Data
Proprietary models converge. Open-weights models don't.
Short answer. 6 of the 9 models that two or more hosts price here cost the same on every host, within 1.15×. DeepSeek V4 Flash 0731 does not: $0.06 per million input tokens on DeepInfra against $0.44 on Novita AI, a 7.3× gap.
In plain words. Some AI models are offered by several companies, and each sets its own price. For most of them the price is about the same everywhere. For 3, it is not: one company charges 7.3× what another does.
When a model's maker sets a list price, the hosts that resell it follow that price and the market converges: 6 of the 9 models served by two or more hosts in this dataset cost the same wherever you run them (within 1.15×). When there is no list price to follow, because the weights are open and the maker does not sell them itself, each host charges what it likes and there is no pattern: 3 models show a real spread, the widest being DeepSeek V4 Flash 0731 at 7.3×, and 2 have no reference price at all. The list prices were verified on November 18, 2026 against the official pages of DeepSeek, Moonshot AI, Z.ai, Alibaba and Minimax. The comparison below covers 36 verified offerings of 14 models across 7 hosts.
Offerings verified between November 16, 2026 and November 18, 2026 against each host's official pricing page. Prices are USD per million tokens. How this is checked
Looking for first-party API prices (OpenAI, Anthropic, Google…)? See the main pricing table →
Where the price is the same
6 models where every host charges within 1.15× of the cheapest. On these models, the per-token price is not what separates the hosts.
- DeepSeek V4 Pro 0813 $1.32 in · $3.96 out
OpenRouter's $1.32 / $3.96 is the maker's list rate, which applies only during the maker's peak hours (Monday to Friday 01:00-04:00 and 06:00-10:00 UTC: 35 of the 168 hours in a week, 21%); the rest of the time that host, like the maker's own API, charges half, $0.66 / $1.98. Together AI and Baseten charge $1.32 / $3.96 at all hours.
- GLM-5.3 $1.40 in · $4.40 out
- GLM-5.3 Flash $0.15 in · $0.50 out
- Kimi K3 $2.85–$3.00 in · $14.25–$15.00 out 1.1×
- MiniMax M3 $0.30 in · $1.20 out
- Muse Spark Open $1.25 in · $4.25 out
Where the hosts' prices differ
3 models where the most expensive host charges more than 1.15× the cheapest for identical weights. Sorted by input price, cheapest first.
DeepSeek V4 Flash 0731 7.3× spread
DeepInfra charges $0.06 per million input tokens; Novita AI charges $0.44.
| Host | Input | Output | Context | Source |
|---|---|---|---|---|
| DeepInfra | $0.06 | $0.18 | 1.0M | deepinfra.com |
| Baseten | $0.13 | $0.26 | — | baseten.co |
| Novita AI | $0.44 | $1.32 | 1.0M | novita.ai |
gpt-oss-120b 3.0× spread
Novita AI charges $0.05 per million input tokens; Fireworks AI, Groq and Together AI charge $0.15.
| Host | Input | Output | Context | Source |
|---|---|---|---|---|
| Novita AI | $0.05 | $0.25 | 131K | novita.ai |
| Baseten | $0.10 | $0.50 | — | baseten.co |
| Together AI | $0.15 | $0.60 | 131K | docs.together.ai |
| Fireworks AI | $0.15 | $0.60 | 131K | docs.fireworks.ai |
| Groq | $0.15 | $0.60 | 131K | console.groq.com |
Llama 3.3 70B Instruct 1.4× spread
DeepInfra charges $0.10 per million input tokens; Novita AI charges $0.135.
Novita AI serves it with a 12K-token context; DeepInfra with 131K.
Models with a single host
7 models below have a single host; for 2 of them (DeepSeek V4 Flash 0731 and Qwen3.8 27B) there is no list price to show. There is nothing to compare here: each of these models is available from one host only.
| Model | Host | Input | Output | Context | Source |
|---|---|---|---|---|---|
| gpt-oss-20b | Groq | $0.075 | $0.30 | 131K | console.groq.com |
| Llama 3.1 8B Instruct | DeepInfra | $0.02 | $0.04 | 131K | deepinfra.com |
| Qwen3 32B | DeepInfra | $0.08 | $0.28 | 41K | deepinfra.com |
| Qwen3.8 Flash | OpenRouter | $0.15 | $0.47 | 1M | openrouter.ai |
| Qwen3.8 Max | Fireworks AI | $2.00 | $6.00 | — | docs.fireworks.ai |
| DeepSeek V4 Flash 0731 | OpenRouter (resellers only) | no list price | no list price | 1.3M | openrouter.ai |
| Qwen3.8 27B | OpenRouter (resellers only) | no list price | no list price | 1M | openrouter.ai |
DeepSeek V4 Flash 0731 is open-weights and has no model maker's list price on
OpenRouter: 27 resellers served it on September 15, 2026,
at prices that neither converge nor carry a struck-through list price, so there is no
reference figure to publish. OpenRouter's :floor suffix routes a request to the cheapest of them at that moment.
Qwen3.8 27B is open-weights and has no model maker's list price on
OpenRouter: 16 resellers served it on September 15, 2026,
at prices that neither converge nor carry a struck-through list price, so there is no
reference figure to publish. OpenRouter's :floor suffix routes a request to the cheapest of them at that moment.
Recently retired
14 offerings that were in this table and no longer can be: delisted, moved behind an enterprise contract, or no longer on the host's official price list. Hosts remove these quietly; we keep the record.
- MiniMax M3 on Together AI last $0.30 in · $1.20 out
Retired November 6, 2026 — Removed from Together's serverless inference on 2026-11-06: Together's deprecations page (docs.together.ai/docs/deprecations), read on 2026-11-16, says 'The following models are deprecated and will be removed from serverless inference on the date listed.' and prints, under 'Removal date | Model | Recommended replacement | Supported by on-demand dedicated endpoints |', '2026-11-06 | MiniMaxAI/MiniMax-M3 | MiniMaxAI/MiniMax-M3.1-Flash | Yes |'. On 2026-11-16 neither Together's pricing page (www.together.ai/pricing) nor its serverless models table (docs.together.ai/docs/serverless-models) listed it; the weekly check of that day reported the offering not found. The last reading that priced it was on 2026-11-09, when the pricing page still printed it. The price shown is that last one.
Together AI's deprecations page, read November 16, 2026:
2026-11-06 | MiniMaxAI/MiniMax-M3 | MiniMaxAI/MiniMax-M3.1-Flash | Yes |
- Qwen3.8 Max on Together AI last $2.00 in · $6.00 out
Retired November 4, 2026 — Removed from Together's serverless inference on 2026-11-04: Together's deprecations page (docs.together.ai/docs/deprecations), read on 2026-11-09, says 'The following models are deprecated and will be removed from serverless inference on the date listed.' and prints, under 'Removal date | Model | Recommended replacement | Supported by on-demand dedicated endpoints |', '2026-11-04 | Qwen/Qwen3.8-2.4T-A95B | Qwen/Qwen3.7-Max | No |'. On 2026-11-09 neither Together's pricing page (www.together.ai/pricing) nor its serverless models table (docs.together.ai/docs/serverless-models) listed it; the weekly check of that day reported the row not found, and the last reading that priced it was on 2026-11-02. The price shown is that last one.
Together AI's deprecations page, read November 9, 2026:
2026-11-04 | Qwen/Qwen3.8-2.4T-A95B | Qwen/Qwen3.7-Max | No |
- Llama 3.3 70B Instruct on Together AI last $1.04 in · $1.04 out
Retired October 22, 2026 — Removed from Together's serverless inference on 2026-10-22: Together's deprecations page (docs.together.ai/docs/deprecations), read on 2026-10-26, says 'The following models are deprecated and will be removed from serverless inference on the date listed.' and prints '2026-10-22 | meta-llama/Llama-3.3-70B-Instruct-Turbo | meta-models/Muse-Glimmer-30B | Yes |'. The same day Together's pricing page (www.together.ai/pricing) no longer listed it among its serverless models, only in its fine-tuning tables. The price shown is the last one read there, on 2026-10-19.
Together AI's deprecations page, read October 26, 2026:
2026-10-22 | meta-llama/Llama-3.3-70B-Instruct-Turbo | meta-models/Muse-Glimmer-30B | Yes |
- DeepSeek V4 Flash 0731 on Together AI last $0.14 in · $0.28 out
Retired October 22, 2026 — Removed from Together's serverless inference on 2026-10-22: Together's deprecations page (docs.together.ai/docs/deprecations), read on 2026-10-26, says 'The following models are deprecated and will be removed from serverless inference on the date listed.' and prints '2026-10-22 | deepseek-ai/DeepSeek-V4-Flash-0731 | deepseek-ai/DeepSeek-V4.1-Flash | Yes |'. The same day Together's pricing page (www.together.ai/pricing) no longer listed it among its serverless models, only in its fine-tuning tables. The price shown is the last one read there, on 2026-10-19.
Together AI's deprecations page, read October 26, 2026:
2026-10-22 | deepseek-ai/DeepSeek-V4-Flash-0731 | deepseek-ai/DeepSeek-V4.1-Flash | Yes |
- DeepSeek V4 Flash 0731 on Fireworks AI last $0.22 in · $0.66 out
Retired September 30, 2026 — No longer listed on Fireworks' pricing page (docs.fireworks.ai/serverless/pricing), read on 2026-09-30. The page says models not listed individually are priced by size; this site does not know whether the model is still served.
- DeepSeek V4 Pro 0813 on Fireworks AI last $1.32 in · $3.96 out
Retired September 30, 2026 — No longer listed on Fireworks' pricing page (docs.fireworks.ai/serverless/pricing), read on 2026-09-30. The page says models not listed individually are priced by size; this site does not know whether the model is still served.
- Kimi K2.6 on Fireworks AI last $0.95 in · $4.00 out
Retired September 30, 2026 — No longer listed on Fireworks' pricing page (docs.fireworks.ai/serverless/pricing), read on 2026-09-30. The page says models not listed individually are priced by size; this site does not know whether the model is still served.
- gpt-oss-120b on DeepInfra last $0.037 in · $0.17 out
Retired September 6, 2026 — Not listed on the official DeepInfra pricing page; previous figure came from OpenRouter.
- gpt-oss-20b on DeepInfra last $0.03 in · $0.14 out
Retired September 6, 2026 — Not listed on the official DeepInfra pricing page; previous figure came from OpenRouter.
- MiniMax M3 on DeepInfra last $0.28 in · $1.10 out
Retired September 6, 2026 — Not listed on the official DeepInfra pricing page; previous figure came from OpenRouter.
- Llama 3.3 70B Instruct on Groq last $0.59 in · $0.79 out
Retired September 6, 2026 — Moved to Groq Enterprise; no public per-token price on console.groq.com/docs/models.
- Llama 3.1 8B Instruct on Groq last $0.05 in · $0.08 out
Retired September 6, 2026 — Moved to Groq Enterprise; no public per-token price on console.groq.com/docs/models.
- Qwen3.8 Max on OpenRouter last $2.00 in · $6.00 out
Retired September 6, 2026 — No longer listed in the OpenRouter model catalog (checked via /api/v1/models).
- DeepSeek R1 on Replicate last $3.75 in · $10.00 out
Retired September 6, 2026 — Only per-token LLM on Replicate; a single offering has no comparative value in this table.
Verification
Every offering above was read on its host's official pricing page; dates range from November 16, 2026 to November 18, 2026.
Every price on this page is a link to the page it was read from. For OpenRouter, the
price shown is the model maker's own list price on OpenRouter's providers page for
that model, without promotional discounts (OpenRouter shows a discounted price with
the list price struck through). It is neither what a default request pays (by default
OpenRouter load-balances each request across several hosts, weighted towards the
cheaper ones, so the effective price varies per request) nor the lowest price
available through OpenRouter: resellers often undercut the maker, and the :floor suffix or sort: "price" gets you the cheapest of them
at that moment, a figure that moves on its own as promotions end and hosts come and
go (why the catalog number is not what you pay). Open-weights
models whose maker does not serve them on OpenRouter have no list price; they are listed
with "no list price" instead of a number. Offerings that could
not be verified on an official page are not shown as prices: they are either excluded
or listed under
"Recently retired" (last review November 6, 2026). Grouping threshold: hosts within 1.15× of the cheapest input
price count as "the same price".