ModelflareAuthenticity, speed and price analysis

Modelclaude-first-topupData security level 4118 samples

Comparison summary

Claude Fable 5.1 on Modelflare: availability over the last 24 hours is 97.5%, ranking 2 of 2 relays with data (median 100.0%); time to first token is 1.34 s, ranking 1 of 2 (median 6.27 s); a coding session costs ¥4.38, ranking 2 of 5 (median ¥22.0).

Authenticity

Model consistency

Output distribution for the same requests on this relay and on the official API · higher is better

Probe agreement93.2%
Answers531 / 570
Model fingerprintClaude Fable 5.1
ClientAPI (Anthropic Messages)
Share of identity-probe answers that match the same model on the reference route. It only shows how routes differ from one another. Measured 2026-11-19 00:15 UTC. See all routes
ⓘ Method: see the blog post “Did the model really get dumber?” Read

Speed

Measured by time to first token (seconds) and output speed (tokens / second)

Time to first token

Seconds until the first token · lower is better

2 relays
ⓘ Output speed: not yet available from the live API; shown once connected

Price

Groups and models

GroupModelAvailabilityInput priceOutput pricePricing unit
claude-awardClaude Fable 5.198.99%¥16.60¥83.00Per million tokens
claude-stableClaude Fable 5.197.12%¥20.92¥104.58Per million tokens
claude-first-topupClaude Fable 5.197.46%¥1.99¥9.96Per million tokens
claude-premiumClaude Fable 5.198.68%¥33.20¥166.00Per million tokens
claude-tmp-cheapClaude Fable 5.198.82%¥3.98¥19.92Per million tokens

Cost per coding session

Claude Fable 5.1 · 2M input and 40k output tokens (¥) · split by token type · lower is better

5 relays
OutputInput
ⓘ USD prices are converted at 1 USD = 6.7128 CNY

Prices: cache hit, input and output

¥ / 1M tokens

Cache hitInputOutput
¥0¥20¥40¥60¥80¥100¥120¥140¥160ZNB.ai¥9.96ModelflareCheapAIApiporterCloudbridge

Cache

Coding requests repeat much of their context, so the cache hit rate largely decides what you actually pay. Drag the hit rate and the costs and ranking below are reweighted with cache prices.

Cache discount
98%
Cache hit ¥0.0498 · input ¥1.992 (per 1M tokens)
Measured hit rate
Pending
Measured by replaying multi-turn sessions: cached-read tokens in usage as a share of all input
Session cost at 80% hit rate
¥1.27
¥4.38 without cache, 71% saved

Cache-weighted session cost

Claude Fable 5.1 · of 2M input tokens, the hit share is billed at the cache price and the rest at the input price, plus 40k output (¥) · lower is better

Rank 2 / 5
80%Coding agents typically see 70%–90%
Cached inputUncached inputOutput
ⓘ Routes without a cache price are billed at the input price; cache write fees are not included

Stability

Availability

Request success rate, last 24 hours · higher is better

2 relays

Status of each model, last 24 hours

One cell per hour · green ok, yellow delayed, red failed

ModelGroupAvailabilityLast 24 hoursFirst tokenSamples
Gemini 3.7 Flashgemini-stable99.0%1.32 s196
GPT 6 Astraopenai-first-topup99.0%1.33 s192
Gemini 3.6 Flashgemini-stable98.9%1.79 s177
Claude Sonnet 5claude-first-topup98.9%1.29 s176
DeepSeek V4 Flashdeepseek-award98.8%1.27 s168
Claude Opus 5claude-first-topup98.6%0.98 s145
DeepSeek V4 Prodeepseek-award98.6%0.89 s142
GPT 6 Solopenai-first-topup98.5%1.21 s195
Gemini 3.8 Flashgemini-stable98.4%1.40 s123
DeepSeek V4.1 Flashdeepseek-stable98.3%1.30 s116
Claude Opus 5.5claude-first-topup98.2%1.57 s166
Grok 4.7grok-stable98.2%1.16 s162
GPT 6.1 Solopenai-first-topup98.0%0.87 s148
GPT 5.5openai-first-topup98.0%1.01 s195
GPT 5.6 Terraopenai-first-topup97.8%1.04 s136
Claude Fable 5claude-first-topup97.7%1.32 s129
Claude Opus 4.8claude-first-topup97.7%1.15 s171
Gemini 3.5 Flashgemini-stable97.6%1.78 s127
Qwen 3.8 Maxqwen-stable97.5%1.06 s200
GPT 5.6 Solopenai-first-topup97.5%1.31 s200
Grok 4.5grok-award97.5%1.84 s119
Claude Fable 5.1claude-first-topup97.5%1.34 s118
Claude Haiku 4.5claude-first-topup97.4%0.87 s154
Grok 4.6grok-award97.3%1.16 s189
Gemini 3.1 Pro Previewgemini-stable97.3%0.91 s185
Claude Haiku 5.5claude-award97.1%1.79 s171
GLM 5.2glm-award———
Gemini 4 Argongemini-stable———
Kimi K3kimi-award———
GLM 5.3 Flashglm-award———
GLM 5.3glm-award———
Gemini 3 Flash Previewgemini-premium———

About the site

Stable access to leading global models at a lower cost.

Modelflare is operated by US limited liability company Havenbyte LLC. It supports GPT, Claude, Gemini, Grok and common compatible protocols, plus over 40 image and video models.

Cache compensation
Selected OpenAI price-priority, stable and advanced groups offer daily cache-hit guarantees of 65%, 75% or 85%. If eligible requests fall short of the applicable target, Modelflare compensates the difference. Settled compensation can be viewed in the usage dashboard.

Top-up offers
A single US$20 top-up unlocks the GPT promotional group at a 0.015 pricing multiplier; a single US$50 top-up unlocks the Claude promotional group at a 0.03 multiplier.

Service details

  • Minimum top-up5 USD
  • Sign-up bonusUS$0.25
  • Support responseAny time
  • Payment methodsAlipay, WeChat Pay, Bank card, USDT, PayPal
  • China invoiceSupported
  • International invoiceSupported
  • RefundsSupported
  • PromotionsA single US$20 top-up unlocks the GPT promotional group at a 0.015 pricing multiplier; a single US$50 top-up unlocks the Claude promotional group at a 0.03 multiplier.

Strengths

  • Established operation and a named entity: operating for over six months, under US limited liability company Havenbyte LLC.
  • Broad model coverage: GPT, Claude, Gemini, Grok and other major models, plus over 40 image and video models.
  • Distinctive cost controls: selected OpenAI groups offer cache-hit guarantees with compensation for eligible shortfalls, visible in the usage dashboard after settlement.
  • Multiple group options: price-priority, stable, advanced and promotional groups cater to different needs.
  • Low-barrier trial: US$0.25 in signup credits lets users try the service before topping up.
  • Supports no-questions-asked refunds within 24 hours, reducing concerns about an initial top-up and trial.
  • Business purchasing supported: invoices issued in China and corporate bank transfers make business payment and expense reimbursement easier.

Limitations

  • Promotional groups require a top-up: a single US$20 payment unlocks GPT, while US$50 unlocks Claude.
  • Cache compensation has eligibility conditions: it covers selected groups and qualifying requests, rather than every model and request.
  • Group rules take time to understand: pricing multipliers, unlock requirements and compensation policies vary between groups.

FAQ

How much does Claude Fable 5.1 cost on Modelflare?

Input ¥1.992 and output ¥9.96 per 1M tokens; at 2M input and 40k output tokens, a coding session costs about ¥4.38, an API rate of 0.030.

How does the cache hit rate affect price?

On Modelflare, the cache-hit price is 3% of the input price. At an 80% hit rate a coding session costs about ¥1.27, versus about ¥4.38 without cache.Measured hit rates will replace this assumption once available.

Which models does Modelflare support?

Folkbench currently lists 32: Claude Fable 5.1, GPT 6 Astra, Claude Opus 5.5, GPT 6.1 Sol, GPT 6 Sol, DeepSeek V4.1 Flash, Claude Haiku 5.5, Claude Fable 5, Grok 4.7, Claude Opus 4.8, GLM 5.3 Flash, Claude Opus 5, GPT 5.6 Sol, Claude Sonnet 5, GPT 5.6 Terra, Kimi K3, GLM 5.3, Grok 4.6, Gemini 3.8 Flash, Claude Haiku 4.5, Gemini 4 Argon, Grok 4.5, DeepSeek V4 Pro, Qwen 3.8 Max, GLM 5.2, Gemini 3.7 Flash, Gemini 3.6 Flash, Gemini 3.1 Pro Preview, GPT 5.5, DeepSeek V4 Flash, Gemini 3.5 Flash, Gemini 3 Flash Preview.

What does the data security level mean?

Folkbench rates relays from 0 to 4 based on public policies and verifiable evidence; Modelflare is currently level 4. The check covers leaks in responses and error messages only, and does not prove data retention or training policies.

How often is this data updated?

Availability and time to first token use a 24-hour window, and this page syncs live data every 15 minutes.

Ordering follows site rules, including partnership tiers and operational weighting; some data are display samples.