Modelflare · Claude Fable 5Authenticity, speed and price analysis

⇆ Compare Visit website

Modelclaude-awardData security level 4153 samples

Authenticity90 / 90

Fingerprint Claude Fable 5 · 90 answers

100Probe agreement
(%)

Speed#1 / 3

First token 0.93 s · Output speed Not provided

0.93First token
(seconds)

Price#2 / 3

Input ¥16.6 · Output ¥83 · Cache discount Not provided

¥36.5Cost per
coding session

Availability#1 / 3

7 days 98.0% · 30 days 98.0%

98.7%Last 24 hours
availability

Comparison summary

Claude Fable 5 on Modelflare: availability over the last 24 hours is 98.7%, ranking 1 of 3 relays with data (median 83.3%); time to first token is 0.93 s, ranking 1 of 3 (median 1.95 s); a coding session costs ¥36.5, ranking 2 of 3 (median ¥36.5).

稳定接入 SOTA 模型。更优的模型价格。 Modelflare 为 AI 工具、应用和 Agent 提供稳定的模型请求服务，聚合多类前沿 SOTA 模型，并提供清晰的价格、用量与请求状态。

Authenticity

Model consistency

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

Probe agreement100%

Answers90 / 90

Model fingerprintClaude Fable 5

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 2026-11-12 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

3 relays

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

Price

Cost per coding session

Claude Fable 5 · 2M input and 40k output tokens (¥) · split by token type · lower is better

3 relays

OutputInput

ⓘ USD prices are converted at 1 USD = 6.7698 CNY

Prices: cache hit, input and output

¥ / 1M tokens

Cache hitInputOutput

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 ¥16.6 (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

¥36.5

¥36.5 without cache, 0% saved

Cache-weighted session cost

Claude Fable 5 · 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 / 3

Cache hit rate80%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

3 relays

Status of each model, last 24 hours

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

Model	Group	Availability	First token	Samples
DeepSeek V4 Pro	deepseek-stable	99.0%	1.35 s	199
Claude Opus 5	claude-award	99.0%	1.21 s	195
Claude Fable 5	claude-award	98.7%	0.93 s	153
GPT 6.1 Sol	openai-first-topup	98.7%	0.87 s	148
Gemini 3.6 Flash	gemini-stable	98.6%	1.79 s	146
Gemini 3.8 Flash	gemini-stable	98.6%	1.40 s	139
GPT 6 Astra	openai-first-topup	98.5%	1.33 s	135
Grok 4.6	grok-stable	98.5%	6.17 s	197
GLM 5.3	glm-stable	98.5%	0.96 s	197
Gemini 3.7 Flash	gemini-stable	98.5%	1.32 s	130
Grok 4.7	grok-stable	98.3%	5.11 s	176
Claude Fable 5.1	claude-first-topup	98.2%	1.34 s	170
Gemini 3.1 Pro Preview	gemini-stable	98.2%	0.91 s	110
DeepSeek V4.1 Flash	deepseek-stable	98.2%	1.31 s	217
GPT 5.5	openai-first-topup	98.1%	1.01 s	161
Gemini 3.5 Flash	gemini-stable	98.1%	1.78 s	103
Claude Haiku 5.5	claude-first-topup	98.0%	0.94 s	200
Kimi K3	kimi-stable	98.0%	1.16 s	198
Qwen 3.8 Max	qwen-stable	98.0%	1.06 s	147
GPT 5.6 Terra	openai-first-topup	97.9%	1.04 s	141
GPT 6 Sol	openai-first-topup	97.7%	1.21 s	132
Claude Sonnet 5	claude-award	97.7%	1.77 s	130
Claude Opus 5.5	claude-first-topup	97.3%	1.57 s	146
DeepSeek V4 Flash	deepseek-stable	97.2%	1.72 s	145
Grok 4.5	grok-stable	97.2%	5.20 s	215
GPT 5.6 Sol	openai-first-topup	97.1%	1.31 s	102

Service details

Minimum top-up5 USD

Sign-up bonus无

Support response随时

Payment methodsAlipay, WeChat Pay, Bank card, USDT, PayPal

China invoice支持

International invoice支持

Refunds支持

Promotions充值 $20 有优惠

Strengths

前端设计美观，接入流程相对直观。
FolkBench 综合评分较高，基础请求稳定：OpenAI 基础请求通过率 100%，Function Calling 与结构化输出均通过 100%。

Limitations

降低低价组充值门槛，使更多用户可以体验低价组

FAQ

How much does Claude Fable 5 cost on Modelflare?

Input ¥16.6 and output ¥83 per 1M tokens; at 2M input and 40k output tokens, a coding session costs about ¥36.5, an API rate of 0.25.

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