ModelflareAuthenticity, speed and price analysis

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.
Modelgemini-stableData security level 4

Comparison summary

No measurements for Gemini 4 Argon yet
Other models on Modelflare already have measurements.
See DeepSeek V4 Pro

Gemini 4 Argon on Modelflare: a coding session costs ¥8.76, ranking 14 of 16 (median ¥3.08).

Authenticity

Model consistency

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

No probe results for this route yet
Probe results for the same model on other routes are in the degradation monitor.
Open the degradation monitor
ⓘ 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

No data for Modelflare0 relays
No data yet
ⓘ Output speed: not yet available from the live API; shown once connected

Price

Groups and models

GroupModelAvailabilityInput priceOutput pricePricing unit
gemini-stableGemini 4 ArgonNot probed yet¥3.98¥19.92Per million tokens

Cost per coding session

Gemini 4 Argon · 2M input and 40k output tokens (¥) · split by token type · lower is better

16 relays
OutputInput
ⓘ USD prices are converted at 1 USD = 6.7698 CNY

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
Not provided
Cache hit — · input ¥3.984 (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
¥8.76
¥8.76 without cache, 0% saved

Cache-weighted session cost

Gemini 4 Argon · 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 14 / 16
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

No data for Modelflare0 relays
No data yet

Status of each model, last 24 hours

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

ModelGroupAvailabilityLast 24 hoursFirst tokenSamples
DeepSeek V4 Prodeepseek-stable99.0%1.06 s194
Claude Opus 5claude-award99.0%1.21 s190
DeepSeek V4.1 Flashdeepseek-stable98.9%1.31 s189
GPT 6 Astraopenai-first-topup98.8%1.33 s165
Qwen 3.8 Maxqwen-stable98.8%1.06 s163
Gemini 3.8 Flashgemini-stable98.7%1.40 s155
Grok 4.6grok-stable98.5%1.84 s135
Claude Sonnet 5claude-award98.5%1.77 s199
Claude Fable 5.1claude-first-topup98.5%1.34 s197
DeepSeek V4 Flashdeepseek-stable98.4%1.72 s188
Gemini 3.7 Flashgemini-stable98.4%1.32 s186
GPT 5.6 Solopenai-first-topup98.4%1.31 s123
Claude Opus 5.5claude-first-topup98.3%1.57 s179
GLM 5.3glm-stable98.3%0.96 s171
Grok 4.7grok-stable98.1%1.16 s161
GPT 6.1 Solopenai-first-topup98.0%0.87 s151
GPT 5.5openai-first-topup97.8%1.01 s181
Claude Haiku 5.5claude-award97.7%1.79 s176
Gemini 3.6 Flashgemini-stable97.6%1.79 s125
Gemini 3.1 Pro Previewgemini-stable97.4%0.91 s154
GPT 6 Solopenai-first-topup97.3%1.20 s151
Grok 4.5grok-stable97.3%1.42 s188
GPT 5.6 Terraopenai-first-topup97.2%1.04 s180
Kimi K3kimi-stable97.2%1.16 s176
Claude Fable 5claude-award97.0%0.94 s101
Gemini 3.5 Flashgemini-stable97.0%1.78 s167
Claude Haiku 4.5claude-award———
Gemini 4 Argongemini-stable———
GLM 5.3 Flashglm-award———
Claude Opus 4.8claude-award———
GLM 5.2glm-award———

FAQ

How much does Gemini 4 Argon cost on Modelflare?

Input ¥3.984 and output ¥19.92 per 1M tokens; at 2M input and 40k output tokens, a coding session costs about ¥8.76, an API rate of 0.29.

How does the cache hit rate affect price?

Modelflare has not published a cache price for this route, so cache hits are billed at the input price.Measured hit rates will replace this assumption once available.

Which models does Modelflare support?

Folkbench currently lists 31: GPT 6 Astra, Claude Fable 5.1, Claude Opus 5.5, GPT 6.1 Sol, GPT 6 Sol, DeepSeek V4.1 Flash, Claude Haiku 5.5, Grok 4.7, GLM 5.3 Flash, Claude Fable 5, Claude Opus 5, Claude Opus 4.8, Claude Sonnet 5, GPT 5.6 Sol, Kimi K3, GLM 5.3, GPT 5.6 Terra, Gemini 4 Argon, Gemini 3.8 Flash, Grok 4.6, DeepSeek V4 Pro, Claude Haiku 4.5, Grok 4.5, Qwen 3.8 Max, GLM 5.2, Gemini 3.1 Pro Preview, Gemini 3.6 Flash, Gemini 3.7 Flash, Gemini 3.5 Flash, GPT 5.5, DeepSeek V4 Flash.

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.