Models

Qwen3-235B-A22B-Instruct-2507

deepinfra · 262K ctx · 9 providers · updated 2026-08-05 00:15 UTC

Cheapest
$0.078 via Requesty
Avg price
$0.619 /1M
providers
9
(3 × $0.071 + $0.100) ÷ 4 = $0.078/1M — the $/1M figure blends input and output at 3:1 — that is the only way models with two different rates can be ranked on one axis. Your actual rate depends on your own input:output mix — input only $0.071, 3:1 $0.078, 1:1 $0.085, output only $0.100 per 1M.

The board shows this model's cheapest measured offer ($0.078/1M); the smaller figure under it is the mean of the 13 offers listed below ($0.619/1M). Add those up and divide — it matches.

ProviderRouter / Source$ in /1M$ out /1MTTFTTPSUptimeEvidence
requesty Requesty $0.071$0.100 — — — API-measured
deepinfra HuggingFace Router $0.090$0.550 477ms 29 — API-measured
novita Pricebook (LiteLLM) $0.090$0.580 — — — Official list
novita HuggingFace Router $0.090$0.580 808ms 50 — API-measured
novita-ai Novita AI $0.090$0.580 — — — API-measured
deepinfra Pricebook (LiteLLM) $0.090$0.600 — — — Official list
nscale HuggingFace Router $0.200$0.600 714ms 13 — API-measured
burncloud burncloud $0.200$0.800 — — — API-measured
fireworks_ai Pricebook (LiteLLM) $0.220$0.880 — — — Official list
replicate Pricebook (LiteLLM) $0.264$1.06 — — — Official list
scaleway Pricebook (LiteLLM) $0.750$2.25 — — — Official list
scaleway HuggingFace Router $0.855$2.56 585ms 99 — API-measured
crusoe Pricebook (LiteLLM) $3.00$3.00 — — — Official list

Price trend

$0.205 $0.0783 2026-07-06 → 2026-08-05 · 31d 2026-07-06 · O 0.0925 H 0.0925 L 0.0925 C 0.0925 $/1M2026-07-07 · O 0.0925 H 0.0925 L 0.0925 C 0.0925 $/1M2026-07-08 · O 0.0925 H 0.0925 L 0.0925 C 0.0925 $/1M2026-07-09 · O 0.0925 H 0.0925 L 0.0925 C 0.0925 $/1M2026-07-10 · O 0.0925 H 0.0925 L 0.0925 C 0.0925 $/1M2026-07-11 · O 0.0925 H 0.0925 L 0.0925 C 0.0925 $/1M2026-07-12 · O 0.205 H 0.205 L 0.205 C 0.205 $/1M2026-07-13 · O 0.205 H 0.205 L 0.205 C 0.205 $/1M2026-07-14 · O 0.205 H 0.205 L 0.205 C 0.205 $/1M2026-07-15 · O 0.205 H 0.205 L 0.205 C 0.205 $/1M2026-07-16 · O 0.0783 H 0.0783 L 0.0783 C 0.0783 $/1M2026-07-17 · O 0.0783 H 0.0783 L 0.0783 C 0.0783 $/1M2026-07-18 · O 0.0783 H 0.0783 L 0.0783 C 0.0783 $/1M2026-07-19 · O 0.0783 H 0.0783 L 0.0783 C 0.0783 $/1M2026-07-20 · O 0.0783 H 0.0783 L 0.0783 C 0.0783 $/1M2026-07-21 · O 0.0783 H 0.0783 L 0.0783 C 0.0783 $/1M2026-07-22 · O 0.0783 H 0.0783 L 0.0783 C 0.0783 $/1M2026-07-23 · O 0.0783 H 0.0783 L 0.0783 C 0.0783 $/1M2026-07-24 · O 0.0783 H 0.0783 L 0.0783 C 0.0783 $/1M2026-07-25 · O 0.0783 H 0.0783 L 0.0783 C 0.0783 $/1M2026-07-26 · O 0.0783 H 0.0783 L 0.0783 C 0.0783 $/1M2026-07-27 · O 0.0783 H 0.0783 L 0.0783 C 0.0783 $/1M2026-07-28 · O 0.0783 H 0.0783 L 0.0783 C 0.0783 $/1M2026-07-29 · O 0.0783 H 0.0783 L 0.0783 C 0.0783 $/1M2026-07-30 · O 0.0783 H 0.0783 L 0.0783 C 0.0783 $/1M2026-07-31 · O 0.0783 H 0.0783 L 0.0783 C 0.0783 $/1M2026-08-01 · O 0.0783 H 0.0783 L 0.0783 C 0.0783 $/1M2026-08-02 · O 0.0783 H 0.0783 L 0.0783 C 0.0783 $/1M2026-08-03 · O 0.0783 H 0.0783 L 0.0783 C 0.0783 $/1M2026-08-04 · O 0.0783 H 0.0783 L 0.0783 C 0.0783 $/1M2026-08-05 · O 0.0783 H 0.0783 L 0.0783 C 0.0783 $/1M

Cheapest blended price, last 31 days (USD/1M): $0.0925 → $0.0925 → $0.0925 → $0.0925 → $0.0925 → $0.0925 → $0.205 → $0.205 → $0.205 → $0.205 → $0.0783 → $0.0783 → $0.0783 → $0.0783 → $0.0783 → $0.0783 → $0.0783 → $0.0783 → $0.0783 → $0.0783 → $0.0783 → $0.0783 → $0.0783 → $0.0783 → $0.0783 → $0.0783 → $0.0783 → $0.0783 → $0.0783 → $0.0783 → $0.0783

Data & method

Cheapest ranked by blended = (3×in + out) ÷ 4; performance columns show only when a source provides them, never estimated. “Official list” = LiteLLM open pricebook (MIT); “API-measured” = provider/aggregator public APIs. Machine-readable data: /api/v1/models/qwen3-235b-a22b-instruct-2507.json. Free reuse requires attribution to tkx.org.

About

Qwen3-235B-A22B-Instruct-2507 is a large language model served by multiple inference providers on AI model marketplaces, designed for natural language processing tasks. It is listed under the organization tag "deepinfra" on these platforms.

AI-generated summary from public information — is this yours?

FAQ

How much does Qwen3-235B-A22B-Instruct-2507 cost?

Cheapest measured offer right now: $0.071/1M input, $0.1/1M output via requesty — across 9 tracked providers, refreshed hourly.

Who serves Qwen3-235B-A22B-Instruct-2507?

9 providers currently serve it. The table above lists each with input/output price, TTFT, TPS, uptime and an evidence tier.

Is the price of Qwen3-235B-A22B-Instruct-2507 going up or down?

The daily candles above track the cheapest blended price ($/1M, 3:1 in:out). TKX snapshots every hour, so drops and hikes show up the same day they happen.

Related analysis

Back to rankings