ZMIME
Comparison · 3 models · Updated Nov 22, 2026

DeepSeek V4 Flash Vision Exp vs Toast 1 vs Mercury 2.5

No independent capability benchmark covers every model here yet. The score uses price and context window.No independent capability benchmark covers every model here yet. The score uses context window.

  1. DeepSeek

    DeepSeek V4 Flash Vision Exp

    Released Aug 21, 2026

    68/100
    • ECI—
    • Price$0.216 / $0.647
    • Context1M
  2. Mixedbread

    Toast 1

    Released Aug 13, 2026

    56/100
    • ECI—
    • Price$0.30 / $0.72
    • Context131K
  3. Inception

    Mercury 2.5

    Released Sep 8, 2026

    62/100
    • ECI—
    • Price$0.20 / $0.75
    • Context260K
  4. DeepSeek

    DeepSeek V4 Flash Vision Exp

    Released Aug 21, 2026

    64/100
    • ECI—
    • Price$0.216 / $0.647
    • Context1M
  5. Mixedbread

    Toast 1

    Released Aug 13, 2026

    32/100
    • ECI—
    • Price$0.30 / $0.72
    • Context131K
  6. Inception

    Mercury 2.5

    Released Sep 8, 2026

    43/100
    • ECI—
    • Price$0.20 / $0.75
    • Context260K
01 — Verdict

Capability evidence is incomplete

There is not enough shared capability evidence to name an overall winner. The scores (DeepSeek V4 Flash Vision Exp 68/100, Mercury 2.5 62/100, Toast 1 56/100) compare the available specifications and price. The score weighs price 71%, context window 29%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.There is not enough shared capability evidence to name an overall winner. The scores (DeepSeek V4 Flash Vision Exp 64/100, Mercury 2.5 43/100, Toast 1 32/100) compare the available specifications only. The score weighs context window 100%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.

  • CapabilityNot enough dataNo independent benchmark covers every model here yet
  • Lowest priceDeepSeek V4 Flash Vision ExpDeepSeek V4 Flash Vision Exp $0.323 · Mercury 2.5 $0.338 · Toast 1 $0.405 per 1M tokens (3:1 blend)
  • Longest contextDeepSeek V4 Flash Vision ExpDeepSeek V4 Flash Vision Exp 1,000,000 · Mercury 2.5 260,000 · Toast 1 131,000 tokens
  • Widest inputsDeepSeek V4 Flash Vision ExpDeepSeek V4 Flash Vision Exp: Text, Images · Toast 1: Text · Mercury 2.5: Text
  • Self-hostingDeepSeek V4 Flash Vision ExpPublishes downloadable weights (MIT)
How the score is built
MeasureWeightDeepSeek V4 Flash Vision ExpToast 1Mercury 2.5
Price71%706669
Context window29%643243
Specs & price only100%68/10056/10062/100

Left out because at least one model lacks the data: capability and inputs & features. The remaining weights were rescaled.

How the score is built
MeasureWeightDeepSeek V4 Flash Vision ExpToast 1Mercury 2.5
Context window100%643243
Specs only100%64/10032/10043/100

Left out because at least one model lacks the data: capability and inputs & features. The remaining weights were rescaled.

02 — Side by side

Every spec in one table

Highlighted cells lead their row. Unavailable specifications are marked “Not published”. Publisher results include their evaluation settings and source.

DeepSeek V4 Flash Vision Exp vs Toast 1 vs Mercury 2.5 specifications side by side
SpecificationDeepSeek V4 Flash Vision ExpDeepSeekToast 1MixedbreadMercury 2.5Inception
Capability
Capabilities Index (ECI)Not publishedNot publishedNot published
ECI rankNot publishedNot publishedNot published
ECI confidence intervalNot publishedNot publishedNot published
ECI evaluation dateNot publishedNot publishedNot published
Documented capabilitiesExperimental multimodal DeepSeek V4 Flash model for image understanding, coding, and agentic workSpecialized search model for knowledge-intensive questions, multi-step retrieval, and evidence synthesisReasoning model for deliberate analysis, multi-step problem solving, and tool use
Model parametersNot publishedNot publishedNot published
Output modalitiesTextTextText
Publisher-reported benchmarks
Terminal-Bench 2.1max effort83.9scoreReported resultNot publishedNot published
NL2Repomax effort57.7scoreReported resultNot publishedNot published
CyberGymmax effort75.3scoreReported resultNot publishedNot published
DeepSWEmax effort59.3scoreReported resultNot publishedNot published
Toolathlon-Verifiedmax effort75.9scoreReported resultNot publishedNot published
DSBench-Hard · internalmax effort63.6scoreReported resultNot publishedNot published
AutomationBench · publicmax effort25.7scoreReported resultNot publishedNot published
ApexBenchPublisher-reported result36.5pass@1Reported resultNot publishedNot published
Agents' Last ExamPublisher-reported result27.3scoreReported resultNot publishedNot published
ChartographyPublisher-reported result64.3scoreReported resultNot publishedNot published
ZeroBenchPublisher-reported result35pass@5Reported resultNot publishedNot published
Price per million tokens
Input$0.216$0.30$0.20 (best)
Output$0.647 (best)$0.72$0.75
Cached inputNot publishedNot published$0.02
Blended (3:1)$0.323 (best)$0.405$0.338
Long-context rateSame rateSame rateSame rate
Price sourceMedian of 15 providersMedian of 1 providersOfficial Inception API
Limits
Context window1,000,000 tokens (best)131,000 tokens260,000 tokens
Max inputNot publishedNot publishedNot published
Max output384,000 tokens (best)4,000 tokens65,536 tokens
Inputs and features
TextYesYesYes
ImagesYesNoNo
PDFsNoNoNo
AudioNoNoNo
VideoNoNoNo
ReasoningYesNoYeslow · medium · high
Tool callingYesYesYes
Structured outputNot publishedNot publishedYes
File attachmentsYesNoNo
Temperature controlYesYesYes
Reasoning controlalwaysNot publishedeffort
Availability
WeightsOpenMITProprietaryProprietary
API model IDNot publishedNot publishedmercury-2.5
API providers16 (best)11
ReleasedAug 21, 2026Aug 13, 2026Sep 8, 2026
Knowledge cutoffNot publishedNot publishedNot published
Publisher documentationModel weightsNot publishedPublisher documentation
Source metadata updatedSep 1, 2026Aug 13, 2026Sep 8, 2026
Data sourcesmodels.dev · Epoch AImodels.dev · Epoch AImodels.dev · Epoch AI
Catalog checkedNov 22, 2026Nov 22, 2026Nov 22, 2026
03 — Cost

What would a month cost?

Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.

  • DeepSeek V4 Flash Vision Exp$3.45
  • Toast 1$4.44
  • Mercury 2.5$3.50
04 — Questions

Which should you choose?

Which is better: DeepSeek V4 Flash Vision Exp, Toast 1 or Mercury 2.5?

There is not enough shared capability evidence to name an overall winner. The scores (DeepSeek V4 Flash Vision Exp 68/100, Mercury 2.5 62/100, Toast 1 56/100) compare the available specifications and price. The score weighs price 71%, context window 29%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.There is not enough shared capability evidence to name an overall winner. The scores (DeepSeek V4 Flash Vision Exp 64/100, Mercury 2.5 43/100, Toast 1 32/100) compare the available specifications only. The score weighs context window 100%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.

Which is cheaper, DeepSeek V4 Flash Vision Exp, Toast 1 or Mercury 2.5?

DeepSeek V4 Flash Vision Exp is cheaper at $0.216 input / $0.647 output per million tokens (median across 15 API providers). Mercury 2.5 costs $0.20 input / $0.75 output per million tokens (official Inception API price); Toast 1 costs $0.30 input / $0.72 output per million tokens (median across 1 API provider). At a typical mix of three input tokens to one output token, that is $0.323 per million tokens for DeepSeek V4 Flash Vision Exp versus $0.338 for Mercury 2.5 (1× as much) and $0.405 for Toast 1 (1.3× as much).

Which scores higher on benchmarks?

There is no independent benchmark that covers all three models yet. DeepSeek V4 Flash Vision Exp has not been scored yet, Toast 1 has not been scored yet and Mercury 2.5 has not been scored yet.

Which is better for coding?

There are no published SWE-bench Verified results for DeepSeek V4 Flash Vision Exp, Toast 1 and Mercury 2.5 yet, so there is no like-for-like coding score. Test both on a sample of your own tasks. All three support tool calling for agent workflows.

Which has the bigger context window?

DeepSeek V4 Flash Vision Exp has the largest context window at 1,000,000 tokens, against 260,000 for Mercury 2.5 and 131,000 for Toast 1. Maximum output per response: DeepSeek V4 Flash Vision Exp up to 384,000, Toast 1 up to 4,000, Mercury 2.5 up to 65,536 tokens.

Which can read images, PDFs, audio or video?

DeepSeek V4 Flash Vision Exp accepts text and images; Toast 1 accepts text; Mercury 2.5 accepts text. DeepSeek V4 Flash Vision Exp handles the widest range of inputs.

Are any of these open source?

DeepSeek V4 Flash Vision Exp publishes its weights (MIT) and can be self-hosted; Toast 1 and Mercury 2.5 is proprietary.

Which is newer?

Mercury 2.5 is the newest, released Sep 8, 2026. DeepSeek V4 Flash Vision Exp came out Aug 21, 2026; Toast 1 came out Aug 13, 2026.

How do you decide the winner?

This rating uses price (71%, blended price per million tokens (3 input : 1 output), log scale); context window (29%, maximum tokens per request, log scale). Dimensions missing for any model are dropped and the remaining weights rescaled, so every model is judged on the same evidence. Specs and prices come from public model listings and the labs’ own API pages; capability scores come from independent benchmark runs. Data updated Nov 22, 2026.This rating uses context window (100%, maximum tokens per request, log scale). Dimensions missing for any model are dropped and the remaining weights rescaled, so every model is judged on the same evidence. Specs and prices come from public model listings and the labs’ own API pages; capability scores come from independent benchmark runs. Data updated Nov 22, 2026.