash
$0.038/M—
MakoraRetiredmakora/clef-flash
$0.018/M$0.00/M
OpenRouter50% offopenrouter/clef-flash
$0.038/M$0.019/M$0.00/M

Is a provider down? OpenRouter status

Pricing

Averaged across 5 providers, in USD per 1M tokens after gateway discounts.

Average input
$0.03 per 1M
Average output
$0.00 per 1M

Cost by volume

Total cost from 0 to 1T tokens on the cheapest and most expensive provider.

Highest$0.038/MDeepInfra and Prime IntellectLowest$0.018/MMakora

Benchmarks

5 published scores from 1 source, each linked to where it was published.

Published scores

BenchmarkScore
BFCL case exactblog.cloudflare.com98.8%

Apps

Use Clef Flash in the tools you already run. Each guide points the app at the Respan gateway.

Setup guides for more apps are in the integration docs.

Clef Flash FAQ

Short answers, built from the data on this page.

Clef Flash is a model from Cloudflare, released on Oct 1, 2026. Clef-flash is the fast 9B member of Cloudflare's open-source Clef decision model family, a fine-tune of Qwen3.5-9B served on Workers AI. It turns a state (text or structured JSON) plus a schema of typed questions into decisions, returning a calibrated probability for every allowed option of every question in a single forward pass instead of generating tokens. Use it for low-latency classification, routing, scoring, and guardrails through the Decisions API. Note: Workers AI currently truncates long text state to roughly the first 2K tokens, so content beyond that is not read; images are counted separately.

On the Respan gateway, input starts at $0.018 per 1M tokens on Makora, and output starts at $0.00 per 1M tokens on every provider, after gateway discounts. Averaged across its 5 providers, it costs $0.03 per 1M input tokens and $0.00 per 1M output tokens.

Clef Flash is available through 5 providers: Concentrate, DeepInfra, Prime Intellect, Makora, and OpenRouter.

Clef Flash accepts up to 25K tokens of context on its largest provider route.

Point any OpenAI-compatible SDK at https://api.respan.ai/api/ with your Respan API key and set the model to "clef-flash". To set it up with a coding agent, copy the agent setup prompt at the top of this page.

Clef Flash has 5 published benchmark scores, including BFCL case exact 98.8% and API-Bank accuracy 93.1%. Each score links to where it was published; the data is collected by Respan.

Certified where it counts.

Built to meet the security and privacy standards that enterprise and healthcare teams require.

ISO 27001

The internationally recognized standard for information security management.

SOC 2

Secure, compliant management of your data across all of our systems.

GDPR

Operated under GDPR, the world's strictest standard for data privacy.

HIPAA

HIPAA compliant, with a BAA available for healthcare teams.

Works with your entire stack

Use Respan with your favorite frameworks and tools.

AnthropicAI21 LabsxAIVercel AI SDK
LangChainOpenRouterAssemblyAICursor
LiteLLMGroqBasetenMem0
CohereCogneeLlamaIndexFireworks
DeepSeekLinkupHaystackTogether AI
PerplexityInference.netPostHogRubyLLM
SlackMastraAzure OpenAIMistral
AWS BedrockMoonshotHyperspellBAML
ModaInstructorGoogle GeminiParasail
ReductoZapierAgnoNebius
OpenAINovita AIReplicateSuperagent

Built for AI agents.
Break less.
Ship more.