Inference providers · open weights · DeepSeek
DeepSeek V4 Flash 0731
Open-weights model published by DeepSeek; the API prices below are set by the 3 hosts that serve it, not by DeepSeek. There is no maker's list price to compare with: DeepSeek publishes the weights, not a per-token rate. Each figure was read on that host's own pricing page and links to it, with the date it was checked.
What each host charges
3 hosts, from $0.06 (DeepInfra) to $0.44 (Novita AI) per 1M input tokens: a 7.3× spread. Above the 1.15× line AI Signal draws, so the choice of host is a price decision.
| Host | Input | Output | Cached input | Context served | Checked | Source |
|---|---|---|---|---|---|---|
| DeepInfra | $0.06 | $0.18 | $0.015 | 1.0M tokens | November 16, 2026 | deepinfra.com |
| Baseten | $0.13 | $0.26 | $0.028 | — | November 16, 2026 | baseten.co |
| Novita AI | $0.44 | $1.32 | $0.028 | 1.0M tokens | November 16, 2026 | novita.ai |
| OpenRouter | no list price: OpenRouter lists resellers only, none of them DeepSeek (27 endpoints on September 15, 2026) | September 9, 2026 | openrouter.ai | |||
DeepInfra charges $0.06 per 1M input tokens and Novita AI $0.44 for the same weights; on output, $0.18 against $1.32.
Hosts that no longer price it
Offerings AI Signal tracked and stopped listing, with the date and the reason. They are kept because nobody else records when a host drops a model.
- Together AI removed October 22, 2026 · last listed at $0.14 in · $0.28 out Together AI removed it from serverless on October 22, 2026:
2026-10-22 | deepseek-ai/DeepSeek-V4-Flash-0731 | deepseek-ai/DeepSeek-V4.1-Flash | Yes |
(docs.together.ai, read October 26, 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. - Fireworks AI removed September 30, 2026 · last listed at $0.22 in · $0.66 out 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.
Mentioned in
5 posts on AI Signal cite DeepSeek V4 Flash 0731. The sentence is the post's own, taken from where it links here.
-
AI Pricing This Week: Large 4 Cut, New Hosts, Oct 26-Nov 1 · November 7, 2026
| Open model | Lowest input price | Highest input price | Highest ÷ lowest | |---|---|---|---| | DeepSeek V4 Flash 0731 | $0.06, DeepInfra | $0.44, Novita AI | 7.3× | | gpt-oss-120b | $0.05, Novita AI | $0.15, Fireworks AI, Groq and Together AI | 3.0× | | Llama 3.3 70B Instruct | $0.10, DeepInfra | $0.135, Novita AI | 1.4× |
-
DeepSeek V4 Flash, gpt-oss-120b and Llama 3.3 70B Pricing by Host: Up to 7.3× Apart on October 29, 2026 · October 29, 2026
OpenRouter also lists this model, but it has no list price there: no endpoint is the model's maker, so it is shown apart on the DeepSeek V4 Flash 0731 page.
-
AI Pricing This Week: OpenAI Shutdown, Mistral, Oct 19-25 · October 26, 2026
Each model now has one current host, so Llama 3.3 70B Instruct and DeepSeek V4 Flash 0731 are kept as records, with Together's offer listed apart from the price table.
-
Same Open Model, Different Host: What a Month Costs · October 12, 2026
| Model | Hosts priced | Cheapest host, month | Most expensive host, month | Difference | |---|---|---|---|---| | Llama 3.3 70B Instruct | 2 | DeepInfra $16.40 | Together AI $124.80 | $108.40 (7.61×) | | DeepSeek V4 Flash 0731 | 2 | DeepInfra $9.60 | Together AI $19.60 | $10.00 (2.04×) | | Kimi K3 | 4 | DeepInfra $570.00 | Together AI, Fireworks AI, OpenRouter $600.00 | $30.00 (1.05×) | | GLM-5.3 | 3 | $228.00 on every host | $228.00 on every host | none | | gpt-oss-120b | 3 | $27.00 on every host | $27.00 on every host | none | | MiniMax M3 | 3 | $54.00 on every host | $54.00 on every host | none |
-
Five Things Decide What You Pay for a Model, and Only One of Them Is the Model · September 15, 2026
DeepSeek V4 Flash 0731 spans 2.75× across its three hosts, from $0.08 on DeepInfra to $0.22 on Fireworks.
Recorded price changes
Every change AI Signal has recorded for a host's price of DeepSeek V4 Flash 0731, with the date it took or takes effect and why. Changes of our own rule are listed too, and say so.
-
October 29, 2026 · DeepInfra · correction of our own reading
Correction of our own reading, not a price change by DeepInfra. DeepInfra's pricing page prints a cached input price inside the input cell of some models ('$0.06 / $0.015 cached'), and two offerings of this dataset did not carry it: DeepSeek V4 Flash 0731 ($0.015) and Kimi K3 ($0.285) per million tokens, read on October 29, 2026. Both rows already printed it when read on September 30, 2026, as the quotes in their notes show; the figure was not carried into the offering. Input and output prices are unchanged.
-
September 30, 2026 · DeepInfra · price down 1.3×
DeepInfra lowered the input price of DeepSeek V4 Flash 0731 from $0.08 to $0.06 per million tokens; output stays at $0.18. It was $0.08 when AI Signal read DeepInfra's pricing page on September 6, 2026 and $0.06 when it read it again on September 30, 2026; the exact day of the change is not known, so the date here is the day it was seen.
-
September 11, 2026 · OpenRouter · reference price withdrawn
DeepSeek's own endpoint for DeepSeek V4 Flash 0731 disappeared from OpenRouter between the afternoon of September 9, 2026, when it was still listed at $0.22 / $0.66 and this row was verified against it, and the 04:30 UTC check of September 10, which found no DeepSeek endpoint; it had not returned by September 11. DeepSeek still serves V4 Pro 0813 on OpenRouter, so this is specific to this model, not a general withdrawal. AI Signal's OpenRouter column shows the model maker's list price, and for this model there is now none to show: the column moves from $0.22 / $0.66 per million tokens (last verified September 9) to "no list price". Nothing changed in our criterion, and no host changed a price; the provider withdrew its endpoint. The model is still served on OpenRouter by resellers (28 listed, 26 healthy on September 11), reachable with :floor; that day the catalog quoted $0.065 / $0.18 via Relace.
-
September 9, 2026 · OpenRouter · change of our criterion · figure shown here up 4.4×
The published OpenRouter price of DeepSeek V4 Flash 0731 rises 4.4x on input ($0.05 to $0.22) and 4.1x on output ($0.16 to $0.66). No host raised its rate. The number changes because the rule changed: until September 9, 2026 this column showed the cheapest healthy endpoint at the moment of checking (OpenInference); from September 9 it shows the model maker's own price on OpenRouter's providers page, without promotional discounts (DeepSeek, $0.22 / $0.66). Cheaper resellers still exist and are still reachable with :floor.
On OpenRouter
On September 15, 2026 OpenRouter listed 27 endpoints for DeepSeek V4 Flash 0731, 24 of them healthy, from $0.04 (OpenInference) to $0.44 per 1M input tokens. The figure OpenRouter's catalog shows for the model, $0.06 / $0.12 (Relace), is the 3rd cheapest of those 27. None of them is DeepSeek: all are resellers, which is why AI Signal shows no OpenRouter price for the model. DeepInfra, Baseten and Novita AI, priced above from their own pages, are among them. Together AI, which AI Signal stopped listing on October 22, 2026 because its own pricing page carries no price for the model, serves it once through OpenRouter; that is a reseller listing, not a published price, so the row stays out. Fireworks AI, which AI Signal stopped listing on September 30, 2026 because its own pricing page carries no price for the model, serves it once through OpenRouter; that is a reseller listing, not a published price, so the row stays out.
Why the catalog figure is not what a request pays →
Specifications
| Weights published by | DeepSeek |
|---|---|
| Context length (maker) | 1.0M tokens |
| Context served by hosts | 1.0M tokens |
| API model ids | DeepInfra: deepseek-ai/DeepSeek-V4-Flash-0731; Baseten: deepseek-ai/DeepSeek-V4-Flash-0731; Novita AI: deepseek/deepseek-v4-flash-0731 |
| Hosts with a verified price | 3 |
Host prices verified on November 16, 2026, each on the host's own pricing page linked in the table above, never from a reseller catalog or a third-party table. Maker and context length from DeepSeek's model card, checked September 15, 2026 (max_position_embeddings 1048576 in the model's config.json). How the data is checked.
Every open model, every host, one table →
When comparing hosts is worth it, and when it is not →
What the OpenRouter price means, and what a request actually pays →